Contrastive Learning Meets Pseudo-label-assisted Mixup Augmentation: A Comprehensive Graph Representation Framework from Local to Global

TL;DR

This paper introduces ComGRL, a comprehensive graph representation framework that combines local and global information through contrastive learning and pseudo-label-assisted Mixup augmentation, improving node classification performance.

Contribution

The novel ComGRL framework effectively integrates local and global graph information using contrastive learning and Mixup, advancing graph representation learning methods.

Findings

Achieves state-of-the-art results on six graph datasets.

Effectively combines local and global information for better representations.

Demonstrates robustness and improved accuracy in node classification.

Abstract

Graph Neural Networks (GNNs) have demonstrated remarkable effectiveness in various graph representation learning tasks. However, most existing GNNs focus primarily on capturing local information through explicit graph convolution, often neglecting global message-passing. This limitation hinders the establishment of a collaborative interaction between global and local information, which is crucial for comprehensively understanding graph data. To address these challenges, we propose a novel framework called Comprehensive Graph Representation Learning (ComGRL). ComGRL integrates local information into global information to derive powerful representations. It achieves this by implicitly smoothing local information through flexible graph contrastive learning, ensuring reliable representations for subsequent global exploration. Then ComGRL transfers the locally derived representations to a multi-head self-attention module, enhancing their discriminative ability by uncovering diverse and rich global correlations. To further optimize local information dynamically under the self-supervision of pseudo-labels, ComGRL employs a triple sampling strategy to construct mixed node pairs and applies reliable Mixup augmentation across attributes and structure for local contrastive learning. This approach broadens the receptive field and facilitates coordination between local and global representation learning, enabling them to reinforce each other. Experimental results across six widely used graph datasets demonstrate that ComGRL achieves excellent performance in node classification tasks. The code could be available at https://github.com/JinluWang1002/ComGRL.