Generative and Contrastive Graph Representation Learning

TL;DR

This paper introduces a novel graph self-supervised learning framework that combines contrastive and generative approaches, utilizing community-aware contrastive learning and diverse augmentations to improve performance on multiple graph tasks.

Contribution

The paper proposes an integrated graph SSL architecture that leverages community-aware contrastive learning and comprehensive augmentations, advancing the effectiveness of graph representation learning.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Achieves 0.23%-2.01% performance improvement across tasks.

Enhances robustness and diversity of learned representations.

Abstract

Self-supervised learning (SSL) on graphs generates node and graph representations (i.e., embeddings) that can be used for downstream tasks such as node classification, node clustering, and link prediction. Graph SSL is particularly useful in scenarios with limited or no labeled data. Existing SSL methods predominantly follow contrastive or generative paradigms, each excelling in different tasks: contrastive methods typically perform well on classification tasks, while generative methods often excel in link prediction. In this paper, we present a novel architecture for graph SSL that integrates the strengths of both approaches. Our framework introduces community-aware node-level contrastive learning, providing more robust and effective positive and negative node pairs generation, alongside graph-level contrastive learning to capture global semantic information. Additionally, we employ a comprehensive augmentation strategy that combines feature masking, node perturbation, and edge perturbation, enabling robust and diverse representation learning. By incorporating these enhancements, our model achieves superior performance across multiple tasks, including node classification, clustering, and link prediction. Evaluations on open benchmark datasets demonstrate that our model outperforms state-of-the-art methods, achieving a performance lift of 0.23%-2.01% depending on the task and dataset.