Search Results for author: Hao Wang

Found 434 papers, 133 papers with code

融合零指代识别的篇章级机器翻译(Context-aware Machine Translation Integrating Zero Pronoun Recognition)

no code implementations CCL 2021 Hao Wang, Junhui Li, ZhengXian Gong

“在汉语等其他有省略代词习惯的语言中, 通常会删掉可从上下文信息推断出的代词。尽管以Transformer为代表的的神经机器翻译模型取得了巨大的成功, 但这种省略现象依旧对神经机器翻译模型造成了很大的挑战。本文在Transformer基础上提出了一个融合零指代识别的翻译模型, 并引入篇章上下文来丰富指代信息。具体地, 该模型采用联合学习的框架, 在翻译模型基础上, 联合了一个分类任务, 即判别句子中省略代词在句子所表示的成分, 使得模型能够融合零指代信息辅助翻译。通过在中英对话数据集上的实验, 验证了本文提出方法的有效性, 与基准模型相比, 翻译性能提升了1. 48个BLEU值。”

Machine Translation

Toward Knowledge-Enriched Conversational Recommendation Systems

no code implementations NLP4ConvAI (ACL) 2022 Tong Zhang, Yong liu, Boyang Li, Peixiang Zhong, Chen Zhang, Hao Wang, Chunyan Miao

Conversational Recommendation Systems recommend items through language based interactions with users. In order to generate naturalistic conversations and effectively utilize knowledge graphs (KGs) containing background information, we propose a novel Bag-of-Entities loss, which encourages the generated utterances to mention concepts related to the item being recommended, such as the genre or director of a movie.

Knowledge Graphs Recommendation Systems +1

Beyond 3DMM Space: Towards Fine-grained 3D Face Reconstruction

1 code implementation ECCV 2020 Xiangyu Zhu, Fan Yang, Di Huang, Chang Yu, Hao Wang, Jianzhu Guo, Zhen Lei, Stan Z. Li

However, most of their training data is constructed by 3D Morphable Model, whose space spanned is only a small part of the shape space.

3D Face Reconstruction

Non-Intrusive Load Monitoring for Feeder-Level EV Charging Detection: Sliding Window-based Approaches to Offline and Online Detection

no code implementations4 Dec 2023 Cameron Martin, Fucai Ke, Hao Wang

Our experimental results demonstrate high-accuracy EV charging detection at the feeder level, achieving an F-Score of 98. 88% in offline detection and 93. 01% in online detection.

Management Non-Intrusive Load Monitoring

PAC Privacy Preserving Diffusion Models

no code implementations2 Dec 2023 Qipan Xu, Youlong Ding, Jie Gao, Hao Wang

Data privacy protection is garnering increased attention among researchers.

Privacy Preserving

Quantum Langevin Dynamics for Optimization

no code implementations27 Nov 2023 Zherui Chen, Yuchen Lu, Hao Wang, Yizhou Liu, Tongyang Li

Finally, based on the observations when comparing QLD with classical Fokker-Plank-Smoluchowski equation, we propose a time-dependent QLD by making temperature and $\hbar$ time-dependent parameters, which can be theoretically proven to converge better than the time-independent case and also outperforms a series of state-of-the-art quantum and classical optimization algorithms in many non-convex landscapes.

How Far Have We Gone in Vulnerability Detection Using Large Language Models

no code implementations21 Nov 2023 Zeyu Gao, Hao Wang, Yuchen Zhou, Wenyu Zhu, Chao Zhang

Given the significant successes of Large Language Models (LLMs) in various tasks, there is growing anticipation of their efficacy in vulnerability detection.

Vulnerability Detection

On the Noise Scheduling for Generating Plausible Designs with Diffusion Models

no code implementations19 Nov 2023 Jiajie Fan, Laure Vuaille, Thomas Bäck, Hao Wang

We delve into the impact of noise schedules of diffusion models on the plausibility of the outcome: there exists a range of noise levels at which the model's performance decides the result plausibility.


Enhancing Recommender System Performance by Histogram Equalization

no code implementations15 Nov 2023 Hao Wang

As a preprocessing step to recommender system algorithms, histogram equalization could enhance both the accuracy and fairness metrics of the recommender system algorithms.

Fairness Recommendation Systems

SCAAT: Improving Neural Network Interpretability via Saliency Constrained Adaptive Adversarial Training

no code implementations9 Nov 2023 Rui Xu, Wenkang Qin, Peixiang Huang, Hao Wang, Lin Luo

Deep Neural Networks (DNNs) are expected to provide explanation for users to understand their black-box predictions.

APGL4SR: A Generic Framework with Adaptive and Personalized Global Collaborative Information in Sequential Recommendation

1 code implementation6 Nov 2023 Mingjia Yin, Hao Wang, Xiang Xu, Likang Wu, Sirui Zhao, Wei Guo, Yong liu, Ruiming Tang, Defu Lian, Enhong Chen

To this end, we propose a graph-driven framework, named Adaptive and Personalized Graph Learning for Sequential Recommendation (APGL4SR), that incorporates adaptive and personalized global collaborative information into sequential recommendation systems.

Graph Learning Multi-Task Learning +1

ProAgent: From Robotic Process Automation to Agentic Process Automation

1 code implementation2 Nov 2023 Yining Ye, Xin Cong, Shizuo Tian, Jiannan Cao, Hao Wang, Yujia Qin, Yaxi Lu, Heyang Yu, Huadong Wang, Yankai Lin, Zhiyuan Liu, Maosong Sun

Empirical experiments are conducted to detail its construction and execution procedure of workflow, showcasing the feasibility of APA, unveiling the possibility of a new paradigm of automation driven by agents.

Decision Making

Pre-trained Recommender Systems: A Causal Debiasing Perspective

1 code implementation30 Oct 2023 Ziqian Lin, Hao Ding, Nghia Hoang, Branislav Kveton, Anoop Deoras, Hao Wang

In particular, we propose to develop a generic recommender that captures universal interaction patterns by training on generic user-item interaction data extracted from different domains, which can then be fast adapted to improve few-shot learning performance in unseen new domains (with limited data).

Few-Shot Learning Recommendation Systems

Is Human Culture Locked by Evolution?

no code implementations28 Oct 2023 Hao Wang

Human culture has evolved for thousands of years and thrived in the era of Internet.

Recommendation Systems

Generative and Contrastive Paradigms Are Complementary for Graph Self-Supervised Learning

no code implementations24 Oct 2023 Yuxiang Wang, Xiao Yan, Chuang Hu, Fangcheng Fu, Wentao Zhang, Hao Wang, Shuo Shang, Jiawei Jiang

For graph self-supervised learning (GSSL), masked autoencoder (MAE) follows the generative paradigm and learns to reconstruct masked graph edges or node features.

