Graph Structure Refinement with Energy-based Contrastive Learning

TL;DR

This paper introduces ECL-GSR, an unsupervised graph structure refinement method that combines energy-based contrastive learning with generative and discriminative training to improve GNN performance on noisy graphs.

Contribution

It is the first to integrate energy-based models with contrastive learning for graph structure refinement, enhancing robustness and efficiency of GNNs.

Findings

Outperforms state-of-the-art on eight benchmarks.

Faster training with fewer samples and memory.

Improves node classification accuracy.

Abstract

Graph Neural Networks (GNNs) have recently gained widespread attention as a successful tool for analyzing graph-structured data. However, imperfect graph structure with noisy links lacks enough robustness and may damage graph representations, therefore limiting the GNNs' performance in practical tasks. Moreover, existing generative architectures fail to fit discriminative graph-related tasks. To tackle these issues, we introduce an unsupervised method based on a joint of generative training and discriminative training to learn graph structure and representation, aiming to improve the discriminative performance of generative models. We propose an Energy-based Contrastive Learning (ECL) guided Graph Structure Refinement (GSR) framework, denoted as ECL-GSR. To our knowledge, this is the first work to combine energy-based models with contrastive learning for GSR. Specifically, we leverage ECL to approximate the joint distribution of sample pairs, which increases the similarity between representations of positive pairs while reducing the similarity between negative ones. Refined structure is produced by augmenting and removing edges according to the similarity metrics among node representations. Extensive experiments demonstrate that ECL-GSR outperforms the state-of-the-art on eight benchmark datasets in node classification. ECL-GSR achieves faster training with fewer samples and memories against the leading baseline, highlighting its simplicity and efficiency in downstream tasks.