Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Wei Hu

Wei Hu

State Key Laboratory for Novel Software Technology, Nanjing University

Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning


Jul 05, 2021
Bi'an Du, Xiang Gao, Wei Hu, Xin Li

* Accepted to ACM MM 2021 
  Access Paper or Ask Questions

A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning


Jun 29, 2021
Nikunj Saunshi, Arushi Gupta, Wei Hu

Figure 1 for A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning
Figure 2 for A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning
Figure 3 for A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning
Figure 4 for A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning
* In proceedings of ICML 2021 
  Access Paper or Ask Questions

Near-Optimal Linear Regression under Distribution Shift


Jun 23, 2021
Qi Lei, Wei Hu, Jason D. Lee

Figure 1 for Near-Optimal Linear Regression under Distribution Shift
Figure 2 for Near-Optimal Linear Regression under Distribution Shift
Figure 3 for Near-Optimal Linear Regression under Distribution Shift
Figure 4 for Near-Optimal Linear Regression under Distribution Shift
* ICML 2021 
  Access Paper or Ask Questions

Knowing the No-match: Entity Alignment with Dangling Cases


Jun 04, 2021
Zequn Sun, Muhao Chen, Wei Hu

Figure 1 for Knowing the No-match: Entity Alignment with Dangling Cases
Figure 2 for Knowing the No-match: Entity Alignment with Dangling Cases
Figure 3 for Knowing the No-match: Entity Alignment with Dangling Cases
Figure 4 for Knowing the No-match: Entity Alignment with Dangling Cases
* ACL 2021 
  Access Paper or Ask Questions

Self-Supervised Graph Representation Learning via Topology Transformations


May 25, 2021
Xiang Gao, Wei Hu, Guo-Jun Qi

Figure 1 for Self-Supervised Graph Representation Learning via Topology Transformations
Figure 2 for Self-Supervised Graph Representation Learning via Topology Transformations
Figure 3 for Self-Supervised Graph Representation Learning via Topology Transformations
Figure 4 for Self-Supervised Graph Representation Learning via Topology Transformations

  Access Paper or Ask Questions

Generic Reversible Visible Watermarking Via Regularized Graph Fourier Transform Coding


May 18, 2021
Wenfa Qi, Wei Hu, Sirui Guo, Zongming Guo, Xiang Wang

Figure 1 for Generic Reversible Visible Watermarking Via Regularized Graph Fourier Transform Coding
Figure 2 for Generic Reversible Visible Watermarking Via Regularized Graph Fourier Transform Coding
Figure 3 for Generic Reversible Visible Watermarking Via Regularized Graph Fourier Transform Coding
Figure 4 for Generic Reversible Visible Watermarking Via Regularized Graph Fourier Transform Coding
* This manuscript is submitted to IEEE Transactions on Image Processing on May 17th 2021. It has 13 pages, 10 figures and 3 tables 
  Access Paper or Ask Questions

Learning Fine-grained Fact-Article Correspondence in Legal Cases


Apr 24, 2021
Jidong Ge, Yunyun huang, Xiaoyu Shen, Chuanyi Li, Wei Hu, Bin Luo

Figure 1 for Learning Fine-grained Fact-Article Correspondence in Legal Cases
Figure 2 for Learning Fine-grained Fact-Article Correspondence in Legal Cases
Figure 3 for Learning Fine-grained Fact-Article Correspondence in Legal Cases
Figure 4 for Learning Fine-grained Fact-Article Correspondence in Legal Cases
* Code and dataset are available at https://github.com/gjdnju/MLMN 
  Access Paper or Ask Questions

Diffusion Probabilistic Models for 3D Point Cloud Generation


Mar 02, 2021
Shitong Luo, Wei Hu

Figure 1 for Diffusion Probabilistic Models for 3D Point Cloud Generation
Figure 2 for Diffusion Probabilistic Models for 3D Point Cloud Generation
Figure 3 for Diffusion Probabilistic Models for 3D Point Cloud Generation
Figure 4 for Diffusion Probabilistic Models for 3D Point Cloud Generation
* Accepted to CVPR 2021 
  Access Paper or Ask Questions

Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations


Mar 01, 2021
Xiang Gao, Wei Hu, Guo-Jun Qi

Figure 1 for Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations
Figure 2 for Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations
Figure 3 for Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations
Figure 4 for Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations

  Access Paper or Ask Questions

Adaptive Graph Representation Learning and Reasoning for Face Parsing


Jan 18, 2021
Gusi Te, Wei Hu, Yinglu Liu, Hailin Shi, Tao Mei

Figure 1 for Adaptive Graph Representation Learning and Reasoning for Face Parsing
Figure 2 for Adaptive Graph Representation Learning and Reasoning for Face Parsing
Figure 3 for Adaptive Graph Representation Learning and Reasoning for Face Parsing
Figure 4 for Adaptive Graph Representation Learning and Reasoning for Face Parsing

  Access Paper or Ask Questions

AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries


Nov 23, 2020
Qianjiang Hu, Xiao Wang, Wei Hu, Guo-Jun Qi

Figure 1 for AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries
Figure 2 for AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries
Figure 3 for AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries
Figure 4 for AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries
* A better result with 200 epochs of network pretraining has been updated in the new submission 
  Access Paper or Ask Questions

Decentralized Knowledge Graph Representation Learning


Oct 16, 2020
Lingbing Guo, Weiqing Wang, Zequn Sun, Chenghao Liu, Wei Hu

Figure 1 for Decentralized Knowledge Graph Representation Learning
Figure 2 for Decentralized Knowledge Graph Representation Learning
Figure 3 for Decentralized Knowledge Graph Representation Learning
Figure 4 for Decentralized Knowledge Graph Representation Learning
* submitted to ICLR 2021 
  Access Paper or Ask Questions

Provable Benefits of Representation Learning in Linear Bandits


Oct 13, 2020
Jiaqi Yang, Wei Hu, Jason D. Lee, Simon S. Du

Figure 1 for Provable Benefits of Representation Learning in Linear Bandits
Figure 2 for Provable Benefits of Representation Learning in Linear Bandits
Figure 3 for Provable Benefits of Representation Learning in Linear Bandits
Figure 4 for Provable Benefits of Representation Learning in Linear Bandits
* 28 pages, 6 figures 
  Access Paper or Ask Questions

Knowledge Association with Hyperbolic Knowledge Graph Embeddings


Oct 05, 2020
Zequn Sun, Muhao Chen, Wei Hu, Chengming Wang, Jian Dai, Wei Zhang

Figure 1 for Knowledge Association with Hyperbolic Knowledge Graph Embeddings
Figure 2 for Knowledge Association with Hyperbolic Knowledge Graph Embeddings
Figure 3 for Knowledge Association with Hyperbolic Knowledge Graph Embeddings
Figure 4 for Knowledge Association with Hyperbolic Knowledge Graph Embeddings
* EMNLP 2020 
  Access Paper or Ask Questions

Global-to-Local Neural Networks for Document-Level Relation Extraction


Sep 22, 2020
Difeng Wang, Wei Hu, Ermei Cao, Weijian Sun

Figure 1 for Global-to-Local Neural Networks for Document-Level Relation Extraction
Figure 2 for Global-to-Local Neural Networks for Document-Level Relation Extraction
Figure 3 for Global-to-Local Neural Networks for Document-Level Relation Extraction
Figure 4 for Global-to-Local Neural Networks for Document-Level Relation Extraction
* Accepted in the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020) 
  Access Paper or Ask Questions

P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions


Sep 15, 2020
Wei Hu, QiHao Zhao, Yangyu Huang, Fan Zhang

Figure 1 for P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions
Figure 2 for P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions
Figure 3 for P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions
Figure 4 for P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions
* ICPR 2020. Codes are available at https://github.com/fistyee/P-DIFF 
  Access Paper or Ask Questions

Rule-Guided Graph Neural Networks for Recommender Systems


Sep 09, 2020
Xinze Lyu, Guangyao Li, Jiacheng Huang, Wei Hu

Figure 1 for Rule-Guided Graph Neural Networks for Recommender Systems
Figure 2 for Rule-Guided Graph Neural Networks for Recommender Systems
Figure 3 for Rule-Guided Graph Neural Networks for Recommender Systems
Figure 4 for Rule-Guided Graph Neural Networks for Recommender Systems
* Accepted in the 19th International Semantic Web Conference (ISWC 2020) 
  Access Paper or Ask Questions

