Search Results for author: Wei Wei

Found 265 papers, 97 papers with code

Incorporating Casual Analysis into Diversified and Logical Response Generation

no code implementations COLING 2022 Jiayi Liu, Wei Wei, Zhixuan Chu, Xing Gao, Ji Zhang, Tan Yan, Yulin kang

Although the Conditional Variational Auto-Encoder (CVAE) model can generate more diversified responses than the traditional Seq2Seq model, the responses often have low relevance with the input words or are illogical with the question.

Response Generation

Risk-aware Direct Preference Optimization under Nested Risk Measure

1 code implementation26 May 2025 Lijun Zhang, Lin Li, Yajie Qi, Huizhong Song, Yaodong Yang, Jun Wang, Wei Wei

This approach formulates a constrained risk-aware advantage function maximization problem and then converts the Bradley-Terry model into a token-level representation.

Step-level Reward for Free in RL-based T2I Diffusion Model Fine-tuning

1 code implementation25 May 2025 Xinyao Liao, Wei Wei, Xiaoye Qu, Yu Cheng

Recent advances in text-to-image (T2I) diffusion model fine-tuning leverage reinforcement learning (RL) to align generated images with learnable reward functions.

Denoising Reinforcement Learning (RL)

SATORI-R1: Incentivizing Multimodal Reasoning with Spatial Grounding and Verifiable Rewards

1 code implementation25 May 2025 Chuming Shen, Wei Wei, Xiaoye Qu, Yu Cheng

Our analysis of the attention map confirms enhanced focus on critical regions, which brings improvements in accuracy.

Image Captioning Multimodal Reasoning +3

Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control

no code implementations23 May 2025 Alireza Rezazadeh, Zichao Li, Ange Lou, Yuying Zhao, Wei Wei, Yujia Bao

Complex tasks are increasingly delegated to ensembles of specialized LLM-based agents that reason, communicate, and coordinate actions-both among themselves and through interactions with external tools, APIs, and databases.

Transfer Learning

No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves

1 code implementation5 May 2025 Dengyang Jiang, Mengmeng Wang, Liuzhuozheng Li, Lei Zhang, Haoyu Wang, Wei Wei, Guang Dai, Yanning Zhang, Jingdong Wang

Recent studies have demonstrated that learning a meaningful internal representation can both accelerate generative training and enhance the generation quality of diffusion transformers.

Image Generation Representation Learning

AlignRAG: Leveraging Critique Learning for Evidence-Sensitive Retrieval-Augmented Reasoning

1 code implementation21 Apr 2025 Jiaqi Wei, Hao Zhou, Xiang Zhang, Di Zhang, Zijie Qiu, Wei Wei, Jinzhe Li, Wanli Ouyang, Siqi Sun

Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs).

RAG Retrieval +2

Fourier Feature Attribution: A New Efficiency Attribution Method

no code implementations2 Apr 2025 Zechen Liu, Feiyang Zhang, Wei Song, Xiang Li, Wei Wei

The study of neural networks from the perspective of Fourier features has garnered significant attention.

feature selection Specificity

Learning a Canonical Basis of Human Preferences from Binary Ratings

no code implementations31 Mar 2025 Kailas Vodrahalli, Wei Wei, James Zou

We find that a small subset of 21 preference categories (selected from a set of nearly 5, 000 distinct preferences) captures >89% of preference variation across individuals.

Contextual Preference Collaborative Measure Framework Based on Belief System

no code implementations31 Mar 2025 Hang Yu, Wei Wei, Zheng Tan, Jing-lei Liu

To reduce the human intervention in the preference measure process, this article proposes a preference collaborative measure framework based on an updated belief system, which is also capable of improving the accuracy and efficiency of preferen-ce measure algorithms. Firstly, the distance of rules and the average internal distance of rulesets are proposed for specifying the relationship between the rules. For discovering the most representative preferences that are common in all users, namely common preference, a algorithm based on average internal distance of ruleset, PRA algorithm, is proposed, which aims to finish the discoveryprocess with minimum information loss rate. Furthermore, the concept of Common belief is proposed to update the belief system, and the common preferences are the evidences of updated belief system. Then, under the belief system, the proposed belief degree and deviation degree are used to determine whether a rule confirms the belief system or not and classify the preference rules into two kinds(generalized or personalized), and eventually filters out Top-K interesting rules relying on belief degree and deviation degree. Based on above, a scalable interestingness calculation framework that can apply various formulas is proposed for accurately calculating interestingness in different conditions. At last, IMCos algorithm and IMCov algorithm are proposed as exemplars to verify the accuracy and efficiency of the framework by using weighted cosine similarity and correlation coefficients as belief degree. In experiments, the proposed algorithms are compared to two state-of-the-art algorithms and the results show that IMCos and IMCov outperform than the other two in most aspects.

A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond

1 code implementation27 Mar 2025 Xiaoye Qu, Yafu Li, Zhaochen Su, Weigao Sun, Jianhao Yan, Dongrui Liu, Ganqu Cui, Daizong Liu, Shuxian Liang, Junxian He, Peng Li, Wei Wei, Jing Shao, Chaochao Lu, Yue Zhang, Xian-Sheng Hua, BoWen Zhou, Yu Cheng

Recent Large Reasoning Models (LRMs), such as DeepSeek-R1 and OpenAI o1, have demonstrated strong performance gains by scaling up the length of Chain-of-Thought (CoT) reasoning during inference.

Survey

Enhancing Retrieval Systems with Inference-Time Logical Reasoning

no code implementations22 Mar 2025 Felix Faltings, Wei Wei, Yujia Bao

This approach enables the retrieval process to handle complex logical reasoning without compromising computational efficiency.

Computational Efficiency Logical Reasoning +2

Enhancing Retrieval for ESGLLM via ESG-CID -- A Disclosure Content Index Finetuning Dataset for Mapping GRI and ESRS

no code implementations10 Mar 2025 Shafiuddin Rehan Ahmed, Ankit Parag Shah, Quan Hung Tran, Vivek Khetan, Sukryool Kang, Ankit Mehta, Yujia Bao, Wei Wei

Frameworks like the Global Reporting Initiative (GRI) and the new European Sustainability Reporting Standards (ESRS) aim to standardize ESG reporting, yet generating comprehensive reports remains challenging due to the considerable length of ESG documents and variability in company reporting styles.

RAG Retrieval +2

Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think

1 code implementation CVPR 2025 Jie Tian, Xiaoye Qu, Zhenyi Lu, Wei Wei, Sichen Liu, Yu Cheng

(3) With the above two-stage models excelling in motion controllability and degree, we decouple the relevant parameters associated with each type of motion ability and inject them into the base I2V-DM.

Denoising Image to Video Generation

MMSciBench: Benchmarking Language Models on Multimodal Scientific Problems

no code implementations27 Feb 2025 Xinwu Ye, Chengfan Li, Siming Chen, Xiangru Tang, Wei Wei

Recent advances in large language models (LLMs) and vision-language models (LVLMs) have shown promise across many tasks, yet their scientific reasoning capabilities remain untested, particularly in multimodal settings.

Benchmarking Visual Reasoning

Brain-inspired analogical mixture prototypes for few-shot class-incremental learning

no code implementations26 Feb 2025 Wanyi Li, Wei Wei, Yongkang Luo, Peng Wang

Inspired by the brain's mechanisms for categorization and analogical learning, we propose a novel approach called Brain-inspired Analogical Mixture Prototypes (BAMP).

class-incremental learning Few-Shot Class-Incremental Learning +1

Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment

1 code implementation24 Feb 2025 Chenghao Fan, Zhenyi Lu, Sichen Liu, Chengfeng Gu, Xiaoye Qu, Wei Wei, Yu Cheng

While Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning for Large Language Models (LLMs), its performance often falls short of Full Fine-Tuning (Full FT).

image-classification Image Classification +4

KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse

1 code implementation21 Feb 2025 Jingbo Yang, Bairu Hou, Wei Wei, Yujia Bao, Shiyu Chang

We describe KVLink, an approach for efficient key-value (KV) cache reuse in large language models (LLMs).

Question Answering

H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking

1 code implementation18 Feb 2025 Martin Kuo, Jianyi Zhang, Aolin Ding, Qinsi Wang, Louis DiValentin, Yujia Bao, Wei Wei, Da-Cheng Juan, Hai Li, Yiran Chen

To further highlight these vulnerabilities, we propose Hijacking Chain-of-Thought (H-CoT), a universal and transferable attack method that leverages the model's own displayed intermediate reasoning to jailbreak its safety reasoning mechanism.

UniQ: Unified Decoder with Task-specific Queries for Efficient Scene Graph Generation

no code implementations10 Jan 2025 Xinyao Liao, Wei Wei, Dangyang Chen, Yuanyuan Fu

In this paper, we introduce UniQ, a Unified decoder with task-specific Queries architecture, where task-specific queries generate decoupled visual features for subjects, objects, and predicates respectively, and unified decoder enables coupled feature modeling within relational triplets.

Decoder Graph Generation +4

Overcoming Language Priors for Visual Question Answering Based on Knowledge Distillation

no code implementations10 Jan 2025 Daowan Peng, Wei Wei

Previous studies have pointed out that visual question answering (VQA) models are prone to relying on language priors for answer predictions.

Knowledge Distillation Question Answering +1

Integrating Language-Image Prior into EEG Decoding for Cross-Task Zero-Calibration RSVP-BCI

no code implementations6 Jan 2025 Xujin Li, Wei Wei, Shuang Qiu, Xinyi Zhang, Fu Li, Huiguang He

Specifically, we propose a prompt encoder based on the language-image pre-trained model to extract language-image features from task-specific prompts and stimulus images as prior knowledge for enhancing EEG decoding.