Contrastive Learning Graph Classification +4

Woodpecker: Hallucination Correction for Multimodal Large Language Models

1 code implementation24 Oct 2023 Shukang Yin, Chaoyou Fu, Sirui Zhao, Tong Xu, Hao Wang, Dianbo Sui, Yunhang Shen, Ke Li, Xing Sun, Enhong Chen

Hallucination is a big shadow hanging over the rapidly evolving Multimodal Large Language Models (MLLMs), referring to the phenomenon that the generated text is inconsistent with the image content.

Vision-Enhanced Semantic Entity Recognition in Document Images via Visually-Asymmetric Consistency Learning

no code implementations23 Oct 2023 Hao Wang, Xiahua Chen, Rui Wang, Chenhui Chu

Extracting meaningful entities belonging to predefined categories from Visually-rich Form-like Documents (VFDs) is a challenging task.

LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay

no code implementations23 Oct 2023 Yihuai Lan, Zhiqiang Hu, Lei Wang, Yang Wang, Deheng Ye, Peilin Zhao, Ee-Peng Lim, Hui Xiong, Hao Wang

To achieve this goal, we adopt Avalon, a representative communication game, as the environment and use system prompts to guide LLM agents to play the game.

DocTrack: A Visually-Rich Document Dataset Really Aligned with Human Eye Movement for Machine Reading

1 code implementation23 Oct 2023 Hao Wang, Qingxuan Wang, Yue Li, Changqing Wang, Chenhui Chu, Rui Wang

The use of visually-rich documents (VRDs) in various fields has created a demand for Document AI models that can read and comprehend documents like humans, which requires the overcoming of technical, linguistic, and cognitive barriers.

document understanding Reading Comprehension

A Data-Centric Multi-Objective Learning Framework for Responsible Recommendation Systems

no code implementations20 Oct 2023 Xu Huang, Jianxun Lian, Hao Wang, Defu Lian, Xing Xie

Recommendation systems effectively guide users in locating their desired information within extensive content repositories.

Fairness Recommendation Systems

Fact-based Agent modeling for Multi-Agent Reinforcement Learning

no code implementations18 Oct 2023 Baofu Fang, Caiming Zheng, Hao Wang

To eliminate this assumption and achieve agent modeling in unknown scenarios, Fact-based Agent modeling (FAM) method is proposed in which fact-based belief inference (FBI) network models other agents in partially observable environment only based on its local information.

Federated Learning Multi-agent Reinforcement Learning +1

Combat Urban Congestion via Collaboration: Heterogeneous GNN-based MARL for Coordinated Platooning and Traffic Signal Control

no code implementations17 Oct 2023 Xianyue Peng, Hang Gao, Hao Wang, H. Michael Zhang

Over the years, reinforcement learning has emerged as a popular approach to develop signal control and vehicle platooning strategies either independently or in a hierarchical way.

Multi-agent Reinforcement Learning reinforcement-learning

Joint Optimization of Traffic Signal Control and Vehicle Routing in Signalized Road Networks using Multi-Agent Deep Reinforcement Learning

no code implementations16 Oct 2023 Xianyue Peng, Hang Gao, Gengyue Han, Hao Wang, Michael Zhang

In this paper, we propose a joint optimization approach for traffic signal control and vehicle routing in signalized road networks.

Private Synthetic Data Meets Ensemble Learning

no code implementations15 Oct 2023 Haoyuan Sun, Navid Azizan, Akash Srivastava, Hao Wang

When machine learning models are trained on synthetic data and then deployed on real data, there is often a performance drop due to the distribution shift between synthetic and real data.

Ensemble Learning

B-Spine: Learning B-Spline Curve Representation for Robust and Interpretable Spinal Curvature Estimation

no code implementations14 Oct 2023 Hao Wang, Qiang Song, Ruofeng Yin, Rui Ma, Yizhou Yu, Yi Chang

In this paper, we propose B-Spine, a novel deep learning pipeline to learn B-spline curve representation of the spine and estimate the Cobb angles for spinal curvature estimation from low-quality X-ray images.

Image-to-Image Translation

LAiW: A Chinese Legal Large Language Models Benchmark (A Technical Report)

1 code implementation9 Oct 2023 Yongfu Dai, Duanyu Feng, Jimin Huang, Haochen Jia, Qianqian Xie, Yifang Zhang, Weiguang Han, Wei Tian, Hao Wang

We have completed the first phase of evaluation, which mainly focuses on the capability of basic legal NLP.

Continuous Invariance Learning

no code implementations9 Oct 2023 Yong Lin, Fan Zhou, Lu Tan, Lintao Ma, Jiameng Liu, Yansu He, Yuan Yuan, Yu Liu, James Zhang, Yujiu Yang, Hao Wang

To address this challenge, we then propose Continuous Invariance Learning (CIL), which extracts invariant features across continuously indexed domains.

Cloud Computing

Empowering Many, Biasing a Few: Generalist Credit Scoring through Large Language Models

1 code implementation1 Oct 2023 Duanyu Feng, Yongfu Dai, Jimin Huang, Yifang Zhang, Qianqian Xie, Weiguang Han, Alejandro Lopez-Lira, Hao Wang

We then propose the first Credit and Risk Assessment Large Language Model (CALM) by instruction tuning, tailored to the nuanced demands of various financial risk assessment tasks.

Decision Making Language Modelling +1

LatticeGen: A Cooperative Framework which Hides Generated Text in a Lattice for Privacy-Aware Generation on Cloud

no code implementations29 Sep 2023 Mengke Zhang, Tianxing He, Tianle Wang, Lu Mi, FatemehSadat Mireshghallah, Binyi Chen, Hao Wang, Yulia Tsvetkov

In the current user-server interaction paradigm of prompted generation with large language models (LLM) on cloud, the server fully controls the generation process, which leaves zero options for users who want to keep the generated text to themselves.

Deep Learning-Based Connector Detection for Robotized Assembly of Automotive Wire Harnesses

no code implementations24 Sep 2023 Hao Wang, Björn Johansson

The mating of connectors is essential in the final assembly of automotive wire harnesses due to the importance of connectors on wire harness connection and signal transmission.

Autonomous Driving object-detection +1

A Systematic Literature Review of Computer Vision Applications in Robotized Wire Harness Assembly

no code implementations24 Sep 2023 Hao Wang, Omkar Salunkhe, Walter Quadrini, Björn Johansson, Dan Lämkull, Fredrik Ore, Mélanie Despeisse, Luca Fumagalli, Johan Stahre

This article presents a systematic literature review on computer vision applications that have been proposed for robotized wire harness assembly, derives challenges from existing studies, and identifies opportunities for future research to promote a more practical robotized assembly of wire harnesses.

Computer Vision Technology for Robotized Wire Harness Assembly

no code implementations24 Sep 2023 Hao Wang, Omkar Salunkhe, Walter Quadrini, Dan Lämkull, Fredrik Ore, Björn Johansson, Johan Stahre

This paradigm shift places more demand on automotive wiring harnesses from the safety perspective and stresses the greater importance of high-quality wire harness assembly in vehicles.

Autonomous Driving

Monotonic Neural Ordinary Differential Equation: Time-series Forecasting for Cumulative Data

no code implementations23 Sep 2023 Zhichao Chen, Leilei Ding, Zhixuan Chu, Yucheng Qi, Jianmin Huang, Hao Wang

Time-Series Forecasting based on Cumulative Data (TSFCD) is a crucial problem in decision-making across various industrial scenarios.

Decision Making Time Series +1

SPGM: Prioritizing Local Features for enhanced speech separation performance

no code implementations22 Sep 2023 Jia Qi Yip, Shengkui Zhao, Yukun Ma, Chongjia Ni, Chong Zhang, Hao Wang, Trung Hieu Nguyen, Kun Zhou, Dianwen Ng, Eng Siong Chng, Bin Ma

Dual-path is a popular architecture for speech separation models (e. g. Sepformer) which splits long sequences into overlapping chunks for its intra- and inter-blocks that separately model intra-chunk local features and inter-chunk global relationships.

Speech Separation

Collaborative Three-Stream Transformers for Video Captioning

no code implementations18 Sep 2023 Hao Wang, Libo Zhang, Heng Fan, Tiejian Luo

Meanwhile, we propose a cross-granularity attention module to align the interactions modeled by the three branches of transformers, then the three branches of transformers can support each other to exploit the most discriminative semantic information of different granularities for accurate predictions of captions.

Video Captioning

Community Battery Energy Storage Systems for Enhancing Distribution System Operation: A Multi-objective Optimization Approach

no code implementations5 Sep 2023 Yunqi Wang, Hao Wang, Markus Wagner, Ariel Liebman

The results show significant improvements in voltage regulation and DER utilization, demonstrating the potential of C-BESS in enabling more reliable DN operation.

Cross-Entropy-Based Approach to Multi-Objective Electric Vehicle Charging Infrastructure Planning

no code implementations27 Aug 2023 Jinhao Li, Yu Hui Yuan, Qiushi Cui, Hao Wang

Therefore, we are motivated to develop a comprehensive multi-objective framework for optimal CS placement in a traffic network overlaid by a distribution network, considering multiple stakeholders' interested factors, such as traffic flow, PEV charging time cost, PEV travel distance, and the reliability of the distribution network.

Decision Making

Hybrid Transformer-RNN Architecture for Household Occupancy Detection Using Low-Resolution Smart Meter Data

no code implementations27 Aug 2023 Xinyu Liang, Hao Wang

Residential occupancy detection has become an enabling technology in today's urbanized world for various smart home applications, such as building automation, energy management, and improved security and comfort.

energy management Management

MARL for Decentralized Electric Vehicle Charging Coordination with V2V Energy Exchange

no code implementations27 Aug 2023 Jiarong Fan, Hao Wang, Ariel Liebman

This paper addresses the EV charging coordination by considering vehicle-to-vehicle (V2V) energy exchange as the flexibility to harness in EV charging stations.

energy management Fairness +2

kTrans: Knowledge-Aware Transformer for Binary Code Embedding

no code implementations24 Aug 2023 Wenyu Zhu, Hao Wang, Yuchen Zhou, JiaMing Wang, Zihan Sha, Zeyu Gao, Chao Zhang

By feeding explicit knowledge as additional inputs to the Transformer, and fusing implicit knowledge with a novel pre-training task, kTrans provides a new perspective to incorporating domain knowledge into a Transformer framework.

Outlier Detection

ChatHaruhi: Reviving Anime Character in Reality via Large Language Model

1 code implementation18 Aug 2023 Cheng Li, Ziang Leng, Chenxi Yan, Junyi Shen, Hao Wang, Weishi MI, Yaying Fei, Xiaoyang Feng, Song Yan, HaoSheng Wang, Linkang Zhan, Yaokai Jia, Pingyu Wu, Haozhen Sun

Role-playing chatbots built on large language models have drawn interest, but better techniques are needed to enable mimicking specific fictional characters.

Language Modelling Large Language Model +2

KMF: Knowledge-Aware Multi-Faceted Representation Learning for Zero-Shot Node Classification

no code implementations15 Aug 2023 Likang Wu, Junji Jiang, Hongke Zhao, Hao Wang, Defu Lian, Mengdi Zhang, Enhong Chen

However, the multi-faceted semantic orientation in the feature-semantic alignment has been neglected by previous work, i. e. the content of a node usually covers diverse topics that are relevant to the semantics of multiple labels.

Node Classification Representation Learning +1

Methods for Acquiring and Incorporating Knowledge into Stock Price Prediction: A Survey

no code implementations9 Aug 2023 Liping Wang, Jiawei Li, Lifan Zhao, Zhizhuo Kou, Xiaohan Wang, Xinyi Zhu, Hao Wang, Yanyan Shen, Lei Chen

Predicting stock prices presents a challenging research problem due to the inherent volatility and non-linear nature of the stock market.

Stock Price Prediction

Backdoor Federated Learning by Poisoning Backdoor-Critical Layers

no code implementations8 Aug 2023 Haomin Zhuang, Mingxian Yu, Hao Wang, Yang Hua, Jian Li, Xu Yuan

Federated learning (FL) has been widely deployed to enable machine learning training on sensitive data across distributed devices.

Backdoor Attack Federated Learning

ConvFormer: Revisiting Transformer for Sequential User Modeling

no code implementations5 Aug 2023 Hao Wang, Jianxun Lian, Mingqi Wu, Haoxuan Li, Jiajun Fan, Wanyue Xu, Chaozhuo Li, Xing Xie

Sequential user modeling, a critical task in personalized recommender systems, focuses on predicting the next item a user would prefer, requiring a deep understanding of user behavior sequences.

Recommendation Systems

A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation

no code implementations ICCV 2023 Jinjing Zhu, Yunhao Luo, Xu Zheng, Hao Wang, Lin Wang

In this paper, we strive to answer the question "how to collaboratively learn convolutional neural network (CNN)-based and vision transformer (ViT)-based models by selecting and exchanging the reliable knowledge between them for semantic segmentation?"

Knowledge Distillation Semantic Segmentation

MFMAN-YOLO: A Method for Detecting Pole-like Obstacles in Complex Environment

no code implementations24 Jul 2023 Lei Cai, Hao Wang, Congling Zhou, Yongqiang Wang, Boyu Liu

To solve the problem that the feature information of pole-like obstacles in complex environments is easily lost, resulting in low detection accuracy and low real-time performance, a multi-scale hybrid attention mechanism detection algorithm is proposed in this paper.

Adversarial Latent Autoencoder with Self-Attention for Structural Image Synthesis

no code implementations19 Jul 2023 Jiajie Fan, Laure Vuaille, Hao Wang, Thomas Bäck

The potential of SA-ALAE is shown by generating engineering blueprints in a real automotive design task.