Differentiable Manifold Reconstruction for Point Cloud Denoising


Aug 09, 2020
Shitong Luo, Wei Hu

Figure 1 for Differentiable Manifold Reconstruction for Point Cloud Denoising
Figure 2 for Differentiable Manifold Reconstruction for Point Cloud Denoising
Figure 3 for Differentiable Manifold Reconstruction for Point Cloud Denoising
Figure 4 for Differentiable Manifold Reconstruction for Point Cloud Denoising
* This work has been accepted to ACM MM 2020 
  Access Paper or Ask Questions

Graph Signal Processing for Geometric Data and Beyond: Theory and Applications


Aug 05, 2020
Wei Hu, Jiahao Pang, Xianming Liu, Dong Tian, Chia-Wen Lin, Anthony Vetro

Figure 1 for Graph Signal Processing for Geometric Data and Beyond: Theory and Applications
Figure 2 for Graph Signal Processing for Geometric Data and Beyond: Theory and Applications
Figure 3 for Graph Signal Processing for Geometric Data and Beyond: Theory and Applications
Figure 4 for Graph Signal Processing for Geometric Data and Beyond: Theory and Applications
* 16 pages, 6 figures 
  Access Paper or Ask Questions

Edge-aware Graph Representation Learning and Reasoning for Face Parsing


Jul 22, 2020
Gusi Te, Yinglu Liu, Wei Hu, Hailin Shi, Tao Mei

Figure 1 for Edge-aware Graph Representation Learning and Reasoning for Face Parsing
Figure 2 for Edge-aware Graph Representation Learning and Reasoning for Face Parsing
Figure 3 for Edge-aware Graph Representation Learning and Reasoning for Face Parsing
Figure 4 for Edge-aware Graph Representation Learning and Reasoning for Face Parsing
* ECCV 2020 
  Access Paper or Ask Questions

Signed Graph Metric Learning via Gershgorin Disc Alignment


Jul 06, 2020
Cheng Yang, Gene Cheung, Wei Hu

Figure 1 for Signed Graph Metric Learning via Gershgorin Disc Alignment
Figure 2 for Signed Graph Metric Learning via Gershgorin Disc Alignment
Figure 3 for Signed Graph Metric Learning via Gershgorin Disc Alignment
Figure 4 for Signed Graph Metric Learning via Gershgorin Disc Alignment
* code available: https://github.com/bobchengyang/SGML 
  Access Paper or Ask Questions

The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks


Jun 25, 2020
Wei Hu, Lechao Xiao, Ben Adlam, Jeffrey Pennington

Figure 1 for The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks
Figure 2 for The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks
Figure 3 for The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks
Figure 4 for The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks

  Access Paper or Ask Questions

When is Particle Filtering Efficient for POMDP Sequential Planning?


Jun 10, 2020
Simon S. Du, Wei Hu, Zhiyuan Li, Ruoqi Shen, Zhao Song, Jiajun Wu

Figure 1 for When is Particle Filtering Efficient for POMDP Sequential Planning?

  Access Paper or Ask Questions

TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs


Apr 22, 2020
Zequn Sun, Jiacheng Huang, Wei Hu, Muchao Chen, Lingbing Guo, Yuzhong Qu

Figure 1 for TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs
Figure 2 for TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs
Figure 3 for TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs
Figure 4 for TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs
* Published in proceedings of the 18th International Semantic Web Conference (ISWC 2019) 
  Access Paper or Ask Questions

3D Dynamic Point Cloud Denoising via Spatial-Temporal Graph Learning


Apr 07, 2020
Wei Hu, Qianjiang Hu, Zehua Wang, Xiang Gao

Figure 1 for 3D Dynamic Point Cloud Denoising via Spatial-Temporal Graph Learning
Figure 2 for 3D Dynamic Point Cloud Denoising via Spatial-Temporal Graph Learning
Figure 3 for 3D Dynamic Point Cloud Denoising via Spatial-Temporal Graph Learning
Figure 4 for 3D Dynamic Point Cloud Denoising via Spatial-Temporal Graph Learning
* It's a new version of '3D Dynamic Point Cloud Denoising via Spatio-temporal Graph Modeling' (1904.12284). It was mis-posted. We will submit a replacement of this version to 1904.12284 
  Access Paper or Ask Questions

Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study


Mar 18, 2020
Farahnaz Akrami, Mohammed Samiul Saeef, Qingheng Zhang, Wei Hu, Chengkai Li

Figure 1 for Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study
Figure 2 for Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study
Figure 3 for Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study
Figure 4 for Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study
* accepted to SIGMOD 2020 
  Access Paper or Ask Questions