An Experimental Study of the Transferability of Spectral Graph Networks

Abstract

Spectral graph convolutional networks are generalizations of standard convolutional networks for graph-structured data using the Laplacian operator. A common misconception is the instability of spectral filters, i.e. the impossibility to transfer spectral filters between graphs of variable size and topology. This misbelief has limited the development of spectral networks for multi-graph tasks in favor of spatial graph networks. However, recent works have proved the stability of spectral filters under graph perturbation. Our work complements and emphasizes further the high quality of spectral transferability by benchmarking spectral graph networks on tasks involving graphs of different size and connectivity. Numerical experiments exhibit favorable performance on graph regression, graph classification, and node classification problems on two graph benchmarks. The implementation of our experiments is available on GitHub for reproducibility.

arXiv comment5 pages, AAAI 2021 Workshop on Deep Learning on Graphs: Methods and Applications (DLG-AAAI 2021)

References in corpus (13)

• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Spectral Networks and Locally Connected Networks on Graphs
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• Residual Gated Graph ConvNets
• Benchmarking Graph Neural Networks
• Fake News Detection on Social Media using Geometric Deep Learning
• Modeling Relational Data with Graph Convolutional Networks
• Learning Symbolic Physics with Graph Networks
• Image Classification with Hierarchical Multigraph Networks
• Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules