Search Results for author: Qing Li

Found 118 papers, 37 papers with code

Exploring Non-Autoregressive Text Style Transfer

1 code implementation EMNLP 2021 Yun Ma, Qing Li

In this paper, we explore Non-AutoRegressive (NAR) decoding for unsupervised text style transfer.

Contrastive Learning Knowledge Distillation +3

Conditional Causal Relationships between Emotions and Causes in Texts

no code implementations EMNLP 2020 Xinhong Chen, Qing Li, JianPing Wang

The causal relationships between emotions and causes in text have recently received a lot of attention.

Task-oriented Domain-specific Meta-Embedding for Text Classification

no code implementations EMNLP 2020 Xin Wu, Yi Cai, Yang Kai, Tao Wang, Qing Li

Meta-embedding learning, which combines complementary information in different word embeddings, have shown superior performances across different Natural Language Processing tasks.

General Classification text-classification +2

Collaborative Learning of Bidirectional Decoders for Unsupervised Text Style Transfer

1 code implementation EMNLP 2021 Yun Ma, Yangbin Chen, Xudong Mao, Qing Li

In this paper, we propose a collaborative learning framework for unsupervised text style transfer using a pair of bidirectional decoders, one decoding from left to right while the other decoding from right to left.

Knowledge Distillation Style Transfer +2

Inferring Attracting Basins of Power System with Machine Learning

no code implementations20 May 2023 Yao Du, Qing Li, Huawei Fan, Meng Zhan, Jinghua Xiao, Xingang Wang

Power systems dominated by renewable energy encounter frequently large, random disturbances, and a critical challenge faced in power-system management is how to anticipate accurately whether the perturbed systems will return to the functional state after the transient or collapse.

SHS-Net: Learning Signed Hyper Surfaces for Oriented Normal Estimation of Point Clouds

1 code implementation CVPR 2023 Qing Li, Huifang Feng, Kanle Shi, Yue Gao, Yi Fang, Yu-Shen Liu, Zhizhong Han

In this work, we introduce signed hyper surfaces (SHS), which are parameterized by multi-layer perceptron (MLP) layers, to learn to estimate oriented normals from point clouds in an end-to-end manner.

Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy

no code implementations10 May 2023 Thanveer Shaik, Xiaohui Tao, Haoran Xie, Lin Li, Xiaofeng Zhu, Qing Li

Machine unlearning (MU) is gaining increasing attention due to the need to remove or modify predictions made by machine learning (ML) models.

Fairness Recommendation Systems

An Adversarial Non-Autoregressive Model for Text Generation with Incomplete Information

no code implementations6 May 2023 Da Ren, Qing Li

Non-autoregressive models have been widely studied in the Complete Information Scenario (CIS), in which the models have complete input information to obtain corresponding output.

Text Generation

MD-Manifold: A Medical-Distance-Based Representation Learning Approach for Medical Concept and Patient Representation

no code implementations30 Apr 2023 Shaodong Wang, Qing Li, Wenli Zhang

Representing medical concepts for healthcare analytical tasks requires incorporating medical domain knowledge and prior information from patient description data.

Data Augmentation Feature Engineering +1

Attention-based Spatial-Temporal Graph Convolutional Recurrent Networks for Traffic Forecasting

no code implementations25 Feb 2023 Haiyang Liu, Chunjiang Zhu, Detian Zhang, Qing Li

The key challenge is to effectively model complex spatial-temporal dependencies and correlations in modern traffic data.

Dynamic Graph Convolution Network with Spatio-Temporal Attention Fusion for Traffic Flow Prediction

no code implementations24 Feb 2023 Xunlian Luo, Chunjiang Zhu, Detian Zhang, Qing Li

However, existing approaches use independent components to model temporal and spatial dependencies and thus ignore the heterogeneous characteristics of traffic flow that vary with time and space.

Fairly Adaptive Negative Sampling for Recommendations

no code implementations16 Feb 2023 Xiao Chen, Wenqi Fan, Jingfan Chen, Haochen Liu, Zitao Liu, Zhaoxiang Zhang, Qing Li

Pairwise learning strategies are prevalent for optimizing recommendation models on implicit feedback data, which usually learns user preference by discriminating between positive (i. e., clicked by a user) and negative items (i. e., obtained by negative sampling).

Fairness

Generative Diffusion Models on Graphs: Methods and Applications

no code implementations6 Feb 2023 Chengyi Liu, Wenqi Fan, Yunqing Liu, Jiatong Li, Hang Li, Hui Liu, Jiliang Tang, Qing Li

Given the great success of diffusion models in image generation, increasing efforts have been made to leverage these techniques to advance graph generation in recent years.

Denoising Graph Generation +2

AttMEMO : Accelerating Transformers with Memoization on Big Memory Systems

no code implementations23 Jan 2023 Yuan Feng, Hyeran Jeon, Filip Blagojevic, Cyril Guyot, Qing Li, Dong Li

Transformer models gain popularity because of their superior inference accuracy and inference throughput.

