140 citations · 223 across the 10 of their papers we have counts for
Showing 2022Show all
3 papers · 1 filter
cs.LG2022★ 2 cited
Single-Pass Contrastive Learning Can Work for Both Homophilic and Heterophilic Graph
Haonan Wang, Jieyu Zhang, Qi Zhu +3
Existing graph contrastive learning (GCL) techniques typically require two forward passes for a single instance to construct the contrastive loss, which is effective for capturing…
cs.LG2022★ 9 cited
Augmentation-Free Graph Contrastive Learning with Performance Guarantee
Haonan Wang, Jieyu Zhang, Qi Zhu +1
Graph contrastive learning (GCL) is the most representative and prevalent self-supervised learning approach for graph-structured data. Despite its remarkable success, existing GCL…
cs.LG2022★ 2 cited
Shift-Robust Node Classification via Graph Adversarial Clustering
Qi Zhu, Chao Zhang, Chanyoung Park +2
Graph Neural Networks (GNNs) are de facto node classification models in graph structured data. However, during testing-time, these algorithms assume no data shift, i.e., $\Pr_\text…