Brain Computer Interface EEG +2

Low-Biased General Annotated Dataset Generation

no code implementations CVPR 2025 Dengyang Jiang, Haoyu Wang, Lei Zhang, Wei Wei, Guang Dai, Mengmeng Wang, Jingdong Wang, Yanning Zhang

Pre-training backbone networks on a general annotated dataset (e. g., ImageNet) that comprises numerous manually collected images with category annotations has proven to be indispensable for enhancing the generalization capacity of downstream visual tasks.

Dataset Generation Image Generation

Unbiased General Annotated Dataset Generation

no code implementations14 Dec 2024 Dengyang Jiang, Haoyu Wang, Lei Zhang, Wei Wei, Guang Dai, Mengmeng Wang, Jingdong Wang, Yanning Zhang

Pre-training backbone networks on a general annotated dataset (e. g., ImageNet) that comprises numerous manually collected images with category annotations has proven to be indispensable for enhancing the generalization capacity of downstream visual tasks.

Dataset Generation Image Generation

Hierarchical Split Federated Learning: Convergence Analysis and System Optimization

no code implementations10 Dec 2024 Zheng Lin, Wei Wei, Zhe Chen, Chan-Tong Lam, Xianhao Chen, Yue Gao, Jun Luo

To tackle this issue, split federated learning (SFL) has emerged as an FL framework with reduced workload on edge devices via model splitting; it has received extensive attention from the research community in recent years.

Federated Learning

PGSO: Prompt-based Generative Sequence Optimization Network for Aspect-based Sentiment Analysis

no code implementations1 Dec 2024 Hao Dong, Wei Wei

The rule-based approach relies on handcraft priority of dependency relation to reorder the context, while the score-based algorithm dynamically regulates the contextual sequence by calculating word position scores using neural network.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2

FreqX: Analyze the Attribution Methods in Another Domain

no code implementations27 Nov 2024 Zechen Liu, Feiyang Zhang, Wei Song, Xiang Li, Wei Wei

However, PFL suffers from Non-IID, heterogeneous devices, lack of fairness, and unclear contribution which urgently need the interpretability of deep learning model to overcome these challenges.

Fairness

Local and Global Feature Attention Fusion Network for Face Recognition

no code implementations25 Nov 2024 Wang Yu, Wei Wei

For low-quality images dominated by missing partial facial regions, local region similarity contributes more to face recognition (FR).

Face Recognition

Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning

no code implementations3 Nov 2024 Fei Zhou, Peng Wang, Lei Zhang, Zhenghua Chen, Wei Wei, Chen Ding, Guosheng Lin, Yanning Zhang

Meta-learning offers a promising avenue for few-shot learning (FSL), enabling models to glean a generalizable feature embedding through episodic training on synthetic FSL tasks in a source domain.

cross-domain few-shot learning

From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs

no code implementations17 Oct 2024 Alireza Rezazadeh, Zichao Li, Wei Wei, Yujia Bao

Recent advancements in large language models have significantly improved their context windows, yet challenges in effective long-term memory management remain.

Dialogue Understanding Management +2

LLM Unlearning via Loss Adjustment with Only Forget Data

no code implementations14 Oct 2024 Yaxuan Wang, Jiaheng Wei, Chris Yuhao Liu, Jinlong Pang, Quan Liu, Ankit Parag Shah, Yujia Bao, Yang Liu, Wei Wei

Existing approaches to LLM unlearning often rely on retain data or a reference LLM, yet they struggle to adequately balance unlearning performance with overall model utility.

Improving Data Efficiency via Curating LLM-Driven Rating Systems

no code implementations9 Oct 2024 Jinlong Pang, Jiaheng Wei, Ankit Parag Shah, Zhaowei Zhu, Yaxuan Wang, Chen Qian, Yang Liu, Yujia Bao, Wei Wei

Instruction tuning is critical for adapting large language models (LLMs) to downstream tasks, and recent studies have demonstrated that small amounts of human-curated data can outperform larger datasets, challenging traditional data scaling laws.

Diversity

Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigation

2 code implementations16 Sep 2024 Meng Chen, Jiawei Tu, Chao Qi, Yonghao Dang, Feng Zhou, Wei Wei, Jianqin Yin

To make the patch inconspicuous to human observers, we introduce a two-stage opacity optimization mechanism, in which opacity is fine-tuned after texture optimization.

Adversarial Robustness object-detection +1

EasyST: A Simple Framework for Spatio-Temporal Prediction

1 code implementation10 Sep 2024 Jiabin Tang, Wei Wei, Lianghao Xia, Chao Huang

Spatio-temporal prediction is a crucial research area in data-driven urban computing, with implications for transportation, public safety, and environmental monitoring.

Knowledge Distillation Prediction

Irreversible investment under weighted discounting: effects of decreasing impatience

no code implementations2 Sep 2024 Pengyu Wei, Wei Wei

This paper employs an intra-personal game-theoretic framework to investigate how decreasing impatience influences irreversible investment behaviors in a continuous-time setting.

Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning

1 code implementation30 Aug 2024 Xiaoye Qu, Jiashuo Sun, Wei Wei, Yu Cheng

By fully grasping the information in the image and carefully considering the certainty of the potential answers when decoding, our MVP can effectively reduce hallucinations in LVLMs. The extensive experiments verify that our proposed MVP significantly mitigates the hallucination problem across four well-known LVLMs.

Hallucination

Mitigating Multilingual Hallucination in Large Vision-Language Models

1 code implementation1 Aug 2024 Xiaoye Qu, Mingyang Song, Wei Wei, Jianfeng Dong, Yu Cheng

In this paper, we make the first attempt to mitigate this important multilingual hallucination in LVLMs.

Hallucination

Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation

no code implementations1 Aug 2024 Xiaoye Qu, Qiyuan Chen, Wei Wei, Jishuo Sun, Jianfeng Dong

To assess the capability of our proposed ARA model in reducing hallucination, we employ three widely used LVLM models (LLaVA-1. 5, Qwen-VL, and mPLUG-Owl2) across four benchmarks.

Hallucination Image Comprehension +2

Gemma 2: Improving Open Language Models at a Practical Size

no code implementations31 Jul 2024 Gemma Team, Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa, Cassidy Hardin, Surya Bhupatiraju, Léonard Hussenot, Thomas Mesnard, Bobak Shahriari, Alexandre Ramé, Johan Ferret, Peter Liu, Pouya Tafti, Abe Friesen, Michelle Casbon, Sabela Ramos, Ravin Kumar, Charline Le Lan, Sammy Jerome, Anton Tsitsulin, Nino Vieillard, Piotr Stanczyk, Sertan Girgin, Nikola Momchev, Matt Hoffman, Shantanu Thakoor, Jean-bastien Grill, Behnam Neyshabur, Olivier Bachem, Alanna Walton, Aliaksei Severyn, Alicia Parrish, Aliya Ahmad, Allen Hutchison, Alvin Abdagic, Amanda Carl, Amy Shen, Andy Brock, Andy Coenen, Anthony Laforge, Antonia Paterson, Ben Bastian, Bilal Piot, Bo Wu, Brandon Royal, Charlie Chen, Chintu Kumar, Chris Perry, Chris Welty, Christopher A. Choquette-Choo, Danila Sinopalnikov, David Weinberger, Dimple Vijaykumar, Dominika Rogozińska, Dustin Herbison, Elisa Bandy, Emma Wang, Eric Noland, Erica Moreira, Evan Senter, Evgenii Eltyshev, Francesco Visin, Gabriel Rasskin, Gary Wei, Glenn Cameron, Gus Martins, Hadi Hashemi, Hanna Klimczak-Plucińska, Harleen Batra, Harsh Dhand, Ivan Nardini, Jacinda Mein, Jack Zhou, James Svensson, Jeff Stanway, Jetha Chan, Jin Peng Zhou, Joana Carrasqueira, Joana Iljazi, Jocelyn Becker, Joe Fernandez, Joost van Amersfoort, Josh Gordon, Josh Lipschultz, Josh Newlan, Ju-yeong Ji, Kareem Mohamed, Kartikeya Badola, Kat Black, Katie Millican, Keelin McDonell, Kelvin Nguyen, Kiranbir Sodhia, Kish Greene, Lars Lowe Sjoesund, Lauren Usui, Laurent SIfre, Lena Heuermann, Leticia Lago, Lilly McNealus, Livio Baldini Soares, Logan Kilpatrick, Lucas Dixon, Luciano Martins, Machel Reid, Manvinder Singh, Mark Iverson, Martin Görner, Mat Velloso, Mateo Wirth, Matt Davidow, Matt Miller, Matthew Rahtz, Matthew Watson, Meg Risdal, Mehran Kazemi, Michael Moynihan, Ming Zhang, Minsuk Kahng, Minwoo Park, Mofi Rahman, Mohit Khatwani, Natalie Dao, Nenshad Bardoliwalla, Nesh Devanathan, Neta Dumai, Nilay Chauhan, Oscar Wahltinez, Pankil Botarda, Parker Barnes, Paul Barham, Paul Michel, Pengchong Jin, Petko Georgiev, Phil Culliton, Pradeep Kuppala, Ramona Comanescu, Ramona Merhej, Reena Jana, Reza Ardeshir Rokni, Rishabh Agarwal, Ryan Mullins, Samaneh Saadat, Sara Mc Carthy, Sarah Cogan, Sarah Perrin, Sébastien M. R. Arnold, Sebastian Krause, Shengyang Dai, Shruti Garg, Shruti Sheth, Sue Ronstrom, Susan Chan, Timothy Jordan, Ting Yu, Tom Eccles, Tom Hennigan, Tomas Kocisky, Tulsee Doshi, Vihan Jain, Vikas Yadav, Vilobh Meshram, Vishal Dharmadhikari, Warren Barkley, Wei Wei, Wenming Ye, Woohyun Han, Woosuk Kwon, Xiang Xu, Zhe Shen, Zhitao Gong, Zichuan Wei, Victor Cotruta, Phoebe Kirk, Anand Rao, Minh Giang, Ludovic Peran, Tris Warkentin, Eli Collins, Joelle Barral, Zoubin Ghahramani, Raia Hadsell, D. Sculley, Jeanine Banks, Anca Dragan, Slav Petrov, Oriol Vinyals, Jeff Dean, Demis Hassabis, Koray Kavukcuoglu, Clement Farabet, Elena Buchatskaya, Sebastian Borgeaud, Noah Fiedel, Armand Joulin, Kathleen Kenealy, Robert Dadashi, Alek Andreev

In this work, we introduce Gemma 2, a new addition to the Gemma family of lightweight, state-of-the-art open models, ranging in scale from 2 billion to 27 billion parameters.