Image Generation

Local Conditional Neural Fields for Versatile and Generalizable Large-Scale Reconstructions in Computational Imaging

1 code implementation12 Jul 2023 Hao Wang, Jiabei Zhu, Yunzhe Li, QianWan Yang, Lei Tian

Unlike traditional neural fields frameworks, LCNF incorporates a local conditional representation that promotes model generalization, learning multiscale information, and efficient processing of large-scale imaging data.

Image Reconstruction Super-Resolution

LogitMat : Zeroshot Learning Algorithm for Recommender Systems without Transfer Learning or Pretrained Models

no code implementations6 Jul 2023 Hao Wang

Unlike other sectors such as fraud detection in the Fintech industry, recommender system is both deep and broad.

Fraud Detection Meta-Learning +2

Optimal Bandwidth Selection for DENCLUE Algorithm

no code implementations6 Jul 2023 Hao Wang

In 2007, a density-based clustering algorithm named DENCLUE was invented to solve clustering problem for nonlinear data structures.


FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy

3 code implementations1 Jul 2023 Jianqing Zhang, Yang Hua, Hao Wang, Tao Song, Zhengui Xue, Ruhui Ma, Haibing Guan

To address this, we propose the Federated Conditional Policy (FedCP) method, which generates a conditional policy for each sample to separate the global information and personalized information in its features and then processes them by a global head and a personalized head, respectively.

Personalized Federated Learning

Counterfactual Collaborative Reasoning

no code implementations30 Jun 2023 Jianchao Ji, Zelong Li, Shuyuan Xu, Max Xiong, Juntao Tan, Yingqiang Ge, Hao Wang, Yongfeng Zhang

In this paper, we explore how the two reasoning abilities can be jointly modeled to enhance both accuracy and explainability of machine learning models.

counterfactual Counterfactual Reasoning +3

PMaF: Deep Declarative Layers for Principal Matrix Features

1 code implementation26 Jun 2023 Zhiwei Xu, Hao Wang, Yanbin Liu, Stephen Gould

We explore two differentiable deep declarative layers, namely least squares on sphere (LESS) and implicit eigen decomposition (IED), for learning the principal matrix features (PMaF).

Energy Optimization for HVAC Systems in Multi-VAV Open Offices: A Deep Reinforcement Learning Approach

no code implementations23 Jun 2023 Hao Wang, Xiwen Chen, Natan Vital, Edward. Duffy, Abolfazl Razi

It takes only a total of 40 minutes for 5 epochs (about 7. 75 minutes per epoch) to train a network with superior performance and covering diverse conditions for its low-complexity architecture; therefore, it easily adapts to changes in the building setups, weather conditions, occupancy rate, etc.

energy management Total Energy

Taxonomy-Structured Domain Adaptation

1 code implementation13 Jun 2023 Tianyi Liu, Zihao Xu, Hao He, Guang-Yuan Hao, Guang-He Lee, Hao Wang

Domain adaptation aims to mitigate distribution shifts among different domains.

Domain Adaptation

Skellam Rank: Fair Learning to Rank Algorithm Based on Poisson Process and Skellam Distribution for Recommender Systems

no code implementations11 Jun 2023 Hao Wang

In this paper, we propose a fair recommender system algorithm that uses Poisson process and Skellam distribution.

Fairness Learning-To-Rank +2

Self-Interpretable Time Series Prediction with Counterfactual Explanations

no code implementations9 Jun 2023 Jingquan Yan, Hao Wang

Interpretable time series prediction is crucial for safety-critical areas such as healthcare and autonomous driving.

Autonomous Driving counterfactual +3

A Peer-to-peer Federated Continual Learning Network for Improving CT Imaging from Multiple Institutions

no code implementations3 Jun 2023 Hao Wang, Ruihong He, XiaoYu Zhang, Zhaoying Bian, Dong Zeng, Jianhua Ma

In this work, we propose a novel peer-to-peer federated continual learning strategy to improve low-dose CT imaging performance from multiple institutions.

Computed Tomography (CT) Continual Learning +1

Representation Reliability and Its Impact on Downstream Tasks

no code implementations31 May 2023 Young-Jin Park, Hao Wang, Shervin Ardeshir, Navid Azizan

Self-supervised pre-trained models extract general-purpose representations from data, and quantifying how reliable they are is crucial because many downstream models use these representations as input for their own tasks.

A Survey on Large Language Models for Recommendation

1 code implementation31 May 2023 Likang Wu, Zhi Zheng, Zhaopeng Qiu, Hao Wang, Hongchao Gu, Tingjia Shen, Chuan Qin, Chen Zhu, HengShu Zhu, Qi Liu, Hui Xiong, Enhong Chen

Large Language Models (LLMs) have emerged as powerful tools in the field of Natural Language Processing (NLP) and have recently gained significant attention in the domain of Recommendation Systems (RS).

Recommendation Systems Self-Supervised Learning

DPFormer: Learning Differentially Private Transformer on Long-Tailed Data

no code implementations28 May 2023 Youlong Ding, Xueyang Wu, Hao Wang, Weike Pan

The Transformer has emerged as a versatile and effective architecture with broad applications.

Modeling Task Relationships in Multi-variate Soft Sensor with Balanced Mixture-of-Experts

no code implementations25 May 2023 Yuxin Huang, Hao Wang, Zhaoran Liu, Licheng Pan, Haozhe Li, Xinggao Liu

Accurate estimation of multiple quality variables is critical for building industrial soft sensor models, which have long been confronted with data efficiency and negative transfer issues.

MaGIC: Multi-modality Guided Image Completion

no code implementations19 May 2023 Yongsheng Yu, Hao Wang, Tiejian Luo, Heng Fan, Libo Zhang

In this paper, we propose a novel, simple yet effective method for Multi-modal Guided Image Completion, dubbed MaGIC, which not only supports a wide range of single modality as the guidance (e. g., text, canny edge, sketch, segmentation, depth, and pose), but also adapts to arbitrarily customized combination of these modalities (i. e., arbitrary multi-modality) for image completion.

Two-Bit RIS-Aided Communications at 3.5GHz: Some Insights from the Measurement Results Under Multiple Practical Scenes

no code implementations19 May 2023 Shun Zhang, Haoran Sun, Runze Yu, Hongshenyuan Cui, Jian Ren, Feifei Gao, Shi Jin, Hongxiang Xie, Hao Wang

In particular, we adopt a self-developed broadband intelligent communication system 40MHz-Net (BICT-40N) terminal in order to fully acquire the channel information.

Intelligent Communication Quantization

Self-discipline on multiple channels

1 code implementation27 Apr 2023 Jiutian Zhao, Liang Luo, Hao Wang

Comparative experimental results on both datasets show that SMC-2 outperforms Label Smoothing Regularizaion and Self-distillation From The Last Mini-batch on all models, and outperforms the state-of-the-art Sharpness-Aware Minimization method on 83% of the models. Compatibility of SMC-2 and data augmentation experimental results show that using both SMC-2 and data augmentation improves the generalization ability of the model between 0. 28% and 1. 80% compared to using only data augmentation.

