Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

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

Muhammet Balcilar 1 Guillaume Renton 1 Pierre Héroux 1 Benoît Gaüzère 1 Sébastien Adam 1 Paul Honeine 1 
1 DocApp - LITIS - Equipe Apprentissage
LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes
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.
Complete list of metadata

Cited literature [40 references]  Display  Hide  Download
Contributor : Paul Honeine Connect in order to contact the contributor
Submitted on : Monday, March 23, 2020 - 3:23:40 PM
Last modification on : Wednesday, March 2, 2022 - 10:10:12 AM


Files produced by the author(s)


  • HAL Id : hal-02515637, version 1


Muhammet Balcilar, Guillaume Renton, Pierre Héroux, Benoît Gaüzère, Sébastien Adam, et al.. Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks. 2020. ⟨hal-02515637⟩



Record views


Files downloads