Knowledge Distillation

Human-like object concept representations emerge naturally in multimodal large language models

no code implementations1 Jul 2024 Changde Du, Kaicheng Fu, Bincheng Wen, Yi Sun, Jie Peng, Wei Wei, Ying Gao, Shengpei Wang, Chuncheng Zhang, Jinpeng Li, Shuang Qiu, Le Chang, Huiguang He

The conceptualization and categorization of natural objects in the human mind have long intrigued cognitive scientists and neuroscientists, offering crucial insights into human perception and cognition.

Triplet

DiffMM: Multi-Modal Diffusion Model for Recommendation

1 code implementation17 Jun 2024 Yangqin Jiang, Lianghao Xia, Wei Wei, Da Luo, Kangyi Lin, Chao Huang

To address this limitation, recent research has introduced self-supervised learning techniques to enhance recommender systems.

Contrastive Learning model +3

Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging

1 code implementation17 Jun 2024 Zhenyi Lu, Chenghao Fan, Wei Wei, Xiaoye Qu, Dangyang Chen, Yu Cheng

In view of this, we propose Twin-Merging, a method that encompasses two principal stages: (1) modularizing knowledge into shared and exclusive components, with compression to reduce redundancy and enhance efficiency; (2) dynamically merging shared and task-specific knowledge based on the input.

On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion

no code implementations17 Jun 2024 Chenghao Fan, Zhenyi Lu, Wei Wei, Jie Tian, Xiaoye Qu, Dangyang Chen, Yu Cheng

\thm{Can we fine-tune a series of task-specific small models and transfer their knowledge directly to a much larger model without additional training?}

In-Context Learning Task Arithmetic +1

Dataset Condensation with Latent Quantile Matching

no code implementations14 Jun 2024 Wei Wei, Tom De Schepper, Kevin Mets

Current distribution matching (DM) based DC methods learn a synthesized dataset by matching the mean of the latent embeddings between the synthetic and the real dataset.

Dataset Condensation Graph Learning

Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models

1 code implementation11 Jun 2024 Zhenyi Lu, Jie Tian, Wei Wei, Xiaoye Qu, Yu Cheng, Wenfeng Xie, Dangyang Chen

Our approach is grounded in the empirical observation that pairwise comparisons can effectively alleviate boundary ambiguity and inherent bias.

text-classification Text Classification

Personalized Topic Selection Model for Topic-Grounded Dialogue

no code implementations4 Jun 2024 Shixuan Fan, Wei Wei, Xiaofei Wen, Xianling Mao, Jixiong Chen, Dangyang Chen

Recently, the topic-grounded dialogue (TGD) system has become increasingly popular as its powerful capability to actively guide users to accomplish specific tasks through topic-guided conversations.

Contrastive Learning model

Position Debiasing Fine-Tuning for Causal Perception in Long-Term Dialogue

no code implementations4 Jun 2024 Shixuan Fan, Wei Wei, Wendi Li, Xian-Ling Mao, Wenfeng Xie, Dangyang Chen

The core of the dialogue system is to generate relevant, informative, and human-like responses based on extensive dialogue history.

Dialogue Generation Position +2

Knowledge Enhanced Multi-intent Transformer Network for Recommendation

1 code implementation31 May 2024 Ding Zou, Wei Wei, Feida Zhu, Chuanyu Xu, Tao Zhang, Chengfu Huo

However, simply integrating KG into recommendation usually brings in negative feedback in industry, due to the ignorance of the following two factors: i) users' multiple intents, which involve diverse nodes in KG.

Denoising Knowledge Graphs +1

Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning

1 code implementation23 May 2024 Jiapu Wang, Kai Sun, Linhao Luo, Wei Wei, Yongli Hu, Alan Wee-Chung Liew, Shirui Pan, BaoCai Yin

To account for the evolving nature of TKGs, a dynamic adaptation strategy is proposed to update the LLM-generated rules with the latest events.

Deep Penalty Methods: A Class of Deep Learning Algorithms for Solving High Dimensional Optimal Stopping Problems

no code implementations18 May 2024 Yunfei Peng, Pengyu Wei, Wei Wei

We validate the efficacy of the DPM through numerical tests conducted on a high-dimensional optimal stopping model in the area of American option pricing.

Computational Efficiency

GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missing

1 code implementation18 May 2024 Chengqing Yu, Fei Wang, Zezhi Shao, Tangwen Qian, Zhao Zhang, Wei Wei, Yongjun Xu

In GinAR, it consists of two key components, that is, interpolation attention and adaptive graph convolution to take place of the fully connected layer of simple recursive units, and thus are capable of recovering all missing variables and reconstructing the correct spatial-temporal dependencies for recursively modeling of multivariate time series data, respectively.

Multivariate Time Series Forecasting Time Series

A Comprehensive Survey on Self-Supervised Learning for Recommendation

1 code implementation4 Apr 2024 Xubin Ren, Wei Wei, Lianghao Xia, Chao Huang

Recommender systems play a crucial role in tackling the challenge of information overload by delivering personalized recommendations based on individual user preferences.

Contrastive Learning Recommendation Systems +2

AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networks

no code implementations19 Mar 2024 Zheng Lin, Guanqiao Qu, Wei Wei, Xianhao Chen, Kin K. Leung

In this paper, we provide a convergence analysis of SFL which quantifies the impact of model splitting (MS) and client-side model aggregation (MA) on the learning performance, serving as a theoretical foundation.

Edge-computing Federated Learning

Reinforcement Learning with Token-level Feedback for Controllable Text Generation

1 code implementation18 Mar 2024 Wendi Li, Wei Wei, Kaihe Xu, Wenfeng Xie, Dangyang Chen, Yu Cheng

To meet the requirements of real-world applications, it is essential to control generations of large language models (LLMs).

Attribute reinforcement-learning +4

PromptMM: Multi-Modal Knowledge Distillation for Recommendation with Prompt-Tuning

1 code implementation27 Feb 2024 Wei Wei, Jiabin Tang, Yangqin Jiang, Lianghao Xia, Chao Huang

Additionally, to adjust the impact of inaccuracies in multimedia data, a disentangled multi-modal list-wise distillation is developed with modality-aware re-weighting mechanism.

Knowledge Distillation Model Compression +1

HiGPT: Heterogeneous Graph Language Model

1 code implementation25 Feb 2024 Jiabin Tang, Yuhao Yang, Wei Wei, Lei Shi, Long Xia, Dawei Yin, Chao Huang

However, existing frameworks for heterogeneous graph learning have limitations in generalizing across diverse heterogeneous graph datasets.

Graph Learning Language Modeling +3

GraphEdit: Large Language Models for Graph Structure Learning

1 code implementation23 Feb 2024 Zirui Guo, Lianghao Xia, Yanhua Yu, Yuling Wang, Zixuan Yang, Wei Wei, Liang Pang, Tat-Seng Chua, Chao Huang

Graph Structure Learning (GSL) focuses on capturing intrinsic dependencies and interactions among nodes in graph-structured data by generating novel graph structures.

Graph structure learning

PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models

no code implementations CVPR 2024 Fei Deng, Qifei Wang, Wei Wei, Matthias Grundmann, Tingbo Hou

However, in the vision domain, existing RL-based reward finetuning methods are limited by their instability in large-scale training, rendering them incapable of generalizing to complex, unseen prompts.

Denoising Reinforcement Learning (RL)

BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models

1 code implementation13 Feb 2024 Haotian Sun, Yuchen Zhuang, Wei Wei, Chao Zhang, Bo Dai

BBox-Adapter distinguishes target and source domain data by treating target data as positive and source data as negative.

Benchmarking Sensitivity of Continual Graph Learning for Skeleton-Based Action Recognition

no code implementations31 Jan 2024 Wei Wei, Tom De Schepper, Kevin Mets

We propose the first continual graph learning benchmark for spatio-temporal graphs and use it to benchmark well-known CGL methods in this novel setting.

Action Recognition Benchmarking +3

Hierarchical Continual Reinforcement Learning via Large Language Model

no code implementations25 Jan 2024 Chaofan Pan, Xin Yang, Hao Wang, Wei Wei, Tianrui Li

Despite the progress in continual reinforcement learning (CRL), existing methods often suffer from insufficient knowledge transfer, particularly when the tasks are diverse.

Language Modeling Language Modelling +6

A Temporal-Spectral Fusion Transformer with Subject-Specific Adapter for Enhancing RSVP-BCI Decoding

1 code implementation12 Jan 2024 Xujin Li, Wei Wei, Shuang Qiu, Huiguang He

The performance improvement of traditional decoding methods relies on a substantial amount of training data from new test subjects, which increases preparation time for BCI systems.

Brain Computer Interface EEG

Enhancing Low-Resource Relation Representations through Multi-View Decoupling

1 code implementation26 Dec 2023 Chenghao Fan, Wei Wei, Xiaoye Qu, Zhenyi Lu, Wenfeng Xie, Yu Cheng, Dangyang Chen

Recently, prompt-tuning with pre-trained language models (PLMs) has demonstrated the significantly enhancing ability of relation extraction (RE) tasks.

