Graph contrastive learning (CL) methods learn node representations in a self-supervised manner by maximizing the similarity between the augmented node representations obtained via a GNN-based encoder. However, CL methods perform poorly on graphs with heterophily, where connected nodes tend to belong to different classes. In this work, we address this problem by proposing an effective graph CL method, namely HLCL, for learning graph representations under heterophily. HLCL first identifies a homophilic and a heterophilic subgraph based on the cosine similarity of node features. It then uses a low-pass and a high-pass graph filter to aggregate representations of nodes connected in the homophilic subgraph and differentiate representations of nodes in the heterophilic subgraph. The final node representations are learned by contrasting both the augmented high-pass filtered views and the augmented low-pass filtered node views. Our extensive experiments show that HLCL outperforms state-of-the-art graph CL methods on benchmark datasets with heterophily, as well as large-scale real-world graphs, by up to 7%, and outperforms graph supervised learning methods on datasets with heterophily by up to 10%.
Rethinking Graph Contrastive Learning through Relative Similarity Preservation
Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心);University of Chinese Academy of Sciences(中国科学院大学);Hangzhou Institute for Advanced Study, UCAS(国科大杭州高等研究院);School of Computing and Information Technology, Great Bay University(大湾区大学计算与信息技术学院);Department of Computer and Information Science, IOTSC, University of Macau(澳门大学计算机与信息科学系)
Addressing Graph Heterogeneity and Heterophily from A Spectral Perspective
Beijing University of Posts and Telecommunications(北京邮电大学);National University of Singapore(新加坡国立大学);Beihang University(北京航空航天大学);Hangzhou Dianzi University(杭州电子科技大学)
How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing
School of Computing, National University of Singapore(新加坡国立大学计算机学院);Zhangjiang Institute for Advanced Study, Shanghai Jiao Tong University(上海交通大学张江高等研究院);Shanghai AI Laboratory(上海人工智能实验室);School of Mathematics and Statistics, University of New South Wales(新南威尔士大学数学与统计学院);Zhejiang Institute of Optoelectronics(浙江光电研究院);Zhejiang Normal University(浙江师范大学);Department of Computer Science and Technology, Cambridge University(剑桥大学计算机科学与技术系)
LOHA: Direct Graph Spectral Contrastive Learning Between Low-pass and High-pass Views
Xiamen University(厦门大学);National Institute for Data Science in Health and Medicine, Xiamen University(厦门大学国家健康与医学数据科学研究院);Pen-Tung Sah Institute of Micro-Nano Science and Technology, Xiamen University(厦门大学萨本栋微纳米科技研究院)
Graph Soft-Contrastive Learning via Neighborhood Ranking
Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心);University of Chinese Academy of Sciences(中国科学院大学);University of Macau(澳门大学);University of Central Florida(中佛罗里达大学);Rutgers University(罗格斯大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Contrastive Continual Multi-view Clustering with Filtered Structural Fusion
School of Computer, National University of Defense Technology(国防科技大学计算机学院);School of Computer Science and Technology, Harbin University of Science and Technology(哈尔滨理工大学计算机科学与技术学院)
Aligning the Spectrum: Hybrid Graph Pre-training and Prompt Tuning across Homophily and Heterophily
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Pennsylvania State University(宾夕法尼亚州立大学)
Adaptive Heterogeneous Graph Neural Networks: Bridging Heterophily and Heterogeneity
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University(通用人工智能国家重点实验室,智能科学与技术学院,北京大学)
Rank Supervised Contrastive Learning for Time Series Classification
School of Computing University of Connecticut Storrs, United States;Knight Foundation School of Computing;Information Sciences Florida International University Florida, United States;School of Computing University of Connecticut Storrs, United Statse
STS-CCL: Spatial-Temporal Synchronous Contextual Contrastive Learning for Urban Traffic Forecasting
Zhejiang University(浙江大学);South China University of Technology(华南理工大学);The University of Sydney(悉尼大学);Chongqing University(重庆大学);Zhejiang Institute of Industry and Information Technology(浙江工业信息技术研究院)
SSC-UNet: UNet with Self-Supervised Contrastive Learning for Phonocardiography Noise Reduction
Walton Institute, South East Technological University(沃森研究所,东南技术大学);Children’s Health Ireland Hospital(儿童健康爱尔兰医院);Tiruvalla Medical Mission Hospital(提鲁瓦拉医疗使命医院)
Pathology-Aware Multi-View Contrastive Learning for Patient-Independent ECG Reconstruction
Department of Computer Science and Engineering, Indian Institute of Technology Roorkee(计算机科学与工程系,印度理工学院Roorkee);Department of Biosciences and Bioengineering, Indian Institute of Technology Roorkee(生物科学与生物工程系,印度理工学院Roorkee)
School of Computer Science and Engineering, University of Electronic Science and Technology of China(电子科技大学计算机科学与工程学院);Alibaba Group(阿里巴巴集团);Michigan State University(密歇根州立大学)
MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series
Shandong University(山东大学);Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University(山东大学-南洋理工大学联合人工智能研究中心(C-FAIR));Lund University(隆德大学);Nanyang Technological University(南洋理工大学)
Topology Reorganized Graph Contrastive Learning with Mitigating Semantic Drift
College of Computer Science & Technology, Nanjing University of Aeronautics & Astronautics(南京航空航天大学计算机科学与技术学院);MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing University of Aeronautics & Astronautics(南京航空航天大学工信部模式分析与机器智能重点实验室)