{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/beyond-homophily-with-graph-echo-state-1","title":"Beyond Homophily with Graph Echo State Networks","arxiv_id":"2210.15731","date":"2022-10-27","proceeding":"30th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) 2022 10","authors":["Domenico Tortorella","Alessio Micheli"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2210.15731v1","url_pdf":"https://arxiv.org/pdf/2210.15731v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[{"method_slug":"hoc","method_name":"HOC"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-actor","task":"Node Classification","dataset":"Actor","model":"Graph ESN","rank_in_archive_order":51,"of":62,"metrics":{"Accuracy":"34.5 ± 0.8"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon","task":"Node Classification","dataset":"Chameleon","model":"Graph ESN","rank_in_archive_order":8,"of":61,"metrics":{"Accuracy":"76.2±1.2"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-full","task":"Node Classification","dataset":"Citeseer Full-supervised","model":"Graph ESN","rank_in_archive_order":6,"of":7,"metrics":{"Accuracy":"74.5±2.1"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-full-supervised","task":"Node Classification","dataset":"Cora Full-supervised","model":"Graph ESN","rank_in_archive_order":5,"of":9,"metrics":{"Accuracy":"86.0±1.0"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell","task":"Node Classification","dataset":"Cornell","model":"Graph ESN","rank_in_archive_order":39,"of":60,"metrics":{"Accuracy":"81.1±6.0"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-full-supervised","task":"Node Classification","dataset":"Pubmed Full-supervised","model":"Graph ESN","rank_in_archive_order":5,"of":7,"metrics":{"Accuracy":"89.2±0.3"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel","task":"Node Classification","dataset":"Squirrel","model":"Graph ESN","rank_in_archive_order":8,"of":59,"metrics":{"Accuracy":"71.2±1.5"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas","task":"Node Classification","dataset":"Texas","model":"Graph ESN","rank_in_archive_order":37,"of":62,"metrics":{"Accuracy":"84.3±4.4"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin","task":"Node Classification","dataset":"Wisconsin","model":"Graph ESN","rank_in_archive_order":46,"of":63,"metrics":{"Accuracy":"83.3±3.8"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}