Relation Relation Extraction +1

Detection-based Intermediate Supervision for Visual Question Answering

no code implementations26 Dec 2023 Yuhang Liu, Daowan Peng, Wei Wei, Yuanyuan Fu, Wenfeng Xie, Dangyang Chen

Recently, neural module networks (NMNs) have yielded ongoing success in answering compositional visual questions, especially those involving multi-hop visual and logical reasoning.

cross-modal alignment Logical Reasoning +2

HiFi Tuner: High-Fidelity Subject-Driven Fine-Tuning for Diffusion Models

no code implementations30 Nov 2023 Zhonghao Wang, Wei Wei, Yang Zhao, Zhisheng Xiao, Mark Hasegawa-Johnson, Humphrey Shi, Tingbo Hou

We further extend our method to a novel image editing task: substituting the subject in an image through textual manipulations.

Denoising Image Generation +2

On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval

no code implementations1 Nov 2023 Jiayi Chen, Hanjun Dai, Bo Dai, Aidong Zhang, Wei Wei

However, prior works for Few-shot VDER mainly address the problem at the document level with a predefined global entity space, which doesn't account for the entity-level few-shot scenario: target entity types are locally personalized by each task and entity occurrences vary significantly among documents.

Contrastive Learning Entity Retrieval +2

LLMRec: Large Language Models with Graph Augmentation for Recommendation

1 code implementation1 Nov 2023 Wei Wei, Xubin Ren, Jiabin Tang, Qinyong Wang, Lixin Su, Suqi Cheng, Junfeng Wang, Dawei Yin, Chao Huang

By employing these strategies, we address the challenges posed by sparse implicit feedback and low-quality side information in recommenders.

Model Optimization Recommendation Systems

Adapt Anything: Tailor Any Image Classifiers across Domains And Categories Using Text-to-Image Diffusion Models

no code implementations25 Oct 2023 WeiJie Chen, Haoyu Wang, Shicai Yang, Lei Zhang, Wei Wei, Yanning Zhang, Luojun Lin, Di Xie, Yueting Zhuang

Such a one-for-all adaptation paradigm allows us to adapt anything in the world using only one text-to-image generator as well as the corresponding unlabeled target data.

Domain Adaptation image-classification +1

Representation Learning with Large Language Models for Recommendation

1 code implementation24 Oct 2023 Xubin Ren, Wei Wei, Lianghao Xia, Lixin Su, Suqi Cheng, Junfeng Wang, Dawei Yin, Chao Huang

RLMRec incorporates auxiliary textual signals, develops a user/item profiling paradigm empowered by LLMs, and aligns the semantic space of LLMs with the representation space of collaborative relational signals through a cross-view alignment framework.

Recommendation Systems Representation Learning

Skipped Feature Pyramid Network with Grid Anchor for Object Detection

no code implementations22 Oct 2023 Li Pengfei, Wei Wei, Yan Yu, Zhu Rong, Zhou Liguo

In our method, the lower-level feature only connects with the feature at the highest level, making it more reasonable that each level is responsible for detecting objects with fixed scales.

Object object-detection +1

MIRACLE: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute Control

1 code implementation22 Oct 2023 Zhenyi Lu, Wei Wei, Xiaoye Qu, Xianling Mao, Dangyang Chen, Jixiong Chen

Subsequently, we employ a conditional variational auto-encoder to align with the dense personalized responses within a latent joint attribute space.

Attribute Dialogue Generation +1

GraphGPT: Graph Instruction Tuning for Large Language Models

1 code implementation19 Oct 2023 Jiabin Tang, Yuhao Yang, Wei Wei, Lei Shi, Lixin Su, Suqi Cheng, Dawei Yin, Chao Huang

The open-sourced model implementation of our GraphGPT is available at https://github. com/HKUDS/GraphGPT.

Data Augmentation Graph Learning +2

Multi Task Consistency Guided Source-Free Test-Time Domain Adaptation Medical Image Segmentation

no code implementations18 Oct 2023 Yanyu Ye, Zhenxi Zhang, Wei Wei, Chunna Tian

To improve the performance of test-time domain adaptation, we propose a multi task consistency guided source-free test-time domain adaptation medical image segmentation method which ensures the consistency of the local boundary predictions and the global prototype representation.

Image Segmentation Medical Image Segmentation +3

Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis

5 code implementations9 Oct 2023 Zezhi Shao, Fei Wang, Yongjun Xu, Wei Wei, Chengqing Yu, Zhao Zhang, Di Yao, Tao Sun, Guangyin Jin, Xin Cao, Gao Cong, Christian S. Jensen, Xueqi Cheng

Multivariate Time Series (MTS) analysis is crucial to understanding and managing complex systems, such as traffic and energy systems, and a variety of approaches to MTS forecasting have been proposed recently.

Benchmarking Multivariate Time Series Forecasting +1

TiBGL: Template-induced Brain Graph Learning for Functional Neuroimaging Analysis

no code implementations14 Sep 2023 Xiangzhu Meng, Wei Wei, Qiang Liu, Shu Wu, Liang Wang

Motivated by the related medical findings on functional connectivites, TiBGL proposes template-induced brain graph learning to extract template brain graphs for all groups.

Functional Connectivity Graph Learning

Multi-Relational Contrastive Learning for Recommendation

1 code implementation3 Sep 2023 Wei Wei, Lianghao Xia, Chao Huang

Personalized recommender systems play a crucial role in capturing users' evolving preferences over time to provide accurate and effective recommendations on various online platforms.

Contrastive Learning Recommendation Systems +1

Local-Global Pseudo-label Correction for Source-free Domain Adaptive Medical Image Segmentation

no code implementations28 Aug 2023 Yanyu Ye, Zhengxi Zhang, Chunna Tianb, Wei Wei

In this study, we address the issue of false labels in self-training based source-free domain adaptive medical image segmentation methods.

Image Segmentation Medical Image Segmentation +5

HyperBandit: Contextual Bandit with Hypernewtork for Time-Varying User Preferences in Streaming Recommendation

no code implementations14 Aug 2023 Chenglei Shen, Xiao Zhang, Wei Wei, Jun Xu

In real-world streaming recommender systems, user preferences often dynamically change over time (e. g., a user may have different preferences during weekdays and weekends).

Recommendation Systems

SSLRec: A Self-Supervised Learning Framework for Recommendation

1 code implementation10 Aug 2023 Xubin Ren, Lianghao Xia, Yuhao Yang, Wei Wei, Tianle Wang, Xuheng Cai, Chao Huang

Our SSLRec platform covers a comprehensive set of state-of-the-art SSL-enhanced recommendation models across different scenarios, enabling researchers to evaluate these cutting-edge models and drive further innovation in the field.

Collaborative Filtering Data Augmentation +2

Multi-view Hypergraph Contrastive Policy Learning for Conversational Recommendation

1 code implementation26 Jul 2023 Sen Zhao, Wei Wei, Xian-Ling Mao, Shuai Zhu, Minghui Yang, Zujie Wen, Dangyang Chen, Feida Zhu

Specifically, MHCPL timely chooses useful social information according to the interactive history and builds a dynamic hypergraph with three types of multiplex relations from different views.

Conversational Recommendation Recommendation Systems

TREA: Tree-Structure Reasoning Schema for Conversational Recommendation

1 code implementation20 Jul 2023 Wendi Li, Wei Wei, Xiaoye Qu, Xian-Ling Mao, Ye Yuan, Wenfeng Xie, Dangyang Chen

TREA constructs a multi-hierarchical scalable tree as the reasoning structure to clarify the causal relationships between mentioned entities, and fully utilizes historical conversations to generate more reasonable and suitable responses for recommended results.

Conversational Recommendation Knowledge Graphs +1

HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models

2 code implementations CVPR 2024 Nataniel Ruiz, Yuanzhen Li, Varun Jampani, Wei Wei, Tingbo Hou, Yael Pritch, Neal Wadhwa, Michael Rubinstein, Kfir Aberman

By composing these weights into the diffusion model, coupled with fast finetuning, HyperDreamBooth can generate a person's face in various contexts and styles, with high subject details while also preserving the model's crucial knowledge of diverse styles and semantic modifications.

Diffusion Personalization Tuning Free Diversity

An Evolution Kernel Method for Graph Classification through Heat Diffusion Dynamics

no code implementations26 Jun 2023 Xue Liu, Dan Sun, Wei Wei, Zhiming Zheng

This approach incorporates the physics-based heat kernel and DropNode technique to transform each static graph into a sequence of temporal ones.

Graph Classification

Multi-View Attention Learning for Residual Disease Prediction of Ovarian Cancer

no code implementations26 Jun 2023 Xiangneng Gao, Shulan Ruan, Jun Shi, Guoqing Hu, Wei Wei

To this end, in this paper, we propose a novel Multi-View Attention Learning (MuVAL) method for residual disease prediction, which focuses on the comprehensive learning of 3D Computed Tomography (CT) images in a multi-view manner.

Computed Tomography (CT) Decision Making +2

DocumentNet: Bridging the Data Gap in Document Pre-Training

no code implementations15 Jun 2023 Lijun Yu, Jin Miao, Xiaoyu Sun, Jiayi Chen, Alexander G. Hauptmann, Hanjun Dai, Wei Wei

Document understanding tasks, in particular, Visually-rich Document Entity Retrieval (VDER), have gained significant attention in recent years thanks to their broad applications in enterprise AI.

document understanding Entity Retrieval +3

An Empirical Study on the Language Modal in Visual Question Answering

no code implementations17 May 2023 Daowan Peng, Wei Wei, Xian-Ling Mao, Yuanyuan Fu, Dangyang Chen

Generalization beyond in-domain experience to out-of-distribution data is of paramount significance in the AI domain.