Graph Learning and Its Applications: A Holistic Survey

no code implementations17 Dec 2022 Shaopeng Wei, Yu Zhao, Xingyan Chen, Qing Li, Fuzhen Zhuang, Ji Liu, Gang Kou

Different from previous surveys on graph learning, we provide a holistic review that analyzes current works from the perspective of graph structure, and discusses the latest applications, trends, and challenges in graph learning.

Graph Learning Representation Learning

Hierarchical Deep Reinforcement Learning for VWAP Strategy Optimization

no code implementations11 Dec 2022 XiaoDong Li, Pangjing Wu, Chenxin Zou, Qing Li

Designing an intelligent volume-weighted average price (VWAP) strategy is a critical concern for brokers, since traditional rule-based strategies are relatively static that cannot achieve a lower transaction cost in a dynamic market.

Hierarchical Reinforcement Learning reinforcement-learning +1

A Comprehensive Survey on Enterprise Financial Risk Analysis from Big Data Perspective

no code implementations28 Nov 2022 Yu Zhao, Huaming Du, Qing Li, Fuzhen Zhuang, Ji Liu, Gang Kou

In contrast, this paper attempts to provide a systematic literature survey of enterprise risk analysis approaches from Big Data perspective, which reviews more than 250 representative articles in the past almost 50 years (from 1968 to 2023).

Management

Joint Multimodal Entity-Relation Extraction Based on Edge-enhanced Graph Alignment Network and Word-pair Relation Tagging

1 code implementation28 Nov 2022 Li Yuan, Yi Cai, Jin Wang, Qing Li

This paper is the first to propose jointly performing MNER and MRE as a joint multimodal entity-relation extraction task (JMERE).

graph construction named-entity-recognition +3

ESIE-BERT: Enriching Sub-words Information Explicitly with BERT for Joint Intent Classification and SlotFilling

no code implementations27 Nov 2022 Yu Guo, Zhilong Xie, Xingyan Chen, Huangen Chen, Leilei Wang, Huaming Du, Shaopeng Wei, Yu Zhao, Qing Li, Gang Wu

We address the problem by introducing a novel joint method on top of BERT which explicitly models the multiple sub-tokens features after wordpiece tokenization, thereby contributing to the two tasks.

intent-classification Intent Classification +4

SQA3D: Situated Question Answering in 3D Scenes

1 code implementation14 Oct 2022 Xiaojian Ma, Silong Yong, Zilong Zheng, Qing Li, Yitao Liang, Song-Chun Zhu, Siyuan Huang

We propose a new task to benchmark scene understanding of embodied agents: Situated Question Answering in 3D Scenes (SQA3D).

Question Answering Referring Expression +1

HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces

1 code implementation13 Oct 2022 Qing Li, Yu-Shen Liu, Jin-San Cheng, Cheng Wang, Yi Fang, Zhizhong Han

To address these issues, we introduce hyper surface fitting to implicitly learn hyper surfaces, which are represented by multi-layer perceptron (MLP) layers that take point features as input and output surface patterns in a high dimensional feature space.

Surface Normals Estimation

Neural-Symbolic Recursive Machine for Systematic Generalization

no code implementations4 Oct 2022 Qing Li, Yixin Zhu, Yitao Liang, Ying Nian Wu, Song-Chun Zhu, Siyuan Huang

In experiments, NSR achieves state-of-the-art performance in three benchmarks from different domains: SCAN for semantic parsing, PCFG for string manipulation, and HINT for arithmetic reasoning.

Arithmetic Reasoning Semantic Parsing +1

Fairness Reprogramming

1 code implementation21 Sep 2022 Guanhua Zhang, Yihua Zhang, Yang Zhang, Wenqi Fan, Qing Li, Sijia Liu, Shiyu Chang

Specifically, FairReprogram considers the case where models can not be changed and appends to the input a set of perturbations, called the fairness trigger, which is tuned towards the fairness criteria under a min-max formulation.

Fairness

A Comprehensive Survey on Trustworthy Recommender Systems

no code implementations21 Sep 2022 Wenqi Fan, Xiangyu Zhao, Xiao Chen, Jingran Su, Jingtong Gao, Lin Wang, Qidong Liu, Yiqi Wang, Han Xu, Lei Chen, Qing Li

As one of the most successful AI-powered applications, recommender systems aim to help people make appropriate decisions in an effective and efficient way, by providing personalized suggestions in many aspects of our lives, especially for various human-oriented online services such as e-commerce platforms and social media sites.

Fairness Recommendation Systems

Disentangled Contrastive Learning for Social Recommendation

no code implementations18 Aug 2022 Jiahao Wu, Wenqi Fan, Jingfan Chen, Shengcai Liu, Qing Li, Ke Tang

In this work, to address such limitation, we propose a novel Disentangled contrastive learning framework for social Recommendations DcRec.

Contrastive Learning Representation Learning +1

InitialGAN: A Language GAN with Completely Random Initialization

no code implementations4 Aug 2022 Da Ren, Qing Li

Text generative models trained via Maximum Likelihood Estimation (MLE) suffer from the notorious exposure bias problem, and Generative Adversarial Networks (GANs) are shown to have potential to tackle this problem.

