Spectral-Aware Augmentation for Enhanced Graph Representation Learning

TL;DR

This paper introduces GASSER, a spectral-aware augmentation method for graph contrastive learning that selectively perturbs specific frequency components, improving representation quality by preserving task-relevant information.

Contribution

GASSER is the first method to apply frequency-specific perturbations guided by spectral insights, enhancing graph augmentation adaptiveness and effectiveness.

Findings

GASSER improves downstream task performance across multiple datasets.

Spectral-guided perturbations better preserve task-relevant information.

Theoretical analysis supports the effectiveness of frequency-specific augmentation.

Abstract

Graph Contrastive Learning (GCL) has demonstrated remarkable effectiveness in learning representations on graphs in recent years. To generate ideal augmentation views, the augmentation generation methods should preserve essential information while discarding less relevant details for downstream tasks. However, current augmentation methods usually involve random topology corruption in the spatial domain, which fails to adequately address information spread across different frequencies in the spectral domain. Our preliminary study highlights this issue, demonstrating that spatial random perturbations impact all frequency bands almost uniformly. Given that task-relevant information typically resides in specific spectral regions that vary across graphs, this one-size-fits-all approach can pose challenges. We argue that indiscriminate spatial random perturbation might unintentionally weaken task-relevant information, reducing its effectiveness. To tackle this challenge, we propose applying perturbations selectively, focusing on information specific to different frequencies across diverse graphs. In this paper, we present GASSER, a model that applies tailored perturbations to specific frequencies of graph structures in the spectral domain, guided by spectral hints. Through extensive experimentation and theoretical analysis, we demonstrate that the augmentation views generated by GASSER are adaptive, controllable, and intuitively aligned with the homophily ratios and spectrum of graph structures.