A collection of Graph Contrastive Learning methods.
It's worth noting that many traditional unsupervised graph representation learning methods inherently follow the contrastive paradigm (e.g., DeepWalk, node2vec, GAE/VGAE etc.). We will not elaborate on them here.
-
An Empirical Study of Graph Contrastive Learning (OpenReview)
-
Evaluating Modules in Graph Contrastive Learning (arXiv)
-
Bipartite Graph Embedding via Mutual Information Maximization (WSDM)
-
SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanism (WWW)
-
Graph Representation Learning by Ensemble Aggregating Subgraphs via Mutual Information Maximization (arXiv)
- Authors: Chenguang Wang, Ziwen Liu
- [paper]
-
Maximizing Mutual Information Across Feature and Topology Views for Learning Graph Representations (arXiv)
- Authors: Xiaolong Fan, Maoguo Gong, Yue Wu, Hao Li
- [paper]
-
Contrastive Multi-View Representation Learning on Graphs (ICML)
-
Graph Representation Learning via Graphical Mutual Information Maximization (WWW)
-
InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization (ICLR)
-
CommDGI: Community Detection Oriented Deep Graph Infomax (CIKM)
- Authors: Tianqi Zhang, Yun Xiong, Jiawei Zhang, Yao Zhang, Yizhu Jiao, Yangyong Zhu
- [paper]
-
Exploiting Mutual Information for Substructure-aware Graph Representation Learning (IJCAI)
- Authors: Pengyang Wang, Yanjie Fu, Yuanchun Zhou, Kunpeng Liu, Xiaolin Li, Kien Hua
- [paper]
-
Attributed Network Embedding based on Mutual Information Estimation (CIKM)
-
Graph Contrastive Learning with Local and Global Mutual Information Maximization (ICIT)
- Authors: Yifei Hu, Ya Zhang
- [paper]
-
Unsupervised Attributed Multiplex Network Embedding (AAAI)
-
Deep Graph InfoMax (ICLR)
-
Spatio-Temporal Deep Graph InfoMax (ICLR workshp @ RLGM)
- Authors: Felix L. Opolka, Aaron Solomon, Cătălina Cangea, Petar Veličković, Pietro Liò, R Devon Hjelm
- [paper]
-
GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training (KDD)
-
Graph Contrastive Learning with Augmentations (NeurIPS)
-
Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practices (WWW)
- Authors: Puja Trivedi, Ekdeep Singh Lubana, Yujun Yan, Yaoqing Yang, Danai Koutra
- [paper]
-
AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators (AAAI)
-
Graph Contrastive Learning with Adaptive Augmentation (WWW)
-
Graph Contrastive Learning Automated (ICML)
-
Adversarial Graph Augmentation to Improve Graph Contrastive Learning (NIPS)
-
Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast (arXiv)
- Authors: Wei Zhuo, Guang Tan
- [paper]
-
Jointly Learnable Data Augmentations for Self-Supervised GNNs (arXiv)
-
Directed Graph Contrastive Learning (NIPS)
-
InfoGCL: Information-Aware Graph Contrastive Learning (NIPS)
- Authors: Dongkuan Xu, Wei Cheng, Dongsheng Luo, Haifeng Chen, Xiang Zhang
- [paper]
-
Graph Adversarial Self-Supervised Learning (NIPS)
-
Motif-Driven Contrastive Learning of Graph Representations (arXiv)
- Authors: Shichang Zhang, Ziniu Hu, Arjun Subramonian, Yizhou Sun
- [paper]
-
Fairness-Aware Node Representation Learning (arXiv)
- Authors: Öykü Deniz Köse, Yanning Shen
- [paper]
-
Towards Domain-Agnostic Contrastive Learning (ICML)
- Authors: Vikas Verma, Minh-Thang Luong, Kenji Kawaguchi, Hieu Pham, Quoc V. Le
- [paper]
-
Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction (WWW)
- Authors: Yingheng Wang, Yaosen Min, Xin Chen, Ji Wu
- [paper]
-
Contrastive Self-supervised Learning for Graph Classification (AAAI)
- Authors: Jiaqi Zeng, Pengtao Xie
- [paper]
-
Deep Graph Contrastive Representation Learning (ICML Workshop on GRL)
-
Sub-graph Contrast for Scalable Self-Supervised Graph Representaion Learning (ICDM)