Graph Persistence goes Spectral

TL;DR

This paper introduces SpectRe, a novel topological descriptor combining spectral information with persistent homology to improve graph representation learning, demonstrating enhanced expressivity and stability over existing methods.

Contribution

SpectRe is a new descriptor that integrates spectral data into PH diagrams, surpassing previous methods in expressivity and stability for graph analysis.

Findings

SpectRe is strictly more expressive than traditional PH and spectral methods.

SpectRe demonstrates local stability in graph representations.

Experiments show SpectRe improves performance on synthetic and real-world datasets.

Abstract

Including intricate topological information (e.g., cycles) provably enhances the expressivity of message-passing graph neural networks (GNNs) beyond the Weisfeiler-Leman (WL) hierarchy. Consequently, Persistent Homology (PH) methods are increasingly employed for graph representation learning. In this context, recent works have proposed decorating classical PH diagrams with vertex and edge features for improved expressivity. However, these methods still fail to capture basic graph structural information. In this paper, we propose SpectRe -- a new topological descriptor for graphs that integrates spectral information into PH diagrams. Notably, SpectRe is strictly more expressive than PH and spectral information on graphs alone. We also introduce notions of global and local stability to analyze existing descriptors and establish that SpectRe is locally stable. Finally, experiments on synthetic and real-world datasets demonstrate the effectiveness of SpectRe and its potential to enhance the capabilities of graph models in relevant learning tasks. Code is available at https://github.com/Aalto-QuML/SpectRe/.