Question Answering Visual Question Answering

Towards Hierarchical Policy Learning for Conversational Recommendation with Hypergraph-based Reinforcement Learning

1 code implementation4 May 2023 Sen Zhao, Wei Wei, Yifan Liu, Ziyang Wang, Wendi Li, Xian-Ling Mao, Shuai Zhu, Minghui Yang, Zujie Wen

Conversational recommendation systems (CRS) aim to timely and proactively acquire user dynamic preferred attributes through conversations for item recommendation.

Attribute Conversational Recommendation +3

AttenWalker: Unsupervised Long-Document Question Answering via Attention-based Graph Walking

1 code implementation3 May 2023 Yuxiang Nie, Heyan Huang, Wei Wei, Xian-Ling Mao

To alleviate the problem, it might be possible to generate long-document QA pairs via unsupervised question answering (UQA) methods.

Few-Shot Learning Question Answering

ALUM: Adversarial Data Uncertainty Modeling from Latent Model Uncertainty Compensation

no code implementations29 Mar 2023 Wei Wei, Jiahuan Zhou, Hongze Li, Ying Wu

Thus, the critical data uncertainty and model uncertainty caused by noisy data can be readily quantified for improving model robustness.

Multi-task Meta Label Correction for Time Series Prediction

1 code implementation9 Mar 2023 Luxuan Yang, Ting Gao, Wei Wei, Min Dai, Cheng Fang, Jinqiao Duan

To address the above issues, we create a label correction method to time series data with meta-learning under a multi-task framework.

Contrastive Learning Data Visualization +5

Heterogeneous Graph Contrastive Learning for Recommendation

1 code implementation2 Mar 2023 Mengru Chen, Chao Huang, Lianghao Xia, Wei Wei, Yong Xu, Ronghua Luo

In light of this, we propose a Heterogeneous Graph Contrastive Learning (HGCL), which is able to incorporate heterogeneous relational semantics into the user-item interaction modeling with contrastive learning-enhanced knowledge transfer across different views.

Contrastive Learning Recommendation Systems +3

Multi-Modal Self-Supervised Learning for Recommendation

2 code implementations21 Feb 2023 Wei Wei, Chao Huang, Lianghao Xia, Chuxu Zhang

The online emergence of multi-modal sharing platforms (eg, TikTok, Youtube) is powering personalized recommender systems to incorporate various modalities (eg, visual, textual and acoustic) into the latent user representations.

Contrastive Learning Data Augmentation +3

Revisiting Prototypical Network for Cross Domain Few-Shot Learning

1 code implementation CVPR 2023 Fei Zhou, Peng Wang, Lei Zhang, Wei Wei, Yanning Zhang

Prototypical Network is a popular few-shot solver that aims at establishing a feature metric generalizable to novel few-shot classification (FSC) tasks using deep neural networks.

cross-domain few-shot learning Knowledge Distillation

Sizing Grid-Connected Wind Power Generation and Energy Storage with Wake Effect and Endogenous Uncertainty: A Distributionally Robust Method

no code implementations30 Dec 2022 Rui Xie, Wei Wei, Yue Chen

In this paper, a bi-objective distributionally robust optimization (DRO) model is proposed to determine the capacities of wind power generation and ESSs considering the wake effect.

STAGE: Span Tagging and Greedy Inference Scheme for Aspect Sentiment Triplet Extraction

1 code implementation28 Nov 2022 Shuo Liang, Wei Wei, Xian-Ling Mao, Yuanyuan Fu, Rui Fang, Dangyang Chen

Hence, we propose a novel approach, Span TAgging and Greedy infErence (STAGE), to extract sentiment triplets in span-level, where each span may consist of multiple words and play different roles simultaneously.

Aspect Sentiment Triplet Extraction Sentence +2

VRDU: A Benchmark for Visually-rich Document Understanding

no code implementations15 Nov 2022 Zilong Wang, Yichao Zhou, Wei Wei, Chen-Yu Lee, Sandeep Tata

Understanding visually-rich business documents to extract structured data and automate business workflows has been receiving attention both in academia and industry.

document understanding

Knowledge-Enhanced Relation Extraction Dataset

no code implementations19 Oct 2022 Yucong Lin, Hongming Xiao, Jiani Liu, Zichao Lin, Keming Lu, Feifei Wang, Wei Wei

Recently, knowledge-enhanced methods leveraging auxiliary knowledge graphs have emerged in relation extraction, surpassing traditional text-based approaches.

Entity Linking Knowledge Graphs +3

Sequential Topic Selection Model with Latent Variable for Topic-Grounded Dialogue

no code implementations17 Oct 2022 Xiaofei Wen, Wei Wei, Xian-Ling Mao

To address the problem, in this paper we propose a novel approach, named Sequential Global Topic Attention (SGTA) to exploit topic transition over all conversations in a subtle way for better modeling post-to-response topic-transition and guiding the response generation to the current conversation.

Response Generation

HCL-TAT: A Hybrid Contrastive Learning Method for Few-shot Event Detection with Task-Adaptive Threshold

no code implementations17 Oct 2022 Ruihan Zhang, Wei Wei, Xian-Ling Mao, Rui Fang, Dangyang Chen

Conventional event detection models under supervised learning settings suffer from the inability of transfer to newly-emerged event types owing to lack of sufficient annotations.

Contrastive Learning Event Detection +2

Metric Distribution to Vector: Constructing Data Representation via Broad-Scale Discrepancies

no code implementations2 Oct 2022 Xue Liu, Dan Sun, Xiaobo Cao, Hao Ye, Wei Wei

Graph embedding provides a feasible methodology to conduct pattern classification for graph-structured data by mapping each data into the vectorial space.

Graph Embedding

Unsupervised Hashing with Semantic Concept Mining

1 code implementation23 Sep 2022 Rong-Cheng Tu, Xian-Ling Mao, Kevin Qinghong Lin, Chengfei Cai, Weize Qin, Hongfa Wang, Wei Wei, Heyan Huang

Recently, to improve the unsupervised image retrieval performance, plenty of unsupervised hashing methods have been proposed by designing a semantic similarity matrix, which is based on the similarities between image features extracted by a pre-trained CNN model.

Image Retrieval Prompt Engineering +4

Incorporating Causal Analysis into Diversified and Logical Response Generation

no code implementations20 Sep 2022 Jiayi Liu, Wei Wei, Zhixuan Chu, Xing Gao, Ji Zhang, Tan Yan, Yulin kang

Although the Conditional Variational AutoEncoder (CVAE) model can generate more diversified responses than the traditional Seq2Seq model, the responses often have low relevance with the input words or are illogical with the question.

Response Generation

Multi-level Contrastive Learning Framework for Sequential Recommendation

no code implementations27 Aug 2022 Ziyang Wang, Huoyu Liu, Wei Wei, Yue Hu, Xian-Ling Mao, Shaojian He, Rui Fang, Dangyang Chen

Different from the previous contrastive learning-based methods for SR, MCLSR learns the representations of users and items through a cross-view contrastive learning paradigm from four specific views at two different levels (i. e., interest- and feature-level).

Contrastive Learning Relation +1

Improving Personality Consistency in Conversation by Persona Extending

1 code implementation23 Aug 2022 Yifan Liu, Wei Wei, Jiayi Liu, Xianling Mao, Rui Fang, Dangyang Chen

Endowing chatbots with a consistent personality plays a vital role for agents to deliver human-like interactions.

Chatbot Natural Language Inference +1

Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting

2 code implementations10 Aug 2022 Zezhi Shao, Zhao Zhang, Fei Wang, Wei Wei, Yongjun Xu

These results suggest that we can design efficient and effective models as long as they solve the indistinguishability of samples, without being limited to STGNNs.

Multivariate Time Series Forecasting Time Series +1

Mind the Gap: Polishing Pseudo labels for Accurate Semi-supervised Object Detection

1 code implementation17 Jul 2022 Lei Zhang, Yuxuan Sun, Wei Wei

Instead of directly exploiting the pseudo labels produced by the teacher detector, we take the first attempt at reducing their deviation from ground truth using dual polishing learning, where two differently structured polishing networks are elaborately developed and trained using synthesized paired pseudo labels and the corresponding ground truth for categories and bounding boxes on the given annotated objects, respectively.

object-detection Object Detection +2

E2FIF: Push the limit of Binarized Deep Imagery Super-resolution using End-to-end Full-precision Information Flow

1 code implementation14 Jul 2022 Zhiqiang Lang, Chongxing Song, Lei Zhang, Wei Wei

Binary neural network (BNN) provides a promising solution to deploy parameter-intensive deep single image super-resolution (SISR) models onto real devices with limited storage and computational resources.

Image Super-Resolution

Temporal Link Prediction via Adjusted Sigmoid Function and 2-Simplex Sructure

no code implementations20 Jun 2022 Ruizhi Zhang, Qiaozi Wang, Qiming Yang, Wei Wei

Temporal network link prediction is an important task in the field of network science, and has a wide range of applications in practical scenarios.

Link Prediction Prediction

Person-job fit estimation from candidate profile and related recruitment history with co-attention neural networks

1 code implementation18 Jun 2022 Ziyang Wang, Wei Wei, Chenwei Xu, Jun Xu, Xian-Ling Mao

Existing studies on person-job fit, however, mainly focus on calculating the similarity between the candidate resumes and the job postings on the basis of their contents, without taking the recruiters' experience (i. e., historical successful recruitment records) into consideration.

Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting

1 code implementation18 Jun 2022 Zezhi Shao, Zhao Zhang, Wei Wei, Fei Wang, Yongjun Xu, Xin Cao, Christian S. Jensen

However, intuitively, traffic data encompasses two different kinds of hidden time series signals, namely the diffusion signals and inherent signals.