Data Augmentation

Fairness-Aware Optimization of Vehicle-to-Vehicle Interaction for Smart EV Charging Coordination

no code implementations5 Apr 2023 Aditya Khele, Canchen Jiang, Hao Wang

We formulate a cost minimization problem for an EV charging station to optimize the V2V schedule together with vehicle-to-grid (V2G), grid-to-vehicle (G2V) charging, as well as the use of renewable energy.


Optimal Energy Storage Scheduling for Wind Curtailment Reduction and Energy Arbitrage: A Deep Reinforcement Learning Approach

no code implementations5 Apr 2023 Jinhao Li, Changlong Wang, Hao Wang

However, the variable nature of wind generation can undermine system reliability and lead to wind curtailment, causing substantial economic losses to wind power producers.


Evolution of the Online Rating Platform Data Structures and its Implications for Recommender Systems

no code implementations25 Mar 2023 Hao Wang

Understanding the evolution pattern and its underlying mechanism is the key to understand the structures of input data for recommender systems.

Recommendation Systems

Analysis and Visualization of the Parameter Space of Matrix Factorization-based Recommender Systems

no code implementations25 Mar 2023 Hao Wang

We continue the research in this direction in this paper, and visualize the inner structure of the parameter space of matrix factorization technologies.

Recommendation Systems

TAPS3D: Text-Guided 3D Textured Shape Generation from Pseudo Supervision

1 code implementation CVPR 2023 Jiacheng Wei, Hao Wang, Jiashi Feng, Guosheng Lin, Kim-Hui Yap

We conduct extensive experiments to analyze each of our proposed components and show the efficacy of our framework in generating high-fidelity 3D textured and text-relevant shapes.

Distribution-restrained Softmax Loss for the Model Robustness

no code implementations22 Mar 2023 Hao Wang, Chen Li, JinZhe Jiang, Xin Zhang, YaQian Zhao, Weifeng Gong

Recently, the robustness of deep learning models has received widespread attention, and various methods for improving model robustness have been proposed, including adversarial training, model architecture modification, design of loss functions, certified defenses, and so on.

A Dual-branch Self-supervised Representation Learning Framework for Tumour Segmentation in Whole Slide Images

no code implementations20 Mar 2023 Hao Wang, Euijoon Ahn, Jinman Kim

These SSL approaches, however, are not designed for handling multi-resolution WSIs, which limits their performance in learning discriminative image features.

Representation Learning Self-Supervised Learning +1

Enhancing Text Generation with Cooperative Training

1 code implementation16 Mar 2023 Tong Wu, Hao Wang, Zhongshen Zeng, Wei Wang, Hai-Tao Zheng, Jiaxing Zhang

Recently, there has been a surge in the use of generated data to enhance the performance of downstream models, largely due to the advancements in pre-trained language models.


Betti Number for Point Sets

no code implementations11 Mar 2023 Hao Wang

Topology is the foundation for many industrial applications ranging from CAD to simulation analysis.

PowerMat: context-aware recommender system without user item rating values that solves the cold-start problem

no code implementations11 Mar 2023 Hao Wang

One important sub-field of recommender systems that has been stagnating is context-aware recommender systems.

Recommendation Systems

Kernel-CF: Collaborative filtering done right with social network analysis and kernel smoothing

no code implementations8 Mar 2023 Hao Wang

Collaborative filtering is the simplest but oldest machine learning algorithm in the field of recommender systems.

Collaborative Filtering Recommendation Systems

GUESR: A Global Unsupervised Data-Enhancement with Bucket-Cluster Sampling for Sequential Recommendation

no code implementations1 Mar 2023 Yongqiang Han, Likang Wu, Hao Wang, Guifeng Wang, Mengdi Zhang, Zhi Li, Defu Lian, Enhong Chen

Sequential Recommendation is a widely studied paradigm for learning users' dynamic interests from historical interactions for predicting the next potential item.

Contrastive Learning Sequential Recommendation

Hierarchical Fuel-Cell Airpath Control: an Efficiency-Aware MIMO Control Approach Combined with a Novel Constraint-Enforcing Reference Governor

no code implementations25 Feb 2023 Eli Bacher-Chong, Mostafa Ali Ayubirad, Zeng Qiu, Hao Wang, Alireza Goshtasbi, Hamid R. Ossareh

Compared with a single-input single-output (SISO) air-flow control approach, the proposed MIMO control approach shows up to 7. 36 percent lower hydrogen fuel consumption.

TMoE-P: Towards the Pareto Optimum for Multivariate Soft Sensors

no code implementations21 Feb 2023 Licheng Pan, Hao Wang, Zhichao Chen, Yuxing Huang, Xinggao Liu

We further present a Task-aware Mixture-of-Experts framework for achieving the Pareto optimum (TMoE-P) in multi-variate soft sensor, which consists of a stacked OMoE module and a POR module.

AttentionMixer: An Accurate and Interpretable Framework for Process Monitoring

no code implementations21 Feb 2023 Hao Wang, Zhiyu Wang, Yunlong Niu, Zhaoran Liu, Haozhe Li, Yilin Liao, Yuxin Huang, Xinggao Liu

An accurate and explainable automatic monitoring system is critical for the safety of high efficiency energy conversion plants that operate under extreme working condition.

Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation

2 code implementations6 Feb 2023 Zihao Xu, Guang-Yuan Hao, Hao He, Hao Wang

To address this challenge, we first provide a formal definition of domain index from the probabilistic perspective, and then propose an adversarial variational Bayesian framework that infers domain indices from multi-domain data, thereby providing additional insight on domain relations and improving domain adaptation performance.

Domain Adaptation

Real-Time High-Resolution Pedestrian Detection in Crowded Scenes via Parallel Edge Offloading

no code implementations20 Jan 2023 Hao Wang, Hao Bao, Liekang Zeng, Ke Luo, Xu Chen

To identify dense and small-size pedestrians in surveillance systems, high-resolution cameras are widely deployed, where high-resolution images are captured and delivered to off-the-shelf pedestrian detection models.

Pedestrian Detection Scheduling

Fair Recommendation by Geometric Interpretation and Analysis of Matrix Factorization

no code implementations10 Jan 2023 Hao Wang

Matrix factorization-based recommender system is in effect an angle preserving dimensionality reduction technique.

Dimensionality Reduction Recommendation Systems

More is Better: A Database for Spontaneous Micro-Expression with High Frame Rates

no code implementations3 Jan 2023 Sirui Zhao, Huaying Tang, Xinglong Mao, Shifeng Liu, Hanqing Tao, Hao Wang, Tong Xu, Enhong Chen

To solve the problem of ME data hunger, we construct a dynamic spontaneous ME dataset with the largest current ME data scale, called DFME (Dynamic Facial Micro-expressions), which includes 7, 526 well-labeled ME videos induced by 671 participants and annotated by more than 20 annotators throughout three years.

