Improving Graph Contrastive Learning via Adaptive Positive Sampling

Jiaming Zhuo, Feiyang Qin, Can Cui, Kun Fu, Bingxin Niu, Mengzhu Wang, Yuanfang Guo, Chuan Wang, Zhen Wang, Xiaochun Cao, Liang Yang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 23179-23187

Graph Contrastive Learning (GCL) a Self-Supervised Learning (SSL) architecture tailored for graphs has shown notable potential for mitigating label scarcity. Its core idea is to amplify feature similarities between the positive sample pairs and reduce them between the negative sample pairs. Unfortunately most existing GCLs consistently present suboptimal performances on both homophilic and heterophilic graphs. This is primarily attributed to two limitations of positive sampling that is incomplete local sampling and blind sampling. To address these limitations this paper introduces a novel GCL framework with an adaptive positive sampling module named grapH contrastivE Adaptive posiTive Samples (HEATS). Motivated by the observation that the affinity matrix corresponding to optimal positive sample sets has a block-diagonal structure with equal weights within each block a self-expressive learning objective incorporating the block and idempotent constraint is presented. This learning objective and the contrastive learning objective are iteratively optimized to improve the adaptability and robustness of HEATS. Extensive experiments on graphs and images validate the effectiveness and generality of HEATS.