Graph Self-Supervised Learning: A Survey

TL;DR

This survey comprehensively reviews graph self-supervised learning methods, categorizing approaches, discussing applications, datasets, benchmarks, and future challenges to advance understanding in this emerging field.

Contribution

It provides a unified framework and taxonomy for graph SSL, highlighting its unique aspects and summarizing recent developments, datasets, and open challenges.

Findings

Categorizes graph SSL approaches into four main types.

Summarizes key datasets and benchmarks used in the field.

Identifies open challenges and future research directions.

Abstract

Deep learning on graphs has attracted significant interests recently. However, most of the works have focused on (semi-) supervised learning, resulting in shortcomings including heavy label reliance, poor generalization, and weak robustness. To address these issues, self-supervised learning (SSL), which extracts informative knowledge through well-designed pretext tasks without relying on manual labels, has become a promising and trending learning paradigm for graph data. Different from SSL on other domains like computer vision and natural language processing, SSL on graphs has an exclusive background, design ideas, and taxonomies. Under the umbrella of graph self-supervised learning, we present a timely and comprehensive review of the existing approaches which employ SSL techniques for graph data. We construct a unified framework that mathematically formalizes the paradigm of graph SSL. According to the objectives of pretext tasks, we divide these approaches into four categories: generation-based, auxiliary property-based, contrast-based, and hybrid approaches. We further describe the applications of graph SSL across various research fields and summarize the commonly used datasets, evaluation benchmark, performance comparison and open-source codes of graph SSL. Finally, we discuss the remaining challenges and potential future directions in this research field.