Graph self-supervised learning based on frequency corruption

2026-04-17

AI Summary

This work addresses the underutilization of high-frequency signals in existing graph self-supervised learning methods, which often overfit to local structures and thereby limit representation quality and generalization. To overcome this, the authors propose a frequency-aware perturbation-based multi-view self-supervised framework. Specifically, they construct corrupted graphs enriched with high-frequency information by perturbing nodes and edges according to their low-frequency contributions, using these as inputs to an autoencoder while targeting reconstruction of low-frequency and general features to encourage multi-band information fusion. Additionally, diverse sampling strategies are introduced to generate multiple views, and node representations across views are aligned to enhance robustness. The method consistently achieves performance gains across node classification, graph prediction, and transfer learning tasks on 14 benchmark datasets, demonstrating its effectiveness and strong generalization capability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Representation Learning for Vision
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• graph self-supervised learning
• high-frequency signals
• overfitting
• representation quality
• generalization

Innovation

• graph self-supervised learning
• frequency corruption
• multi-frequency fusion
• robust representation learning
• graph autoencoder