An Empirical Study of Graph Contrastive Learning
This work provides empirical insights and a library to ease implementation for researchers in graph representation learning, but it is incremental as it builds on existing GCL paradigms without introducing new methods.
The paper tackles the lack of understanding in Graph Contrastive Learning (GCL) by identifying critical design components and conducting extensive experiments, resulting in general guidelines such as using sparse graph augmentations and aligning contrasting modes with task granularities, with performance improvements demonstrated on benchmark datasets.
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 augmentations that produce sparse graph views bring promising 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 library PyGCL, featuring modularized CL components, standardized evaluation, and experiment management. We envision this work to provide useful empirical evidence of effective GCL algorithms and offer several insights for future research.