Graph Learning Graph Neural Network +2

Parameter Convex Neural Networks

no code implementations11 Jun 2022 Jingcheng Zhou, Wei Wei, Xing Li, Bowen Pang, Zhiming Zheng

Deep learning utilizing deep neural networks (DNNs) has achieved a lot of success recently in many important areas such as computer vision, natural language processing, and recommendation systems.

Graph Attention Recommendation Systems

Relational Triple Extraction: One Step is Enough

no code implementations11 May 2022 Yu-Ming Shang, Heyan Huang, Xin Sun, Wei Wei, Xian-Ling Mao

Extracting relational triples from unstructured text is an essential task in natural language processing and knowledge graph construction.

graph construction Sentence

Automatic Noisy Label Correction for Fine-Grained Entity Typing

1 code implementation6 May 2022 Weiran Pan, Wei Wei, Feida Zhu

Fine-grained entity typing (FET) aims to assign proper semantic types to entity mentions according to their context, which is a fundamental task in various entity-leveraging applications.

Entity Typing

Declaration-based Prompt Tuning for Visual Question Answering

1 code implementation5 May 2022 Yuhang Liu, Wei Wei, Daowan Peng, Feida Zhu

In recent years, the pre-training-then-fine-tuning paradigm has yielded immense success on a wide spectrum of cross-modal tasks, such as visual question answering (VQA), in which a visual-language (VL) model is first optimized via self-supervised task objectives, e. g., masked language modeling (MLM) and image-text matching (ITM), and then fine-tuned to adapt to downstream task (e. g., VQA) via a brand-new objective function, e. g., answer prediction.

Image-text matching Language Modeling +6

Unsupervised Mismatch Localization in Cross-Modal Sequential Data with Application to Mispronunciations Localization

no code implementations5 May 2022 Wei Wei, Huang Hengguan, Gu Xiangming, Wang Hao, Wang Ye

Content mismatch usually occurs when data from one modality is translated to another, e. g. language learners producing mispronunciations (errors in speech) when reading a sentence (target text) aloud.

Sentence

Multi-core fiber enabled fading noise suppression in φ-OFDR based quantitative distributed vibration sensing

no code implementations3 May 2022 Yuxiang Feng, Weilin Xie, Yinxia Meng, Jiang Yang, Qiang Yang, Yan Ren, Tianwai Bo, Zhongwei Tan, Wei Wei, Yi Dong

Coherent fading has been regarded as a critical issue in phase-sensitive optical frequency domain reflectometry ({\phi}-OFDR) based distributed fiber-optic sensing.

Enhance Ambiguous Community Structure via Multi-strategy Community Related Link Prediction Method with Evolutionary Process

1 code implementation28 Apr 2022 Qiming Yang, Wei Wei, Ruizhi Zhang, Bowen Pang, Xiangnan Feng

To address this issue, in this paper, we design a new community attribute based link prediction strategy HAP and propose a two-step community enhancement algorithm with automatic evolution process based on HAP.

Attribute Community Detection +1

Cross-Lingual Phrase Retrieval

1 code implementation ACL 2022 Heqi Zheng, Xiao Zhang, Zewen Chi, Heyan Huang, Tan Yan, Tian Lan, Wei Wei, Xian-Ling Mao

In this paper, we propose XPR, a cross-lingual phrase retriever that extracts phrase representations from unlabeled example sentences.

Retrieval Sentence

Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System

1 code implementation19 Apr 2022 Ding Zou, Wei Wei, Xian-Ling Mao, Ziyang Wang, Minghui Qiu, Feida Zhu, Xin Cao

Different from traditional contrastive learning methods which generate two graph views by uniform data augmentation schemes such as corruption or dropping, we comprehensively consider three different graph views for KG-aware recommendation, including global-level structural view, local-level collaborative and semantic views.

Contrastive Learning Data Augmentation +2

BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis

1 code implementation Findings (ACL) 2022 Shuo Liang, Wei Wei, Xian-Ling Mao, Fei Wang, Zhiyong He

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task that aims to align aspects and corresponding sentiments for aspect-specific sentiment polarity inference.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2

An Optimal Control Method to Compute the Most Likely Transition Path for Stochastic Dynamical Systems with Jumps

1 code implementation31 Mar 2022 Wei Wei, Ting Gao, Jinqiao Duan, Xiaoli Chen

One of the challenges to calculate the most likely transition path for stochastic dynamical systems under non-Gaussian L\'evy noise is that the associated rate function can not be explicitly expressed by paths.

Multi-view Intent Disentangle Graph Networks for Bundle Recommendation

1 code implementation23 Feb 2022 Sen Zhao, Wei Wei, Ding Zou, Xianling Mao

Specifically, MIDGN disentangles the user's intents from two different perspectives, respectively: 1) In the global level, MIDGN disentangles the user's intent coupled with inter-bundle items; 2) In the Local level, MIDGN disentangles the user's intent coupled with items within each bundle.

Diversity

Optimal configuration of cooperative stationary and mobile energy storage considering ambient temperature: A case for Winter Olympic Game

no code implementations20 Feb 2022 He Meng, Hongjie Jia, Tao Xu, Wei Wei, Yuhan Wu, Lemeng Liang, Shuqi Cai, Zuozheng Liu, Rujing Wang

The international mega-event, such as the Winter Olympic Game, has been considered as one of the most carbon intensive activities worldwide.

Contrastive Meta Learning with Behavior Multiplicity for Recommendation

1 code implementation17 Feb 2022 Wei Wei, Chao Huang, Lianghao Xia, Yong Xu, Jiashu Zhao, Dawei Yin

In addition, to capture the diverse multi-behavior patterns, we design a contrastive meta network to encode the customized behavior heterogeneity for different users.

Contrastive Learning Meta-Learning

Underwater Differential Game: Finite-Time Target Hunting Task with Communication Delay

no code implementations1 Feb 2022 Wei Wei, Jingjing Wang, Jun Du, Zhengru Fang, Chunxiao Jiang, Yong Ren

Simulations show that underwater disturbances have a large impact on the system considering communication delay.

Deep Reinforcement Learning

Credit Valuation Adjustment with Replacement Closeout: Theory and Algorithms

no code implementations22 Jan 2022 Chaofan Sun, Ken Seng Tan, Wei Wei

In contrast to the risk-free closeout, the replacement closeout renders a nonlinear valuation system, which constitutes the major difficulty in the valuation of the counterparty credit risk.

Computational Efficiency

Meta-CPR: Generalize to Unseen Large Number of Agents with Communication Pattern Recognition Module

no code implementations14 Dec 2021 Wei-Cheng Tseng, Wei Wei, Da-Cheng Juan, Min Sun

The number of agents can grow or an environment sometimes needs to interact with a changing number of agents in real-world scenarios.

Meta Reinforcement Learning reinforcement-learning +2

RATE: Overcoming Noise and Sparsity of Textual Features in Real-Time Location Estimation

1 code implementation12 Nov 2021 Yu Zhang, Wei Wei, Binxuan Huang, Kathleen M. Carley, Yan Zhang

Real-time location inference of social media users is the fundamental of some spatial applications such as localized search and event detection.

Event Detection

Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework

1 code implementation28 Oct 2021 Lifan Yuan, Yichi Zhang, Yangyi Chen, Wei Wei

In this paper, we instantiate our framework with an attack algorithm named Textual Projected Gradient Descent (T-PGD).

Adversarial Attack Language Modelling

Geometry-Entangled Visual Semantic Transformer for Image Captioning

no code implementations29 Sep 2021 Ling Cheng, Wei Wei, Feida Zhu, Yong liu, Chunyan Miao

However, those fusion-based models, they are still criticized for the lack of geometry information for inter and intra attention refinement.

Caption Generation Image Captioning

Approaching the Transient Stability Boundary of a Power System: Theory and Applications

no code implementations26 Sep 2021 Peng Yang, Feng Liu, Wei Wei, Zhaojian Wang

Estimating the stability boundary is a fundamental and challenging problem in transient stability studies.

Context-aware Entity Typing in Knowledge Graphs

1 code implementation Findings (EMNLP) 2021 Weiran Pan, Wei Wei, Xian-Ling Mao

Knowledge graph entity typing aims to infer entities' missing types in knowledge graphs which is an important but under-explored issue.

Entity Typing Knowledge Graphs

Storage and Transmission Capacity Requirements of a Remote Solar Power Generation System

no code implementations13 Sep 2021 Yue Chen, Wei Wei, Cheng Wang, Miadreza Shafie-khah, João P. S. Catalão

Large solar power stations usually locate in remote areas and connect to the main grid via a long transmission line.

Multi-granularity Textual Adversarial Attack with Behavior Cloning

1 code implementation EMNLP 2021 Yangyi Chen, Jin Su, Wei Wei

Furthermore, we propose a reinforcement-learning based method to train a multi-granularity attack agent through behavior cloning with the expert knowledge from our MAYA algorithm to further reduce the query times.

Adversarial Attack Sentence

Heterogeneous Graph Neural Network with Multi-view Representation Learning

no code implementations31 Aug 2021 Zezhi Shao, Yongjun Xu, Wei Wei, Fei Wang, Zhao Zhang, Feida Zhu

Graph neural networks for heterogeneous graph embedding is to project nodes into a low-dimensional space by exploring the heterogeneity and semantics of the heterogeneous graph.

Graph Embedding Graph Neural Network +4

A Graph Data Augmentation Strategy with Entropy Preservation

no code implementations13 Jul 2021 Xue Liu, Dan Sun, Wei Wei

Considering the preservation of graph entropy, we propose an effective strategy to generate randomly perturbed training data but maintain both graph topology and graph entropy.

Data Augmentation Node Classification

Locality Relationship Constrained Multi-view Clustering Framework

no code implementations11 Jul 2021 Xiangzhu Meng, Wei Wei, Wenzhe Liu

LRC-MCF aims to explore the diversity, geometric, consensus and complementary information among different views, by capturing the locality relationship information and the common similarity relationships among multiple views.

