An Empirical Study of Graph Contrastive Learning

Yanqiao Zhu, Yichen Xu, Qiang Liu, Shu Wu

Keywords: Graph contrastive learning, self-supervised learning, graph neural networks

Abstract: Graph Contrastive Learning (GCL) establishes a new paradigm for learning graph representations without human annotations. Although remarkable progress has been witnessed recently, the success behind GCL is still left somewhat mysterious. In this work, we first identify several critical design considerations within a general GCL paradigm, including augmentation functions, contrasting modes, contrastive objectives, and negative mining techniques. Then, to understand the interplay of different GCL components, we conduct extensive, controlled experiments over a set of benchmark tasks on datasets across various domains. Our empirical studies suggest a set of general receipts for effective GCL, e.g., simple topology augmentation that produces sparse graphs brings most performance improvements; contrasting modes should be aligned with the granularities of end tasks. In addition, to foster future research and ease the implementation of GCL algorithms, we develop an easy-to-use toolbox PyGCL, featuring modularized CL components, standardized evaluation, and experiment management. We envision this work to provide useful empirical evidence of existing GCL architectures and offer several insights for future research.

URL: https://github.com/GraphCL/PyGCL

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2109.01116/code)