IPDAE: Improved Patch-Based Deep Autoencoder for Lossy Point Cloud Geometry Compression

1 code implementation4 Aug 2022 Kang You, Pan Gao, Qing Li

Point cloud is a crucial representation of 3D contents, which has been widely used in many areas such as virtual reality, mixed reality, autonomous driving, etc.

Autonomous Driving Mixed Reality

Knowledge-enhanced Black-box Attacks for Recommendations

no code implementations21 Jul 2022 Jingfan Chen, Wenqi Fan, Guanghui Zhu, Xiangyu Zhao, Chunfeng Yuan, Qing Li, Yihua Huang

Recent studies have shown that deep neural networks-based recommender systems are vulnerable to adversarial attacks, where attackers can inject carefully crafted fake user profiles (i. e., a set of items that fake users have interacted with) into a target recommender system to achieve malicious purposes, such as promote or demote a set of target items.

Recommendation Systems

Cycle Encoding of a StyleGAN Encoder for Improved Reconstruction and Editability

1 code implementation19 Jul 2022 Xudong Mao, Liujuan Cao, Aurele T. Gnanha, Zhenguo Yang, Qing Li, Rongrong Ji

The recently proposed pivotal tuning model makes significant progress towards reconstruction and editability, by using a two-step approach that first inverts the input image into a latent code, called pivot code, and then alters the generator so that the input image can be accurately mapped into the pivot code.

Pareto Optimization for Active Learning under Out-of-Distribution Data Scenarios

no code implementations4 Jul 2022 Xueying Zhan, Zeyu Dai, Qingzhong Wang, Qing Li, Haoyi Xiong, Dejing Dou, Antoni B. Chan

In this paper, we propose a sampling scheme, Monte-Carlo Pareto Optimization for Active Learning (POAL), which selects optimal subsets of unlabeled samples with fixed batch size from the unlabeled data pool.

Active Learning

Saliency Attack: Towards Imperceptible Black-box Adversarial Attack

1 code implementation4 Jun 2022 Zeyu Dai, Shengcai Liu, Ke Tang, Qing Li

In this paper, we propose to restrict the perturbations to a small salient region to generate adversarial examples that can hardly be perceived.

Adversarial Attack

Simultaneous Double Q-learning with Conservative Advantage Learning for Actor-Critic Methods

1 code implementation8 May 2022 Qing Li, Wengang Zhou, Zhenbo Lu, Houqiang Li

Actor-critic Reinforcement Learning (RL) algorithms have achieved impressive performance in continuous control tasks.

Continuous Control Q-Learning +1

Towards Sustainable Satellite Edge Computing

no code implementations10 Mar 2022 Qing Li, Shangguang Wang, Xiao Ma, Ao Zhou, Fangchun Yang

Recently, Low Earth Orbit (LEO) satellites experience rapid development and satellite edge computing emerges to address the limitation of bent-pipe architecture in existing satellite systems.

Edge-computing Scheduling

An End-to-End Cascaded Image Deraining and Object Detection Neural Network

no code implementations23 Feb 2022 Kaige Wang, Tianming Wang, Jianchuang Qu, Huatao Jiang, Qing Li, Lin Chang

Firstly, the gap between the low-level vision task represented by rain removal and the high-level vision task represented by object detection is significant, and the low-level vision task can hardly contribute to the high-level vision task.

object-detection Object Detection +1

Combining Intra-Risk and Contagion Risk for Enterprise Bankruptcy Prediction Using Graph Neural Networks

1 code implementation1 Feb 2022 Yu Zhao, Shaopeng Wei, Yu Guo, Qing Yang, Xingyan Chen, Qing Li, Fuzhen Zhuang, Ji Liu, Gang Kou

This study for the first time considers both types of risk and their joint effects in bankruptcy prediction.

Indicative Image Retrieval: Turning Blackbox Learning into Grey

no code implementations28 Jan 2022 Xulu Zhang, Zhenqun Yang, Hao Tian, Qing Li, XiaoYong Wei

In many applications, we need the matching evidence to be indicated rather than just have the ranked list (e. g., the locations of the target proteins/cells/lesions in medical images).

Image Retrieval Representation Learning +1

Conceptor Learning for Class Activation Mapping

no code implementations21 Jan 2022 Guangwu Qian, Zhen-Qun Yang, Xu-Lu Zhang, YaoWei Wang, Qing Li, Xiao-Yong Wei

Class Activation Mapping (CAM) has been widely adopted to generate saliency maps which provides visual explanations for deep neural networks (DNNs).

Stock Movement Prediction Based on Bi-typed Hybrid-relational Market Knowledge Graph via Dual Attention Networks

1 code implementation11 Jan 2022 Yu Zhao, Huaming Du, Ying Liu, Shaopeng Wei, Xingyan Chen, Fuzhen Zhuang, Qing Li, Ji Liu, Gang Kou

Stock Movement Prediction (SMP) aims at predicting listed companies' stock future price trend, which is a challenging task due to the volatile nature of financial markets.