Deep Reinforcement Learning for Wind and Energy Storage Coordination in Wholesale Energy and Ancillary Service Markets

no code implementations27 Dec 2022 Jinhao Li, Changlong Wang, Hao Wang

Simulations also show that using curtailed wind generation as a power source for charging the BESS can lead to additional financial gains.

energy trading Scheduling

First De-Trend then Attend: Rethinking Attention for Time-Series Forecasting

1 code implementation15 Dec 2022 Xiyuan Zhang, Xiaoyong Jin, Karthick Gopalswamy, Gaurav Gupta, Youngsuk Park, Xingjian Shi, Hao Wang, Danielle C. Maddix, Yuyang Wang

Transformer-based models have gained large popularity and demonstrated promising results in long-term time-series forecasting in recent years.

Time Series Time Series Forecasting

Proximal Policy Optimization Based Reinforcement Learning for Joint Bidding in Energy and Frequency Regulation Markets

no code implementations13 Dec 2022 Muhammad Anwar, Changlong Wang, Frits de Nijs, Hao Wang

Driven by the global decarbonization effort, the rapid integration of renewable energy into the conventional electricity grid presents new challenges and opportunities for the battery energy storage system (BESS) participating in the energy market.

Model-Free Approach to Fair Solar PV Curtailment Using Reinforcement Learning

no code implementations13 Dec 2022 Zhuo Wei, Frits de Nijs, Jinhao Li, Hao Wang

This paper investigates reinforcement learning, which gradually optimizes a fair PV curtailment strategy by interacting with the system.

Fairness reinforcement-learning +1

Robust Perception through Equivariance

1 code implementation12 Dec 2022 Chengzhi Mao, Lingyu Zhang, Abhishek Joshi, Junfeng Yang, Hao Wang, Carl Vondrick

In this paper, we introduce a framework that uses the dense intrinsic constraints in natural images to robustify inference.

Adversarial Robustness Instance Segmentation +2

Complete cavity map of the C. elegans connectome

no code implementations7 Dec 2022 Bo Liu, Rongmei Yang, Hao Wang, Linyuan Lü

This study reports for the first time a complete cavity map of C. elegans neural network, developing a new method for mining higher-order structures that can be applied by researchers in neuroscience, network science and other interdisciplinary fields to explore higher-order structural markers of complex systems.

Pareto Pairwise Ranking for Fairness Enhancement of Recommender Systems

no code implementations6 Dec 2022 Hao Wang

Famous algorithms such as Bayesian Personalized Ranking and Collaborative Less is More Filtering have left deep impact in both academia and industry.

Fairness Learning-To-Rank +1

AL-iGAN: An Active Learning Framework for Tunnel Geological Reconstruction Based on TBM Operational Data

no code implementations2 Dec 2022 Hao Wang, Lixue Liu, Xueguan Song, Chao Zhang, DaCheng Tao

In tunnel boring machine (TBM) underground projects, an accurate description of the rock-soil types distributed in the tunnel can decrease the construction risk ({\it e. g.} surface settlement and landslide) and improve the efficiency of construction.

Active Learning

FedALA: Adaptive Local Aggregation for Personalized Federated Learning

2 code implementations2 Dec 2022 Jianqing Zhang, Yang Hua, Hao Wang, Tao Song, Zhengui Xue, Ruhui Ma, Haibing Guan

A key challenge in federated learning (FL) is the statistical heterogeneity that impairs the generalization of the global model on each client.

Personalized Federated Learning Test

The Hypervolume Indicator Hessian Matrix: Analytical Expression, Computational Time Complexity, and Sparsity

1 code implementation8 Nov 2022 André H. Deutz, Michael T. M. Emmerich, Hao Wang

Also, for the general $m$-dimensional case, a compact recursive analytical expression is established, and its algorithmic implementation is discussed.

Multiobjective Optimization Second-order methods

Fast Key Points Detection and Matching for Tree-Structured Images

no code implementations7 Nov 2022 Hao Wang, Xiwen Chen, Abolfazl Razi, Rahul Amin

The proposed algorithm is applicable to a variety of tree-structured image matching, but our focus is on dendrites, recently-developed visual identifiers.

Graph Matching Key Point Matching

R$^2$F: A General Retrieval, Reading and Fusion Framework for Document-level Natural Language Inference

1 code implementation22 Oct 2022 Hao Wang, Yixin Cao, Yangguang Li, Zhen Huang, Kun Wang, Jing Shao

Document-level natural language inference (DOCNLI) is a new challenging task in natural language processing, aiming at judging the entailment relationship between a pair of hypothesis and premise documents.

Natural Language Inference Retrieval

Federated Unlearning for On-Device Recommendation

no code implementations20 Oct 2022 Wei Yuan, Hongzhi Yin, Fangzhao Wu, Shijie Zhang, Tieke He, Hao Wang

It removes a user's contribution by rolling back and calibrating the historical parameter updates and then uses these updates to speed up federated recommender reconstruction.

Recommendation Systems

Entire Space Counterfactual Learning: Tuning, Analytical Properties and Industrial Applications

no code implementations20 Oct 2022 Hao Wang, Zhichao Chen, Jiajun Fan, Yuxin Huang, Weiming Liu, Xinggao Liu

As a basic research problem for building effective recommender systems, post-click conversion rate (CVR) estimation has long been plagued by sample selection bias and data sparsity issues.

Auxiliary Learning counterfactual +2

Visual Prompt Tuning for Test-time Domain Adaptation

no code implementations10 Oct 2022 Yunhe Gao, Xingjian Shi, Yi Zhu, Hao Wang, Zhiqiang Tang, Xiong Zhou, Mu Li, Dimitris N. Metaxas

First, DePT plugs visual prompts into the vision Transformer and only tunes these source-initialized prompts during adaptation.

Test Unsupervised Domain Adaptation

1st ICLR International Workshop on Privacy, Accountability, Interpretability, Robustness, Reasoning on Structured Data (PAIR^2Struct)

no code implementations7 Oct 2022 Hao Wang, WanYu Lin, Hao He, Di Wang, Chengzhi Mao, Muhan Zhang

Recent years have seen advances on principles and guidance relating to accountable and ethical use of artificial intelligence (AI) spring up around the globe.

ManiCLIP: Multi-Attribute Face Manipulation from Text

1 code implementation2 Oct 2022 Hao Wang, Guosheng Lin, Ana García del Molino, Anran Wang, Jiashi Feng, Zhiqi Shen

In this paper we present a novel multi-attribute face manipulation method based on textual descriptions.

Text-based Image Editing

Insurance Contract for High Renewable Energy Integration

no code implementations21 Sep 2022 Dongwei Zhao, Hao Wang, Jianwei Huang, Xiaojun Lin

A proper insurance design needs to resolve the following two challenges: (i) users' reliability preference is private information; and (ii) the insurance design is tightly coupled with the renewable energy investment decision.

