Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks

Abstract

This paper aims at revisiting Graph Convolutional Neural Networks by bridging the gap between spectral and spatial design of graph convolutions. We theoretically demonstrate some equivalence of the graph convolution process regardless it is designed in the spatial or the spectral domain. The obtained general framework allows to lead a spectral analysis of the most popular ConvGNNs, explaining their performance and showing their limits. Moreover, the proposed framework is used to design new convolutions in spectral domain with a custom frequency profile while applying them in the spatial domain. We also propose a generalization of the depthwise separable convolution framework for graph convolutional networks, what allows to decrease the total number of trainable parameters by keeping the capacity of the model. To the best of our knowledge, such a framework has never been used in the GNNs literature. Our proposals are evaluated on both transductive and inductive graph learning problems. Obtained results show the relevance of the proposed method and provide one of the first experimental evidence of transferability of spectral filter coefficients from one graph to another. Our source codes are publicly available at: https://github.com/balcilar/Spectral-Designed-Graph-Convolutions

24 pages, 8figures, preprint

References in corpus (7)

• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Geometric deep learning: going beyond Euclidean data
• Empirical Evaluation of Rectified Activations in Convolutional Network
• Deep Convolutional Networks on Graph-Structured Data
• Towards Sparse Hierarchical Graph Classifiers
• A Generalization of Convolutional Neural Networks to Graph-Structured Data
• Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules

Cited by in corpus (6)

• RA-GCN: Graph Convolutional Network for Disease Prediction Problems with Imbalanced Data
• Beyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filtering
• A Review of Graph Neural Networks and Their Applications in Power Systems
• Multiplex Graph Networks for Multimodal Brain Network Analysis
• Which Hyperparameters to Optimise? An Investigation of Evolutionary Hyperparameter Optimisation in Graph Neural Network For Molecular Property Prediction
• Spotting Silent Buffer Overflows in Execution Trace through Graph Neural Network Assisted Data Flow Analysis