Clustering MULTI-VIEW LEARNING

Global Context Enhanced Graph Neural Networks for Session-based Recommendation

2 code implementations9 Jun 2021 Ziyang Wang, Wei Wei, Gao Cong, Xiao-Li Li, Xian-Ling Mao, Minghui Qiu

In GCE-GNN, we propose a novel global-level item representation learning layer, which employs a session-aware attention mechanism to recursively incorporate the neighbors' embeddings of each node on the global graph.

Representation Learning Session-Based Recommendations

Emotion-aware Chat Machine: Automatic Emotional Response Generation for Human-like Emotional Interaction

no code implementations6 Jun 2021 Wei Wei, Jiayi Liu, Xianling Mao, Guibing Guo, Feida Zhu, Pan Zhou, Yuchong Hu

The consistency of a response to a given post at semantic-level and emotional-level is essential for a dialogue system to deliver human-like interactions.

Response Generation

Exploiting Global Contextual Information for Document-level Named Entity Recognition

no code implementations2 Jun 2021 Zanbo Wang, Wei Wei, Xianling Mao, Shanshan Feng, Pan Zhou, Zhiyong He, Sheng Jiang

To this end, we propose a model called Global Context enhanced Document-level NER (GCDoc) to leverage global contextual information from two levels, i. e., both word and sentence.

named-entity-recognition Named Entity Recognition +2

DARNet: Dual-Attention Residual Network for Automatic Diagnosis of COVID-19 via CT Images

1 code implementation14 May 2021 Jun Shi, Huite Yi, Shulan Ruan, Zhaohui Wang, Xiaoyu Hao, Hong An, Wei Wei

The ongoing global pandemic of Coronavirus Disease 2019 (COVID-19) poses a serious threat to public health and the economy.

Computed Tomography (CT) Diagnostic

On the Time-Inconsistent Deterministic Linear-Quadratic Control

no code implementations8 May 2021 Hongyan Cai, Danhong Chen, Yunfei Peng, Wei Wei

By studying the solvability of the Riccati equation, we show the existence and uniqueness of the linear equilibrium for the time-inconsistent LQ problem.

A Student-Teacher Architecture for Dialog Domain Adaptation under the Meta-Learning Setting

no code implementations6 Apr 2021 Kun Qian, Wei Wei, Zhou Yu

The most recent researches on domain adaption focus on giving the model a better initialization, rather than optimizing the adaptation process.

Domain Adaptation Meta-Learning

Research of Damped Newton Stochastic Gradient Descent Method for Neural Network Training

no code implementations31 Mar 2021 Jingcheng Zhou, Wei Wei, Zhiming Zheng

First-order methods like stochastic gradient descent(SGD) are recently the popular optimization method to train deep neural networks (DNNs), but second-order methods are scarcely used because of the overpriced computing cost in getting the high-order information.

regression Second-order methods

Beyond Visual Attractiveness: Physically Plausible Single Image HDR Reconstruction for Spherical Panoramas

no code implementations24 Mar 2021 Wei Wei, Li Guan, Yue Liu, Hao Kang, Haoxiang Li, Ying Wu, Gang Hua

By the proposed physical regularization, our method can generate HDRs which are not only visually appealing but also physically plausible.

HDR Reconstruction Single-shot HDR Reconstruction

Context-aware Biaffine Localizing Network for Temporal Sentence Grounding

no code implementations CVPR 2021 Daizong Liu, Xiaoye Qu, Jianfeng Dong, Pan Zhou, Yu Cheng, Wei Wei, Zichuan Xu, Yulai Xie

This paper addresses the problem of temporal sentence grounding (TSG), which aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query.

Sentence Temporal Sentence Grounding

Understanding Heart-Failure Patients EHR Clinical Features via SHAP Interpretation of Tree-Based Machine Learning Model Predictions

1 code implementation20 Mar 2021 Shuyu Lu, Ruoyu Chen, Wei Wei, Xinghua Lu

We examined whether machine learning models, more specifically the XGBoost model, can accurately predict patient stage based on EHR, and we further applied the SHapley Additive exPlanations (SHAP) framework to identify informative features and their interpretations.

A Data-Centric Framework for Composable NLP Workflows

1 code implementation EMNLP 2020 Zhengzhong Liu, Guanxiong Ding, Avinash Bukkittu, Mansi Gupta, Pengzhi Gao, Atif Ahmed, Shikun Zhang, Xin Gao, Swapnil Singhavi, Linwei Li, Wei Wei, Zecong Hu, Haoran Shi, Haoying Zhang, Xiaodan Liang, Teruko Mitamura, Eric P. Xing, Zhiting Hu

Empirical natural language processing (NLP) systems in application domains (e. g., healthcare, finance, education) involve interoperation among multiple components, ranging from data ingestion, human annotation, to text retrieval, analysis, generation, and visualization.

Text Retrieval

Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach

1 code implementation EMNLP 2021 Haoming Jiang, Bo Dai, Mengjiao Yang, Tuo Zhao, Wei Wei

An ideal environment for evaluating dialog systems, also known as the Turing test, needs to involve human interaction, which is usually not affordable for large-scale experiments.

Model-based Reinforcement Learning Off-policy evaluation +3

Graph Classification Based on Skeleton and Component Features

no code implementations2 Feb 2021 Xue Liu, Wei Wei, Xiangnan Feng, Xiaobo Cao, Dan Sun

Most existing popular methods for learning graph embedding only consider fixed-order global structural features and lack structures hierarchical representation.

General Classification Graph Classification +1

Large Deviations for SDE driven by Heavy-tailed Lévy Processes

no code implementations11 Jan 2021 Wei Wei, Qiao Huang, Jinqiao Duan

We obtain sample-path large deviations for a class of one-dimensional stochastic differential equations with bounded drifts and heavy-tailed L\'evy processes.

Probability 60H10, 60F10, 60J76

A Robust and Domain-Adaptive Approach for Low-Resource Named Entity Recognition

1 code implementation2 Jan 2021 Houjin Yu, Xian-Ling Mao, Zewen Chi, Wei Wei, Heyan Huang

Recently, it has attracted much attention to build reliable named entity recognition (NER) systems using limited annotated data.

Ranked #3 on Named Entity Recognition (NER) on SciERC (using extra training data)

Low Resource Named Entity Recognition named-entity-recognition +2

Representation Learning of Reconstructed Graphs Using Random Walk Graph Convolutional Network

no code implementations2 Jan 2021 Xing Li, Wei Wei, Xiangnan Feng, Zhiming Zheng

Graphs are often used to organize data because of their simple topological structure, and therefore play a key role in machine learning.

Graph Neural Network Graph Representation Learning +2

Generative Fairness Teaching

no code implementations1 Jan 2021 Rongmei Lin, Hanjun Dai, Li Xiong, Wei Wei

We propose a generative fairness teaching framework that provides a model with not only real samples but also synthesized samples to compensate the data biases during training.

Fairness

Context-Aware Temperature for Language Modeling

no code implementations1 Jan 2021 Pei-Hsin Wang, Sheng-Iou Hsieh, Shih-Chieh Chang, Yu-Ting Chen, Da-Cheng Juan, Jia-Yu Pan, Wei Wei

Current practices to apply temperature scaling assume either a fixed, or a manually-crafted dynamically changing schedule.

Language Modeling Language Modelling

FLAR: A Unified Prototype Framework for Few-Sample Lifelong Active Recognition

no code implementations ICCV 2021 Lei Fan, Peixi Xiong, Wei Wei, Ying Wu

To address this demand, in this paper, we propose a unified framework towards Few-sample Lifelong Active Recognition (FLAR), which aims at performing active recognition on progressively arising novel categories that only have few training samples.

Knowledge Distillation Lifelong learning +1

Contextual Temperature for Language Modeling

no code implementations25 Dec 2020 Pei-Hsin Wang, Sheng-Iou Hsieh, Shih-Chieh Chang, Yu-Ting Chen, Jia-Yu Pan, Wei Wei, Da-Chang Juan

Temperature scaling has been widely used as an effective approach to control the smoothness of a distribution, which helps the model performance in various tasks.

Language Modeling Language Modelling

Self-attention Comparison Module for Boosting Performance on Retrieval-based Open-Domain Dialog Systems

no code implementations21 Dec 2020 Tian Lan, Xian-Ling Mao, Zhipeng Zhao, Wei Wei, Heyan Huang

Since the pre-trained language models are widely used, retrieval-based open-domain dialog systems, have attracted considerable attention from researchers recently.

Open-Domain Dialog Retrieval

Ultra-Fast, Low-Storage, Highly Effective Coarse-grained Selection in Retrieval-based Chatbot by Using Deep Semantic Hashing

1 code implementation17 Dec 2020 Tian Lan, Xian-Ling Mao, Xiaoyan Gao, Wei Wei, Heyan Huang

Specifically, in our proposed DSHC model, a hashing optimizing module that consists of two autoencoder models is stacked on a trained dense representation model, and three loss functions are designed to optimize it.

Chatbot Open-Ended Question Answering +1

Accelerated, Scalable and Reproducible AI-driven Gravitational Wave Detection

no code implementations15 Dec 2020 E. A. Huerta, Asad Khan, Xiaobo Huang, Minyang Tian, Maksim Levental, Ryan Chard, Wei Wei, Maeve Heflin, Daniel S. Katz, Volodymyr Kindratenko, Dawei Mu, Ben Blaiszik, Ian Foster

The development of reusable artificial intelligence (AI) models for wider use and rigorous validation by the community promises to unlock new opportunities in multi-messenger astrophysics.