Implicit Relations Stock Prediction

Learning Bi-typed Multi-relational Heterogeneous Graph via Dual Hierarchical Attention Networks

1 code implementation24 Dec 2021 Yu Zhao, Shaopeng Wei, Huaming Du, Xingyan Chen, Qing Li, Fuzhen Zhuang, Ji Liu, Gang Kou

To address this issue, we propose a novel Dual Hierarchical Attention Networks (DHAN) based on the bi-typed multi-relational heterogeneous graphs to learn comprehensive node representations with the intra-class and inter-class attention-based encoder under a hierarchical mechanism.

Graph Learning

Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text

no code implementations14 Dec 2021 Qing Li, Boqing Gong, Yin Cui, Dan Kondratyuk, Xianzhi Du, Ming-Hsuan Yang, Matthew Brown

The experiments show that the resultant unified foundation transformer works surprisingly well on both the vision-only and text-only tasks, and the proposed knowledge distillation and gradient masking strategy can effectively lift the performance to approach the level of separately-trained models.

Image Classification Knowledge Distillation +1

Self-Ensemling for 3D Point Cloud Domain Adaption

no code implementations10 Dec 2021 Qing Li, Xiaojiang Peng, Chuan Yan, Pan Gao, Qi Hao

In SEN, a student network is kept in a collaborative manner with supervised learning and self-supervised learning, and a teacher network conducts temporal consistency to learn useful representations and ensure the quality of point clouds reconstruction.

Autonomous Driving Self-Supervised Learning +1

Deep Keyphrase Completion

no code implementations29 Oct 2021 Yu Zhao, Jia Song, Huali Feng, Fuzhen Zhuang, Qing Li, Xiaojie Wang, Ji Liu

Keyphrase provides accurate information of document content that is highly compact, concise, full of meanings, and widely used for discourse comprehension, organization, and text retrieval.

Keyphrase Extraction Keyphrase Generation +2

Towards General Deep Leakage in Federated Learning

no code implementations18 Oct 2021 Jiahui Geng, Yongli Mou, Feifei Li, Qing Li, Oya Beyan, Stefan Decker, Chunming Rong

We find that image restoration fails even if there is only one incorrectly inferred label in the batch; we also find that when batch images have the same label, the corresponding image is restored as a fusion of that class of images.

Federated Learning Image Restoration

Benchmark Problems for CEC2021 Competition on Evolutionary Transfer Multiobjectve Optimization

1 code implementation15 Oct 2021 Songbai Liu, Qiuzhen Lin, Kay Chen Tan, Qing Li

Evolutionary transfer multiobjective optimization (ETMO) has been becoming a hot research topic in the field of evolutionary computation, which is based on the fact that knowledge learning and transfer across the related optimization exercises can improve the efficiency of others.

Multiobjective Optimization Transfer Learning

SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing

2 code implementations ACL 2022 Junyi Ao, Rui Wang, Long Zhou, Chengyi Wang, Shuo Ren, Yu Wu, Shujie Liu, Tom Ko, Qing Li, Yu Zhang, Zhihua Wei, Yao Qian, Jinyu Li, Furu Wei

Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +7

Multi-View Self-Attention Based Transformer for Speaker Recognition

no code implementations11 Oct 2021 Rui Wang, Junyi Ao, Long Zhou, Shujie Liu, Zhihua Wei, Tom Ko, Qing Li, Yu Zhang

In this work, we propose a novel multi-view self-attention mechanism and present an empirical study of different Transformer variants with or without the proposed attention mechanism for speaker recognition.

Speaker Recognition

Stabilized Self-training with Negative Sampling on Few-labeled Graph Data

no code implementations29 Sep 2021 Ziang Zhou, Jieming Shi, Shengzhong Zhang, Zengfeng Huang, Qing Li

Therefore, we propose an effective framework, Stabilized self-training with Negative sampling (SN), which is applicable to existing GNNs to stabilize the training process and enhance the training data, and consequently, boost classification accuracy on graphs with few labeled data.

Benchmarking Node Classification

Imperceptible Black-box Attack via Refining in Salient Region

no code implementations29 Sep 2021 Zeyu Dai, Shengcai Liu, Ke Tang, Qing Li

To address this issue, in this paper we propose to use segmentation priors for black-box attacks such that the perturbations are limited in the salient region.

DM-CT: Consistency Training with Data and Model Perturbation

no code implementations29 Sep 2021 Xiaobo Liang, Runze Mao, Lijun Wu, Juntao Li, Weiqing Liu, Qing Li, Min Zhang

The common approach of consistency training is performed on the data-level, which typically utilizes the data augmentation strategy (or adversarial training) to make the predictions from the augmented input and the original input to be consistent, so that the model is more robust and attains better generalization ability.

