Graph self-supervised learning based on frequency corruption

TL;DR

This paper introduces FC-GSSL, a graph self-supervised learning method that enhances representation quality by corrupting graphs to emphasize different frequency signals and fusing multi-frequency information.

Contribution

The paper proposes a novel frequency corruption technique and sampling strategies to improve robustness and generalization in graph self-supervised learning.

Findings

FC-GSSL outperforms existing methods on 14 datasets.

Corrupted graphs biased toward high-frequency signals improve robustness.

Multi-frequency fusion enhances representation quality.

Abstract

Graph self-supervised learning can reduce the need for labeled graph data and has been widely used in recommendation, social networks, and other web applications. However, existing methods often underuse high-frequency signals and may overfit to specific local patterns, which limits representation quality and generalization. We propose Frequency-Corrupt Based Graph Self-Supervised Learning (FC-GSSL), a method that builds corrupted graphs biased toward high-frequency information by corrupting nodes and edges according to their low-frequency contributions. These corrupted graphs are used as inputs to an autoencoder, while low-frequency and general features are reconstructed as supervision targets, forcing the model to fuse information from multiple frequency bands. We further design multiple sampling strategies and generate diverse corrupted graphs from the intersections and unions of the sampling results. By aligning node representations from these views, the model can discover useful frequency combinations, reduce reliance on specific high-frequency components, and improve robustness. Experiments on 14 datasets across node classification, graph prediction, and transfer learning show that FC-GSSL consistently improves performance and generalization.