Total Energy Vocal Bursts Intensity Prediction

LO-Det: Lightweight Oriented Object Detection in Remote Sensing Images

no code implementations16 Sep 2022 Zhanchao Huang, Wei Li, Xiang-Gen Xia, Hao Wang, Feiran Jie, Ran Tao

Specifically, a channel separation-aggregation (CSA) structure is designed to simplify the complexity of stacked separable convolutions, and a dynamic receptive field (DRF) mechanism is developed to maintain high accuracy by customizing the convolution kernel and its perception range dynamically when reducing the network complexity.

object-detection Object Detection +1

Model Inversion Attacks against Graph Neural Networks

no code implementations16 Sep 2022 Zaixi Zhang, Qi Liu, Zhenya Huang, Hao Wang, Chee-Kong Lee, Enhong Chen

One famous privacy attack against data analysis models is the model inversion attack, which aims to infer sensitive data in the training dataset and leads to great privacy concerns.

Reinforcement Learning (RL)

Transformer-CNN Cohort: Semi-supervised Semantic Segmentation by the Best of Both Students

no code implementations6 Sep 2022 Xu Zheng, Yunhao Luo, Hao Wang, Chong Fu, Lin Wang

To this end, we propose class-aware feature consistency distillation (CFCD) that first leverages the outputs of each student as the pseudo labels and generates class-aware feature (CF) maps.

Semi-Supervised Semantic Segmentation

Task-wise Sampling Convolutions for Arbitrary-Oriented Object Detection in Aerial Images

1 code implementation6 Sep 2022 Zhanchao Huang, Wei Li, Xiang-Gen Xia, Hao Wang, Ran Tao

However, the inconsistent features for the localization and classification tasks in AOOD models may lead to ambiguity and low-quality object predictions, which constrains the detection performance.

object-detection Object Detection In Aerial Images +1

Few-shot Incremental Event Detection

no code implementations5 Sep 2022 Hao Wang, Hanwen Shi, Jianyong Duan

In practice, however, the lack of high-quality labeled data of new event classes makes it difficult to obtain enough data for model training.

Event Detection Incremental Learning

Soft MIMO Detection Using Marginal Posterior Probability Statistics

no code implementations17 Aug 2022 Jiankun Zhang, Hao Wang, Jing Qian, Zhenxing Gao

Soft demodulation of received symbols into bit log-likelihood ratios (LLRs) is at the very heart of multiple-input-multiple-output (MIMO) detection.

Online Learning Based NLOS Ranging Error Mitigation in 5G Positioning

no code implementations16 Aug 2022 Jiankun Zhang, Hao Wang

The fifth-generation (5G) wireless communication is useful for positioning due to its large bandwidth and low cost.

Energy and Spectrum Efficient Federated Learning via High-Precision Over-the-Air Computation

no code implementations15 Aug 2022 Liang Li, Chenpei Huang, Dian Shi, Hao Wang, Xiangwei Zhou, Minglei Shu, Miao Pan

Guided by FL convergence analysis, we formulate a joint transmission probability and local computing control optimization, aiming to minimize the overall energy consumption (i. e., iterative local computing + multi-round communications) of mobile devices in FL.

Federated Learning

A Screening Strategy for Structured Optimization Involving Nonconvex $\ell_{q,p}$ Regularization

no code implementations2 Aug 2022 Tiange Li, Xiangyu Yang, Hao Wang

In this paper, we develop a simple yet effective screening rule strategy to improve the computational efficiency in solving structured optimization involving nonconvex $\ell_{q, p}$ regularization.

Paired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval

no code implementations29 Jul 2022 Hao Wang, Guosheng Lin, Steven C. H. Hoi, Chunyan Miao

When we do online paired data augmentation, we first generate augmented text through random token replacement, then pass the augmented text into the latent space alignment module to output the latent codes, which are finally fed to StyleGAN2 to generate the augmented images.

Cross-Modal Retrieval Data Augmentation +3

3D Cartoon Face Generation with Controllable Expressions from a Single GAN Image

no code implementations29 Jul 2022 Hao Wang, Guosheng Lin, Steven C. H. Hoi, Chunyan Miao

To this end, we discover the semantic meanings of StyleGAN latent space, such that we are able to produce face images of various expressions, poses, and lighting by controlling the latent codes.

Face Generation Face Model

Subgraph Frequency Distribution Estimation using Graph Neural Networks

no code implementations14 Jul 2022 Zhongren Chen, Xinyue Xu, Shengyi Jiang, Hao Wang, Lu Mi

Small subgraphs (graphlets) are important features to describe fundamental units of a large network.

Earthformer: Exploring Space-Time Transformers for Earth System Forecasting

1 code implementation12 Jul 2022 Zhihan Gao, Xingjian Shi, Hao Wang, Yi Zhu, Yuyang Wang, Mu Li, Dit-yan Yeung

With the explosive growth of the spatiotemporal Earth observation data in the past decade, data-driven models that apply Deep Learning (DL) are demonstrating impressive potential for various Earth system forecasting tasks.

Earth Surface Forecasting Weather Forecasting

Enabling Harmonious Human-Machine Interaction with Visual-Context Augmented Dialogue System: A Review

no code implementations2 Jul 2022 Hao Wang, Bin Guo, Yating Zeng, Yasan Ding, Chen Qiu, Ying Zhang, Lina Yao, Zhiwen Yu

The intelligent dialogue system, aiming at communicating with humans harmoniously with natural language, is brilliant for promoting the advancement of human-machine interaction in the era of artificial intelligence.

Winning the CVPR'2022 AQTC Challenge: A Two-stage Function-centric Approach

1 code implementation20 Jun 2022 Shiwei Wu, Weidong He, Tong Xu, Hao Wang, Enhong Chen

Affordance-centric Question-driven Task Completion for Egocentric Assistant(AQTC) is a novel task which helps AI assistant learn from instructional videos and scripts and guide the user step-by-step.

Landscape Learning for Neural Network Inversion

no code implementations ICCV 2023 Ruoshi Liu, Chengzhi Mao, Purva Tendulkar, Hao Wang, Carl Vondrick

Many machine learning methods operate by inverting a neural network at inference time, which has become a popular technique for solving inverse problems in computer vision, robotics, and graphics.

Adversarial Defense

DotMat: Solving Cold-start Problem and Alleviating Sparsity Problem for Recommender Systems

no code implementations31 May 2022 Hao Wang

Cold-start and sparsity problem are two key intrinsic problems to recommender systems.

Recommendation Systems

DH-GAN: A Physics-driven Untrained Generative Adversarial Network for 3D Microscopic Imaging using Digital Holography

no code implementations25 May 2022 Xiwen Chen, Hao Wang, Abolfazl Razi, Michael Kozicki, Christopher Mann

Digital holography is a 3D imaging technique by emitting a laser beam with a plane wavefront to an object and measuring the intensity of the diffracted waveform, called holograms.

Theoretically Accurate Regularization Technique for Matrix Factorization based Recommender Systems

no code implementations21 May 2022 Hao Wang

Regularization is a popular technique to solve the overfitting problem of machine learning algorithms.

