Papers › Beyond Homophily with Graph Echo State Networks

Beyond Homophily with Graph Echo State Networks

27 Oct 202230th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) 2022 10arXiv:2210.15731archive 2025-07-28

Domenico Tortorella, Alessio Micheli

Graph Echo State Networks (GESN) have already demonstrated their efficacy and efficiency in graph classification tasks. However, semi-supervised node classification brought out the problem of over-smoothing in end-to-end trained deep models, which causes a bias towards high homophily graphs. We evaluate for the first time GESN on node classification tasks with different degrees of homophily, analyzing also the impact of the reservoir radius. Our experiments show that reservoir models are able to achieve better or comparable accuracy with respect to fully trained deep models that implement ad hoc variations in the architectural bias, with a gain in terms of efficiency.

PaperPDFConference PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

ClassificationGraph ClassificationNode Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Actor Graph ESN Accuracy 34.5 ± 0.8 #51 of 62 Archive leaderboard report
Node Classification Chameleon Graph ESN Accuracy 76.2±1.2 #8 of 61 Archive leaderboard report
Node Classification Citeseer Full-supervised Graph ESN Accuracy 74.5±2.1 #6 of 7 Archive leaderboard report
Node Classification Cora Full-supervised Graph ESN Accuracy 86.0±1.0 #5 of 9 Archive leaderboard report
Node Classification Cornell Graph ESN Accuracy 81.1±6.0 #39 of 60 Archive leaderboard report
Node Classification Pubmed Full-supervised Graph ESN Accuracy 89.2±0.3 #5 of 7 Archive leaderboard report
Node Classification Squirrel Graph ESN Accuracy 71.2±1.5 #8 of 59 Archive leaderboard report
Node Classification Texas Graph ESN Accuracy 84.3±4.4 #37 of 62 Archive leaderboard report
Node Classification Wisconsin Graph ESN Accuracy 83.3±3.8 #46 of 63 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

HOC

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