Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classification
This work addresses the need for more property-conserving and structure-sensitive augmentation methods in graph classification, representing an incremental improvement over existing techniques.
The authors tackled the problem of graph property distortions and limited structural changes in graph data augmentation by developing Dual-Prism methods that preserve low-frequency eigenvalues to maintain critical properties. Their approach, validated through extensive experiments, offers a new direction for graph data augmentation.
Graph Neural Networks have become the preferred tool to process graph data, with their efficacy being boosted through graph data augmentation techniques. Despite the evolution of augmentation methods, issues like graph property distortions and restricted structural changes persist. This leads to the question: Is it possible to develop more property-conserving and structure-sensitive augmentation methods? Through a spectral lens, we investigate the interplay between graph properties, their augmentation, and their spectral behavior, and observe that keeping the low-frequency eigenvalues unchanged can preserve the critical properties at a large scale when generating augmented graphs. These observations inform our introduction of the Dual-Prism (DP) augmentation methods, including DP-Noise and DP-Mask, which retain essential graph properties while diversifying augmented graphs. Extensive experiments validate the efficiency of our approach, providing a new and promising direction for graph data augmentation.