Data Augmentation Image Classification +2

YouRefIt: Embodied Reference Understanding with Language and Gesture

no code implementations ICCV 2021 Yixin Chen, Qing Li, Deqian Kong, Yik Lun Kei, Song-Chun Zhu, Tao Gao, Yixin Zhu, Siyuan Huang

To the best of our knowledge, this is the first embodied reference dataset that allows us to study referring expressions in daily physical scenes to understand referential behavior, human communication, and human-robot interaction.

Graph Trend Filtering Networks for Recommendations

1 code implementation12 Aug 2021 Wenqi Fan, Xiaorui Liu, Wei Jin, Xiangyu Zhao, Jiliang Tang, Qing Li

The key of recommender systems is to predict how likely users will interact with items based on their historical online behaviors, e. g., clicks, add-to-cart, purchases, etc.

Collaborative Filtering Graph Representation Learning +1

DGEM: A New Dual-modal Graph Embedding Method in Recommendation System

no code implementations9 Aug 2021 Huimin Zhou, Qing Li, Yong Jiang, Rongwei Yang, Zhuyun Qi

In the current deep learning based recommendation system, the embedding method is generally employed to complete the conversion from the high-dimensional sparse feature vector to the low-dimensional dense feature vector.

Graph Embedding

Jointly Attacking Graph Neural Network and its Explanations

no code implementations7 Aug 2021 Wenqi Fan, Wei Jin, Xiaorui Liu, Han Xu, Xianfeng Tang, Suhang Wang, Qing Li, Jiliang Tang, JianPing Wang, Charu Aggarwal

Despite the great success, recent studies have shown that GNNs are highly vulnerable to adversarial attacks, where adversaries can mislead the GNNs' prediction by modifying graphs.

Adversarial Learning with Mask Reconstruction for Text-Guided Image Inpainting

1 code implementation Conference 2021 Xingcai Wu, Yucheng Xie, Jiaqi Zeng, Zhenguo Yang, Yi Yu, Qing Li, and Wenyin Liu

In this paper, we propose an adversarial learning framework with mask reconstruction (ALMR) for image inpainting with textual guidance, which consists of a two-stage generator and dual discriminators.

Image Inpainting

Multiple-criteria Based Active Learning with Fixed-size Determinantal Point Processes

no code implementations4 Jul 2021 Xueying Zhan, Qing Li, Antoni B. Chan

In this paper, we introduce a multiple-criteria based active learning algorithm, which incorporates three complementary criteria, i. e., informativeness, representativeness and diversity, to make appropriate selections in the active learning rounds under different data types.

Active Learning Informativeness +1

Intent Disentanglement and Feature Self-supervision for Novel Recommendation

no code implementations28 Jun 2021 Tieyun Qian, Yile Liang, Qing Li, Xuan Ma, Ke Sun, Zhiyong Peng

Improving the recommendation of tail items can promote novelty and bring positive effects to both users and providers, and thus is a desirable property of recommender systems.

Disentanglement Recommendation Systems +1

Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering

no code implementations8 Mar 2021 Qing Li, Xiaojiang Peng, Yu Qiao, Qi Hao

The multi-label learning module leverages a memory feature bank and assigns each image with a multi-label vector based on the similarities between the image and feature bank.

Multi-Label Learning Pseudo Label +1

A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics

no code implementations2 Mar 2021 Qing Li, Siyuan Huang, Yining Hong, Yixin Zhu, Ying Nian Wu, Song-Chun Zhu

We believe the HINT dataset and the experimental findings are of great interest to the learning community on systematic generalization.

Few-Shot Learning Program Synthesis +1

Tips and Tricks for Webly-Supervised Fine-Grained Recognition: Learning from the WebFG 2020 Challenge

no code implementations29 Dec 2020 Xiu-Shen Wei, Yu-Yan Xu, Yazhou Yao, Jia Wei, Si Xi, Wenyuan Xu, Weidong Zhang, Xiaoxin Lv, Dengpan Fu, Qing Li, Baoying Chen, Haojie Guo, Taolue Xue, Haipeng Jing, Zhiheng Wang, Tianming Zhang, Mingwen Zhang

WebFG 2020 is an international challenge hosted by Nanjing University of Science and Technology, University of Edinburgh, Nanjing University, The University of Adelaide, Waseda University, etc.

SMART: A Situation Model for Algebra Story Problems via Attributed Grammar

no code implementations27 Dec 2020 Yining Hong, Qing Li, Ran Gong, Daniel Ciao, Siyuan Huang, Song-Chun Zhu

Solving algebra story problems remains a challenging task in artificial intelligence, which requires a detailed understanding of real-world situations and a strong mathematical reasoning capability.

Mathematical Reasoning

Learning by Fixing: Solving Math Word Problems with Weak Supervision

1 code implementation19 Dec 2020 Yining Hong, Qing Li, Daniel Ciao, Siyuan Huang, Song-Chun Zhu

To generate more diverse solutions, \textit{tree regularization} is applied to guide the efficient shrinkage and exploration of the solution space, and a \textit{memory buffer} is designed to track and save the discovered various fixes for each problem.