Distributed Computing Gravitational Wave Detection

Data-Driven Dispatchable Regions with Potentially Active Boundaries for Renewable Power Generation: Concept and Construction

no code implementations13 Dec 2020 Yanqi Liu, Zhigang Li, Wei Wei, Jiehui Zheng, Hongcai Zhang

State-of-the-art dispatchable region (DR) research has studied how system operational constraints influence the DR but has seldom considered the effect of the uncertainty features of RPG outputs.

Exploiting Group-level Behavior Pattern forSession-based Recommendation

no code implementations10 Dec 2020 Ziyang Wang, Wei Wei, Xian-Ling Mao, Xiao-Li Li, Shanshan Feng

In RNMSR, we propose to learn the user preference from both instance-level and group-level, respectively: (i) instance-level, which employs GNNs on a similarity-based item-pairwise session graph to capture the users' preference in instance-level.

Representation Learning Session-Based Recommendations

Spatiotemporal Graph Neural Network based Mask Reconstruction for Video Object Segmentation

no code implementations10 Dec 2020 Daizong Liu, Shuangjie Xu, Xiao-Yang Liu, Zichuan Xu, Wei Wei, Pan Zhou

To capture temporal information from previous frames, we use a memory network to refine the mask of current frame by retrieving historic masks in a temporal graph.

Graph Neural Network Object +3

Com-DDPG: A Multiagent Reinforcement Learning-based Offloading Strategy for Mobile Edge Computing

no code implementations9 Dec 2020 Honghao Gao, Xuejie Wang, Xiaojin Ma, Wei Wei, Shahid Mumtaz

First, we discuss the task dependency model, task priority model, energy consumption model, and average latency from the perspective of server clusters and multidependence on mobile tasks.

Decision Making Edge-computing +1 Distributed, Parallel, and Cluster Computing Multiagent Systems

Meta-Generating Deep Attentive Metric for Few-shot Classification

no code implementations3 Dec 2020 Lei Zhang, Fei Zhou, Wei Wei, Yanning Zhang

To mitigate this problem, we present a novel deep metric meta-generation method that turns to an orthogonal direction, ie, learning to adaptively generate a specific metric for a new FSL task based on the task description (eg, a few labelled samples).

Classification Few-Shot Learning +1

Unsupervised Alternating Optimization for Blind Hyperspectral Imagery Super-resolution

no code implementations3 Dec 2020 Jiangtao Nie, Lei Zhang, Wei Wei, Zhiqiang Lang, Yanning Zhang

One of the main reason comes from the fact that the predefined degeneration models (e. g. blur in spatial domain) utilized by most HSI SR methods often exist great discrepancy with the real one, which results in these deep models overfit and ultimately degrade their performance on real data.

Meta-Learning Super-Resolution

Differentiable Top-k with Optimal Transport

no code implementations NeurIPS 2020 Yujia Xie, Hanjun Dai, Minshuo Chen, Bo Dai, Tuo Zhao, Hongyuan Zha, Wei Wei, Tomas Pfister

Finding the k largest or smallest elements from a collection of scores, i. e., top-k operation, is an important model component widely used in information retrieval, machine learning, and data mining.

Information Retrieval Retrieval

Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization

no code implementations NeurIPS 2020 Hung-Jen Chen, An-Chieh Cheng, Da-Cheng Juan, Wei Wei, Min Sun

To preserve the knowledge we learn from previous instances, we proposed a method to protect the path by restricting the gradient updates of one instance from overriding past updates calculated from previous instances if these instances are not similar.

Continual Learning

AirConcierge: Generating Task-Oriented Dialogue via Efficient Large-Scale Knowledge Retrieval

1 code implementation Findings of the Association for Computational Linguistics 2020 Chieh-Yang Chen, Pei-Hsin Wang, Shih-Chieh Chang, Da-Cheng Juan, Wei Wei, Jia-Yu Pan

Despite recent success in neural task-oriented dialogue systems, developing such a real-world system involves accessing large-scale knowledge bases (KBs), which cannot be simply encoded by neural approaches, such as memory network mechanisms.

Retrieval Task-Oriented Dialogue Systems +2

Exploring Global Information for Session-based Recommendation

no code implementations20 Nov 2020 Ziyang Wang, Wei Wei, Gao Cong, Xiao-Li Li, Xian-Ling Mao, Minghui Qiu, Shanshan Feng

Based on BGNN, we propose a novel approach, called Session-based Recommendation with Global Information (SRGI), which infers the user preferences via fully exploring global item-transitions over all sessions from two different perspectives: (i) Fusion-based Model (SRGI-FM), which recursively incorporates the neighbor embeddings of each node on global graph into the learning process of session level item representation; and (ii) Constrained-based Model (SRGI-CM), which treats the global-level item-transition information as a constraint to ensure the learned item embeddings are consistent with the global item-transition.

Session-Based Recommendations

User-based Network Embedding for Collective Opinion Spammer Detection

no code implementations16 Nov 2020 Ziyang Wang, Wei Wei, Xian-Ling Mao, Guibing Guo, Pan Zhou, Shanshan Feng

Due to the huge commercial interests behind online reviews, a tremendousamount of spammers manufacture spam reviews for product reputation manipulation.

Network Embedding Relation

Target Guided Emotion Aware Chat Machine

no code implementations15 Nov 2020 Wei Wei, Jiayi Liu, Xianling Mao, Guibin Guo, Feida Zhu, Pan Zhou, Yuchong Hu, Shanshan Feng

The consistency of a response to a given post at semantic-level and emotional-level is essential for a dialogue system to deliver human-like interactions.

A Survey on Recent Advances in Sequence Labeling from Deep Learning Models

no code implementations13 Nov 2020 Zhiyong He, Zanbo Wang, Wei Wei, Shanshan Feng, Xianling Mao, Sheng Jiang

Sequence labeling (SL) is a fundamental research problem encompassing a variety of tasks, e. g., part-of-speech (POS) tagging, named entity recognition (NER), text chunking, etc.

Chunking Information Retrieval +9

Deep Cross-modal Hashing via Margin-dynamic-softmax Loss

no code implementations6 Nov 2020 Rong-Cheng Tu, Xian-Ling Mao, Rongxin Tu, Binbin Bian, Wei Wei, Heyan Huang

Finally, by minimizing the novel \textit{margin-dynamic-softmax loss}, the modality-specific hashing networks can be trained to generate hash codes which can simultaneously preserve the cross-modal similarity and abundant semantic information well.

Cross-Modal Retrieval Retrieval

Question Answering with Long Multiple-Span Answers

1 code implementation Findings of the Association for Computational Linguistics 2020 Ming Zhu, Aman Ahuja, Da-Cheng Juan, Wei Wei, Chandan K. Reddy

To this end, we present MASH-QA, a Multiple Answer Spans Healthcare Question Answering dataset from the consumer health domain, where answers may need to be excerpted from multiple, non-consecutive parts of text spanned across a long document.

Question Answering Sentence

Deep Kernel Supervised Hashing for Node Classification in Structural Networks

no code implementations26 Oct 2020 Jia-Nan Guo, Xian-Ling Mao, Shu-Yang Lin, Wei Wei, Heyan Huang

However, nearly all the existing network embedding based methods are hard to capture the actual category features of a node because of the linearly inseparable problem in low-dimensional space; meanwhile they cannot incorporate simultaneously network structure information and node label information into network embedding.

Classification General Classification +2

Differentiable Top-$k$ with Optimal Transport

no code implementations NeurIPS Workshop LMCA 2020 Yujia Xie, Hanjun Dai, Minshuo Chen, Bo Dai, Tuo Zhao, Hongyuan Zha, Wei Wei, Tomas Pfister

The top-$k$ operation, i. e., finding the $k$ largest or smallest elements from a collection of scores, is an important model component, which is widely used in information retrieval, machine learning, and data mining.

Information Retrieval Retrieval

Which Kind Is Better in Open-domain Multi-turn Dialog,Hierarchical or Non-hierarchical Models? An Empirical Study

no code implementations7 Aug 2020 Tian Lan, Xian-Ling Mao, Wei Wei, He-Yan Huang

Thus, in this paper, we will measure systematically nearly all representative hierarchical and non-hierarchical models over the same experimental settings to check which kind is better.

Representation Learning of Graphs Using Graph Convolutional Multilayer Networks Based on Motifs

no code implementations31 Jul 2020 Xing Li, Wei Wei, Xiangnan Feng, Xue Liu, Zhiming Zheng

The graph structure is a commonly used data storage mode, and it turns out that the low-dimensional embedded representation of nodes in the graph is extremely useful in various typical tasks, such as node classification, link prediction , etc.

Clustering Graph Neural Network +3

Remix: Rebalanced Mixup

no code implementations8 Jul 2020 Hsin-Ping Chou, Shih-Chieh Chang, Jia-Yu Pan, Wei Wei, Da-Cheng Juan

In this work, we propose a new regularization technique, Remix, that relaxes Mixup's formulation and enables the mixing factors of features and labels to be disentangled.

Robust Processing-In-Memory Neural Networks via Noise-Aware Normalization

no code implementations7 Jul 2020 Li-Huang Tsai, Shih-Chieh Chang, Yu-Ting Chen, Jia-Yu Pan, Wei Wei, Da-Cheng Juan

In this paper, we propose a noise-agnostic method to achieve robust neural network performance against any noise setting.

object-detection Object Detection +1

A Hybrid Natural Language Generation System Integrating Rules and Deep Learning Algorithms

no code implementations15 Jun 2020 Wei Wei, Bei Zhou, Georgios Leontidis

This paper proposes an enhanced natural language generation system combining the merits of both rule-based approaches and modern deep learning algorithms, boosting its performance to the extent where the generated textual content is capable of exhibiting agile human-writing styles and the content logic of which is highly controllable.

Text Generation

Cannot find the paper you are looking for? You can Submit a new open access paper.