Fairness Recommendation Systems +1

Probability Distribution of Hypervolume Improvement in Bi-objective Bayesian Optimization

no code implementations11 May 2022 Hao Wang, Kaifeng Yang, Michael Affenzeller, Michael Emmerich

This work provides the exact expression of the probability distribution of the hypervolume improvement (HVI) for bi-objective generalization of Bayesian optimization.

Bayesian Optimization

High Dimensional Bayesian Optimization with Kernel Principal Component Analysis

no code implementations28 Apr 2022 Kirill Antonov, Elena Raponi, Hao Wang, Carola Doerr

Bayesian Optimization (BO) is a surrogate-based global optimization strategy that relies on a Gaussian Process regression (GPR) model to approximate the objective function and an acquisition function to suggest candidate points.

Bayesian Optimization GPR +2

KL-Mat : Fair Recommender System via Information Geometry

no code implementations27 Apr 2022 Hao Wang

Recommender system has intrinsic problems such as sparsity and fairness.

Fairness Recommendation Systems

MovieMat: Context-aware Movie Recommendation with Matrix Factorization by Matrix Fitting

no code implementations27 Apr 2022 Hao Wang

In this paper, we take advantage of the MatMat framework, which factorizes matrices by matrix fitting to build a context-aware movie recommender system that is superior to classic matrix factorization and comparable in the fairness metric.

Collaborative Filtering Fairness +4

Extremal GloVe: Theoretically Accurate Distributed Word Embedding by Tail Inference

no code implementations27 Apr 2022 Hao Wang

However, the initial formulation of GloVe is not theoretically sound in two aspects, namely the selection of the weighting function and its power exponent is ad-hoc.

Recommendation Systems Word Embeddings

Self-recoverable Adversarial Examples: A New Effective Protection Mechanism in Social Networks

1 code implementation26 Apr 2022 Jiawei Zhang, Jinwei Wang, Hao Wang, Xiangyang Luo

The destruction to DNNs brought by the adversarial attack sparks the potential that adversarial examples serve as a new protection mechanism for privacy security in social networks.

Adversarial Attack Adversarial Defense

Analyzing the Impact of Undersampling on the Benchmarking and Configuration of Evolutionary Algorithms

no code implementations20 Apr 2022 Diederick Vermetten, Hao Wang, Manuel López-Ibañez, Carola Doerr, Thomas Bäck

Particularly, we show that the number of runs used in many benchmarking studies, e. g., the default value of 15 suggested by the COCO environment, can be insufficient to reliably rank algorithms on well-known numerical optimization benchmarks.

Benchmarking Evolutionary Algorithms

Per-run Algorithm Selection with Warm-starting using Trajectory-based Features

no code implementations20 Apr 2022 Ana Kostovska, Anja Jankovic, Diederick Vermetten, Jacob de Nobel, Hao Wang, Tome Eftimov, Carola Doerr

In contrast to other recent work on online per-run algorithm selection, we warm-start the second optimizer using information accumulated during the first optimization phase.

Time Series Analysis

Preference Enhanced Social Influence Modeling for Network-Aware Cascade Prediction

no code implementations18 Apr 2022 Likang Wu, Hao Wang, Enhong Chen, Zhi Li, Hongke Zhao, Jianhui Ma

To that end, we propose a novel framework to promote cascade size prediction by enhancing the user preference modeling according to three stages, i. e., preference topics generation, preference shift modeling, and social influence activation.

Coverage and Capacity Optimization in STAR-RISs Assisted Networks: A Machine Learning Approach

no code implementations13 Apr 2022 Xinyu Gao, Wenqiang Yi, Alexandros Agapitos, Hao Wang, Yuanwei Liu

Coverage and capacity are the important metrics for performance evaluation in wireless networks, while the coverage and capacity have several conflicting relationships, e. g. high transmit power contributes to large coverage but high inter-cell interference reduces the capacity performance.

BIG-bench Machine Learning

Switching between Numerical Black-box Optimization Algorithms with Warm-starting Policies

no code implementations13 Apr 2022 Dominik Schröder, Diederick Vermetten, Hao Wang, Carola Doerr, Thomas Bäck

In this work, we build on the recent study of Vermetten et al. [GECCO 2020], who presented a data-driven approach to investigate promising switches between pairs of algorithms for numerical black-box optimization.

Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape

no code implementations9 Apr 2022 Xiangyu Zhu, Chang Yu, Di Huang, Zhen Lei, Hao Wang, Stan Z. Li

3D Morphable Model (3DMM) fitting has widely benefited face analysis due to its strong 3D priori.

Vocal Bursts Intensity Prediction

ESCM$^2$: Entire Space Counterfactual Multi-Task Model for Post-Click Conversion Rate Estimation

1 code implementation3 Apr 2022 Hao Wang, Tai-Wei Chang, Tianqiao Liu, Jianmin Huang, Zhichao Chen, Chao Yu, Ruopeng Li, Wei Chu

In this paper, we theoretically demonstrate that ESMM suffers from the following two problems: (1) Inherent Estimation Bias (IEB), where the estimated CVR of ESMM is inherently higher than the ground truth; (2) Potential Independence Priority (PIP) for CTCVR estimation, where there is a risk that the ESMM overlooks the causality from click to conversion.

counterfactual Recommendation Systems +1

OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks

1 code implementation CVPR 2022 WanYu Lin, Hao Lan, Hao Wang, Baochun Li

This paper proposes a new eXplanation framework, called OrphicX, for generating causal explanations for any graph neural networks (GNNs) based on learned latent causal factors.

Graph Learning

On Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization and Beyond

1 code implementation17 Mar 2022 Yuzhe Yang, Hao Wang, Dina Katabi

We first develop the domain-class transferability graph, and show that such transferability governs the success of learning in MDLT.

Domain Generalization

Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review

no code implementations7 Mar 2022 Abolfazl Razi, Xiwen Chen, Huayu Li, Hao Wang, Brendan Russo, Yan Chen, Hongbin Yu

This paper explores Deep Learning (DL) methods that are used or have the potential to be used for traffic video analysis, emphasizing driving safety for both Autonomous Vehicles (AVs) and human-operated vehicles.

Anomaly Detection Autonomous Vehicles +5

Domain Adaptation with Factorizable Joint Shift

no code implementations6 Mar 2022 Hao He, Yuzhe Yang, Hao Wang

In this paper, we propose a new assumption, Factorizable Joint Shift (FJS), to handle the co-existence of sampling bias in covariates and labels.

Unsupervised Domain Adaptation

Full RGB Just Noticeable Difference (JND) Modelling

no code implementations1 Mar 2022 Jian Jin, Dong Yu, Weisi Lin, Lili Meng, Hao Wang, Huaxiang Zhang

Besides, the JND of the red and blue channels are larger than that of the green one according to the experimental results of the proposed model, which demonstrates that more changes can be tolerated in the red and blue channels, in line with the well-known fact that the human visual system is more sensitive to the green channel in comparison with the red and blue ones.

Image Quality Assessment