 Ranked #1 on Math Word Problem Solving on Math23K (weakly-supervised metric)

Weakly-supervised Learning

Multi Scale Temporal Graph Networks For Skeleton-based Action Recognition

no code implementations5 Dec 2020 Tingwei Li, Ruiwen Zhang, Qing Li

To appropriately describe the relations between joints in the skeleton graph, we propose a multi-scale graph strategy, adopting a full-scale graph, part-scale graph, and core-scale graph to capture the local features of each joint and the contour features of important joints.

Action Recognition Skeleton Based Action Recognition

A Unified Sequence Labeling Model for Emotion Cause Pair Extraction

no code implementations COLING 2020 Xinhong Chen, Qing Li, JianPing Wang

Existing approaches address the task by first extracting emotion and cause clauses via two binary classifiers separately, and then training another binary classifier to pair them up.

Emotion-Cause Pair Extraction

Deep Learning based Monocular Depth Prediction: Datasets, Methods and Applications

no code implementations9 Nov 2020 Qing Li, Jiasong Zhu, Jun Liu, Rui Cao, Qingquan Li, Sen Jia, Guoping Qiu

Despite the rapid progress in this topic, there are lacking of a comprehensive review, which is needed to summarize the current progress and provide the future directions.

Depth Prediction Indoor Localization +2

Suppressing Mislabeled Data via Grouping and Self-Attention

1 code implementation ECCV 2020 Xiaojiang Peng, Kai Wang, Zhaoyang Zeng, Qing Li, Jianfei Yang, Yu Qiao

Specifically, this plug-and-play AFM first leverages a \textit{group-to-attend} module to construct groups and assign attention weights for group-wise samples, and then uses a \textit{mixup} module with the attention weights to interpolate massive noisy-suppressed samples.

Image Classification

MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization

no code implementations29 Sep 2020 Yangbin Chen, Yun Ma, Tom Ko, Jian-Ping Wang, Qing Li

MetaMix can be integrated with any of the MAML-based algorithms and learn the decision boundaries generalizing better to new tasks.

Few-Shot Learning Transfer Learning

Object-aware Multimodal Named Entity Recognition in Social Media Posts with Adversarial Learning

1 code implementation3 Aug 2020 Changmeng Zheng, Zhiwei Wu, Tao Wang, Cai Yi, Qing Li

To better exploit visual and textual information in NER, we propose an adversarial gated bilinear attention neural network (AGBAN).

named-entity-recognition Named Entity Recognition +1

Physical properties revealed by transport measurements on superconducting Nd$_{0.8}$Sr$_{0.2}$NiO$_{2}$ thin films

no code implementations9 Jul 2020 Ying Xiang, Qing Li, Yueying Li, Huan Yang, Yuefeng Nie, Hai-Hu Wen

The angle dependent resistivity at a fixed temperature and different magnetic fields cannot be scaled to one curve, which deviates from the prediction of the anisotropic Ginzburg-Landau theory.

Superconductivity Materials Science Strongly Correlated Electrons

Neural Mixed Counting Models for Dispersed Topic Discovery

no code implementations ACL 2020 Jiemin Wu, Yanghui Rao, Zusheng Zhang, Haoran Xie, Qing Li, Fu Lee Wang, Ziye Chen

Mixed counting models that use the negative binomial distribution as the prior can well model over-dispersed and hierarchically dependent random variables; thus they have attracted much attention in mining dispersed document topics.

Variational Inference

MiniNet: An extremely lightweight convolutional neural network for real-time unsupervised monocular depth estimation

no code implementations27 Jun 2020 Jun Liu, Qing Li, Rui Cao, Wenming Tang, Guoping Qiu

To the best of our knowledge, this work is the first extremely lightweight neural network trained on monocular video sequences for real-time unsupervised monocular depth estimation, which opens up the possibility of implementing deep learning-based real-time unsupervised monocular depth prediction on low-cost embedded devices.

Depth Prediction Monocular Depth Estimation +1

PoseGAN: A Pose-to-Image Translation Framework for Camera Localization

no code implementations23 Jun 2020 Kanglin Liu, Qing Li, Guoping Qiu

We present PoseGANs, a conditional generative adversarial networks (cGANs) based framework for the implementation of pose-to-image translation.

Camera Localization Pose Estimation +1

Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning

1 code implementation ICML 2020 Qing Li, Siyuan Huang, Yining Hong, Yixin Chen, Ying Nian Wu, Song-Chun Zhu

In this paper, we address these issues and close the loop of neural-symbolic learning by (1) introducing the \textbf{grammar} model as a \textit{symbolic prior} to bridge neural perception and symbolic reasoning, and (2) proposing a novel \textbf{back-search} algorithm which mimics the top-down human-like learning procedure to propagate the error through the symbolic reasoning module efficiently.

Question Answering Reinforcement Learning (RL) +1

Attacking Black-box Recommendations via Copying Cross-domain User Profiles

no code implementations17 May 2020 Wenqi Fan, Tyler Derr, Xiangyu Zhao, Yao Ma, Hui Liu, Jian-Ping Wang, Jiliang Tang, Qing Li

In this work, we present our framework CopyAttack, which is a reinforcement learning based black-box attack method that harnesses real users from a source domain by copying their profiles into the target domain with the goal of promoting a subset of items.

