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

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

26 Mar 2020arXiv:2003.11702archive 2025-07-28

Muhammet Balcilar, Guillaume Renton, Pierre Heroux, Benoit Gauzere, Sebastien Adam, Paul Honeine

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

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

balcilar/Spectral-Designed-Graph-Convolutions officialmentioned in papermentioned on GitHubtf report
sidneyarcidiacono/UnderstandingGCNs mentioned on GitHubGPL-3.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Graph ClassificationGraph LearningNode Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification ENZYMES DSGCN-allfeat Accuracy 78.39 #4 of 54 Archive leaderboard report
Graph Classification ENZYMES DSGCN-nodelabel Accuracy 65.13 #21 of 54 Archive leaderboard report
Node Classification CiteSeer with Public Split: fixed 20 nodes per class DSGCN Accuracy 73.3 #17 of 40 Archive leaderboard report
Node Classification Cora with Public Split: fixed 20 nodes per class DSGCN Accuracy 84.2% #12 of 36 Archive leaderboard report
Node Classification Cora: fixed 20 node per class DSGCN Accuracy 84.2 #1 of 9 Archive leaderboard report
Node Classification PPI DSGCN F1 99.09 ± 0.03 #11 of 24 Archive leaderboard report
Node Classification PubMed with Public Split: fixed 20 nodes per class DSGCN Accuracy 81.9% #5 of 37 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ConvolutionDepthwise ConvolutionDepthwise Separable ConvolutionPointwise Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections