1.8k citations
- Peking UniversityCN36 papers
- University of Chinese Academy of SciencesCN21 papers
- Sun Yat-sen UniversityCN20 papers
- Tsinghua UniversityCN20 papers
- Harbin Institute of TechnologyCN19 papers
- Chinese Academy of SciencesCN15 papers
- Beihang UniversityCN14 papers
- Southern University of Science and TechnologyCN14 papers
- Tencent (China)CN14 papers
- Beijing Jiaotong UniversityCN9 papers
- Hong Kong University of Science and TechnologyHK9 papers
- Institute of Computing TechnologyCN8 papers
16 papers · 1 filter
MaxMatch: Semi-Supervised Learning with Worst-Case Consistency
Yangbangyan Jiang, Xiaodan Li, Yuefeng Chen +5
In recent years, great progress has been made to incorporate unlabeled data to overcome the inefficiently supervised problem via semi-supervised learning (SSL). Most state-of-the-a…
A Tale of HodgeRank and Spectral Method: Target Attack Against Rank Aggregation Is the Fixed Point of Adversarial Game
Ke Ma, Qianqian Xu, Jinshan Zeng +3
Rank aggregation with pairwise comparisons has shown promising results in elections, sports competitions, recommendations, and information retrieval. However, little attention has…
Continuous-Time and Multi-Level Graph Representation Learning for Origin-Destination Demand Prediction
Liangzhe Han, Xiaojian Ma, Leilei Sun +4
Traffic demand forecasting by deep neural networks has attracted widespread interest in both academia and industry society. Among them, the pairwise Origin-Destination (OD) demand…
Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network
Tianyu Zhao, Cheng Yang, Yibo Li +7
Heterogeneous Graph Neural Network (HGNN) has been successfully employed in various tasks, but we cannot accurately know the importance of different design dimensions of HGNNs due…
Spatial-Temporal Sequential Hypergraph Network for Crime Prediction with Dynamic Multiplex Relation Learning
Lianghao Xia, Chao Huang, Yong Xu +4
Crime prediction is crucial for public safety and resource optimization, yet is very challenging due to two aspects: i) the dynamics of criminal patterns across time and space, cri…
Learning with Noisy Labels via Sparse Regularization
Xiong Zhou, Xianming Liu, Chenyang Wang +3
Learning with noisy labels is an important and challenging task for training accurate deep neural networks. Some commonly-used loss functions, such as Cross Entropy (CE), suffer fr…