Data Poisoning Recommendation Systems

Incorporating Effective Global Information via Adaptive Gate Attention for Text Classification

no code implementations22 Feb 2020 Xianming Li, Zongxi Li, Yingbin Zhao, Haoran Xie, Qing Li

The dominant text classification studies focus on training classifiers using textual instances only or introducing external knowledge (e. g., hand-craft features and domain expert knowledge).

General Classification text-classification +1

Solving Cold Start Problem in Recommendation with Attribute Graph Neural Networks

no code implementations28 Dec 2019 Tieyun Qian, Yile Liang, Qing Li

More importantly, for a cold start user/item that does not have any interactions, such methods are unable to learn the preference embedding of the user/item since there is no link to this user/item in the graph.

Matrix Completion Recommendation Systems

Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling

no code implementations23 Dec 2019 Wenkai Han, Chenglu Wen, Cheng Wang, Xin Li, Qing Li

Point2Node can dynamically explore correlation among all graph nodes from different levels, and adaptively aggregate the learned features.

Effective Stabilized Self-Training on Few-Labeled Graph Data

1 code implementation7 Oct 2019 Ziang Zhou, Jieming Shi, Shengzhong Zhang, Zengfeng Huang, Qing Li

However, under extreme cases when very few labels are available (e. g., 1 labeled node per class), GNNs suffer from severe performance degradation.

Benchmarking Model Selection +1

Learning Category Correlations for Multi-label Image Recognition with Graph Networks

no code implementations28 Sep 2019 Qing Li, Xiaojiang Peng, Yu Qiao, Qiang Peng

In this paper, instead of using a pre-defined graph which is inflexible and may be sub-optimal for multi-label classification, we propose the A-GCN, which leverages the popular Graph Convolutional Networks with an Adaptive label correlation graph to model label dependencies.

Multi-Label Classification Word Embeddings

Product Image Recognition with Guidance Learning and Noisy Supervision

no code implementations26 Jul 2019 Qing Li, Xiaojiang Peng, Liangliang Cao, Wenbin Du, Hao Xing, Yu Qiao

Instead of collecting product images by labor-and time-intensive image capturing, we take advantage of the web and download images from the reviews of several e-commerce websites where the images are casually captured by consumers.

Deep Social Collaborative Filtering

no code implementations16 Jul 2019 Wenqi Fan, Yao Ma, Dawei Yin, Jian-Ping Wang, Jiliang Tang, Qing Li

Meanwhile, most of these models treat neighbors' information equally without considering the specific recommendations.

Collaborative Filtering Recommendation Systems

Deep Adversarial Social Recommendation

1 code implementation30 May 2019 Wenqi Fan, Tyler Derr, Yao Ma, JianPing Wang, Jiliang Tang, Qing Li

Recent years have witnessed rapid developments on social recommendation techniques for improving the performance of recommender systems due to the growing influence of social networks to our daily life.

Recommendation Systems Representation Learning

Virtual Mixup Training for Unsupervised Domain Adaptation

4 code implementations10 May 2019 Xudong Mao, Yun Ma, Zhenguo Yang, Yangbin Chen, Qing Li

Existing methods only impose the locally-Lipschitz constraint around the training points while miss the other areas, such as the points in-between training data.

Unsupervised Domain Adaptation

MMED: A Multi-domain and Multi-modality Event Dataset

1 code implementation4 Apr 2019 Zhenguo Yang, Zehang Lin, Min Cheng, Qing Li, Wenyin Liu

In this work, we construct and release a multi-domain and multi-modality event dataset (MMED), containing 25, 165 textual news articles collected from hundreds of news media sites (e. g., Yahoo News, Google News, CNN News.)

Question Answering Retrieval +1

pyLLE: a Fast and User Friendly Lugiato-Lefever Equation Solver

1 code implementation22 Mar 2019 Gregory Moille, Qing Li, Xiyuan Lu, Kartik Srinivasan

We present the development of pyLLE, a freely accessible and cross-platform Lugiato-Lefever equation solver programmed in Python and Julia and optimized for the simulation of microresonator frequency combs.

Mathematical Software Optics

Graph Neural Networks for Social Recommendation

7 code implementations19 Feb 2019 Wenqi Fan, Yao Ma, Qing Li, Yuan He, Eric Zhao, Jiliang Tang, Dawei Yin

These advantages of GNNs provide great potential to advance social recommendation since data in social recommender systems can be represented as user-user social graph and user-item graph; and learning latent factors of users and items is the key.

Ranked #3 on Recommendation Systems on Epinions (using extra training data)

Recommendation Systems

Enhancing Remote Sensing Image Retrieval with Triplet Deep Metric Learning Network

no code implementations15 Feb 2019 Rui Cao, Qian Zhang, Jiasong Zhu, Qing Li, Qingquan Li, Bozhi Liu, Guoping Qiu

With the rapid growing of remotely sensed imagery data, there is a high demand for effective and efficient image retrieval tools to manage and exploit such data.

Image Retrieval Metric Learning +1

Learning Shared Semantic Space with Correlation Alignment for Cross-modal Event Retrieval

1 code implementation14 Jan 2019 Zhenguo Yang, Zehang Lin, Peipei Kang, Jianming Lv, Qing Li, Wenyin Liu

In this paper, we propose to learn shared semantic space with correlation alignment (${S}^{3}CA$) for multimodal data representations, which aligns nonlinear correlations of multimodal data distributions in deep neural networks designed for heterogeneous data.

Retrieval

Single Bitmap Block Truncation Coding of Color Images Using Hill Climbing Algorithm

no code implementations13 Jul 2018 Lige Zhang, Xiaolin Qin, Qing Li, Haoyue Peng, Yu Hou

Compared with various schemes, the simulation results of the proposed scheme are better than that of the reference schemes in visual quality and time consumption.

Unpaired Multi-Domain Image Generation via Regularized Conditional GANs

1 code implementation7 May 2018 Xudong Mao, Qing Li

To tackle this problem, we propose Regularized Conditional GAN (RegCGAN) which is capable of learning to generate corresponding images in the absence of paired training data.

Image Generation Unsupervised Domain Adaptation

VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions

no code implementations ECCV 2018 Qing Li, Qingyi Tao, Shafiq Joty, Jianfei Cai, Jiebo Luo

Most existing works in visual question answering (VQA) are dedicated to improving the accuracy of predicted answers, while disregarding the explanations.

Multi-Task Learning Question Answering +1

Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatial-Temporal Patterns

1 code implementation CVPR 2018 Jianming Lv, Weihang Chen, Qing Li, Can Yang

Most of the proposed person re-identification algorithms conduct supervised training and testing on single labeled datasets with small size, so directly deploying these trained models to a large-scale real-world camera network may lead to poor performance due to underfitting.

Incremental Learning Learning-To-Rank +2

VizWiz Grand Challenge: Answering Visual Questions from Blind People

no code implementations CVPR 2018 Danna Gurari, Qing Li, Abigale J. Stangl, Anhong Guo, Chi Lin, Kristen Grauman, Jiebo Luo, Jeffrey P. Bigham

The study of algorithms to automatically answer visual questions currently is motivated by visual question answering (VQA) datasets constructed in artificial VQA settings.

Question Answering Visual Question Answering

Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions

no code implementations EMNLP 2018 Qing Li, Jianlong Fu, Dongfei Yu, Tao Mei, Jiebo Luo

Most existing approaches adopt the pipeline of representing an image via pre-trained CNNs, and then using the uninterpretable CNN features in conjunction with the question to predict the answer.

Image Captioning Question Answering +1

On the Effectiveness of Least Squares Generative Adversarial Networks

2 code implementations18 Dec 2017 Xudong Mao, Qing Li, Haoran Xie, Raymond Y. K. Lau, Zhen Wang, Stephen Paul Smolley

To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss for both the discriminator and the generator.

AlignGAN: Learning to Align Cross-Domain Images with Conditional Generative Adversarial Networks

no code implementations5 Jul 2017 Xudong Mao, Qing Li, Haoran Xie

Recently, several methods based on generative adversarial network (GAN) have been proposed for the task of aligning cross-domain images or learning a joint distribution of cross-domain images.

A Network Framework for Noisy Label Aggregation in Social Media

no code implementations ACL 2017 Xueying Zhan, Yao-Wei Wang, Yanghui Rao, Haoran Xie, Qing Li, Fu Lee Wang, Tak-Lam Wong

This paper focuses on the task of noisy label aggregation in social media, where users with different social or culture backgrounds may annotate invalid or malicious tags for documents.

Cultural Vocal Bursts Intensity Prediction Image Classification +2

Multiple VLAD encoding of CNNs for image classification

no code implementations30 Jun 2017 Qing Li, Qiang Peng, Chuan Yan

In this paper, we propose a special framework, which is the multiple VLAD encoding method with the CNNs features for image classification.

Classification General Classification +1

T-CONV: A Convolutional Neural Network For Multi-scale Taxi Trajectory Prediction

no code implementations23 Nov 2016 Jianming Lv, Qing Li, Xintong Wang

Precise destination prediction of taxi trajectories can benefit many intelligent location based services such as accurate ad for passengers.

Trajectory Prediction

Least Squares Generative Adversarial Networks

23 code implementations ICCV 2017 Xudong Mao, Qing Li, Haoran Xie, Raymond Y. K. Lau, Zhen Wang, Stephen Paul Smolley

To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss function for the discriminator.

HCRS: A hybrid clothes recommender system based on user ratings and product features

no code implementations25 Nov 2014 Xiaosong Hu, Wen Zhu, Qing Li

Nowadays, online clothes-selling business has become popular and extremely attractive because of its convenience and cheap-and-fine price.

Recommendation Systems

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