{"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-low-frequency-information-in-graph","title":"Beyond Low-frequency Information in Graph Convolutional Networks","arxiv_id":"2101.00797","date":"2021-01-04","proceeding":null,"authors":["Deyu Bo","Xiao Wang","Chuan Shi","HuaWei Shen"],"abstract":"Graph neural networks (GNNs) have been proven to be effective in various network-related tasks. Most existing GNNs usually exploit the low-frequency signals of node features, which gives rise to one fundamental question: is the low-frequency information all we need in the real world applications? In this paper, we first present an experimental investigation assessing the roles of low-frequency and high-frequency signals, where the results clearly show that exploring low-frequency signal only is distant from learning an effective node representation in different scenarios. How can we adaptively learn more information beyond low-frequency information in GNNs? A well-informed answer can help GNNs enhance the adaptability. We tackle this challenge and propose a novel Frequency Adaptation Graph Convolutional Networks (FAGCN) with a self-gating mechanism, which can adaptively integrate different signals in the process of message passing. For a deeper understanding, we theoretically analyze the roles of low-frequency signals and high-frequency signals on learning node representations, which further explains why FAGCN can perform well on different types of networks. Extensive experiments on six real-world networks validate that FAGCN not only alleviates the over-smoothing problem, but also has advantages over the state-of-the-arts.","url_abs":"https://arxiv.org/abs/2101.00797v1","url_pdf":"https://arxiv.org/pdf/2101.00797v1.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":[{"paper_slug":"beyond-low-frequency-information-in-graph","repo_url":"https://github.com/bdy9527/FAGCN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"node-classification-on-non-homophilic","task_name":"Node Classification on Non-Homophilic (Heterophilic) Graphs"}],"methods":[{"method_slug":"graph-convolutional-networks","method_name":"Graph Convolutional Networks"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-actor","task":"Node Classification","dataset":"Actor","model":"FAGCN","rank_in_archive_order":48,"of":62,"metrics":{"Accuracy":"34.82 ± 1.35"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon","task":"Node Classification","dataset":"Chameleon","model":"FAGCN","rank_in_archive_order":60,"of":61,"metrics":{"Accuracy":"46.07 ± 2.11"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon-60-20-20","task":"Node Classification","dataset":"Chameleon (60%/20%/20% random splits)","model":"FAGCN","rank_in_archive_order":36,"of":38,"metrics":{"1:1 Accuracy":"49.47 ± 2.84"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-60-20-20","task":"Node Classification","dataset":"CiteSeer (60%/20%/20% random splits)","model":"FAGCN","rank_in_archive_order":2,"of":33,"metrics":{"1:1 Accuracy":"82.37 ± 1.46"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-60-20-20","task":"Node Classification","dataset":"CiteSeer (60%/20%/20% random splits)","model":"H2GCN","rank_in_archive_order":23,"of":33,"metrics":{"1:1 Accuracy":"79.97 ± 0.69"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-48-32-20","task":"Node Classification","dataset":"Citeseer (48%/32%/20% fixed splits)","model":"FAGCN","rank_in_archive_order":14,"of":26,"metrics":{"1:1 Accuracy":"77.07 ± 2.05"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-48-32-20-fixed","task":"Node Classification","dataset":"Cora (48%/32%/20% fixed splits)","model":"FAGCN","rank_in_archive_order":10,"of":26,"metrics":{"1:1 Accuracy":"88.05 ± 1.57"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-60-20-20-random","task":"Node Classification","dataset":"Cora (60%/20%/20% random splits)","model":"FAGCN","rank_in_archive_order":16,"of":33,"metrics":{"1:1 Accuracy":"88.85 ± 1.36"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell","task":"Node Classification","dataset":"Cornell","model":"FAGCN","rank_in_archive_order":46,"of":60,"metrics":{"Accuracy":"76.76 ± 5.87"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell-60-20-20","task":"Node Classification","dataset":"Cornell (60%/20%/20% random splits)","model":"FAGCN","rank_in_archive_order":21,"of":36,"metrics":{"1:1 Accuracy":"88.03 ± 5.6"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-film-60-20-20-random","task":"Node Classification","dataset":"Film (60%/20%/20% random splits)","model":"H2GCN","rank_in_archive_order":23,"of":37,"metrics":{"1:1 Accuracy":"38.85 ± 1.17"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-film-60-20-20-random","task":"Node Classification","dataset":"Film (60%/20%/20% random splits)","model":"FAGCN","rank_in_archive_order":35,"of":37,"metrics":{"1:1 Accuracy":"31.59 ± 1.37"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-48-32-20-fixed","task":"Node Classification","dataset":"PubMed (48%/32%/20% fixed splits)","model":"FAGCN","rank_in_archive_order":22,"of":26,"metrics":{"1:1 Accuracy":"88.09 ± 1.38"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-60-20-20-random","task":"Node Classification","dataset":"PubMed (60%/20%/20% random splits)","model":"FAGCN","rank_in_archive_order":18,"of":37,"metrics":{"1:1 Accuracy":"89.98 ± 0.54"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel","task":"Node Classification","dataset":"Squirrel","model":"FAGCN","rank_in_archive_order":58,"of":59,"metrics":{"Accuracy":"30.83 ± 0.69"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel-60-20-20","task":"Node Classification","dataset":"Squirrel (60%/20%/20% random splits)","model":"FAGCN","rank_in_archive_order":25,"of":37,"metrics":{"1:1 Accuracy":"42.24 ± 1.2"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas","task":"Node Classification","dataset":"Texas","model":"FAGCN","rank_in_archive_order":53,"of":62,"metrics":{"Accuracy":"76.49 ± 2.87"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas-60-20-20-random","task":"Node Classification","dataset":"Texas (60%/20%/20% random splits)","model":"FAGCN","rank_in_archive_order":19,"of":36,"metrics":{"1:1 Accuracy":"88.85 ± 4.39"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin","task":"Node Classification","dataset":"Wisconsin","model":"WRGAT","rank_in_archive_order":32,"of":63,"metrics":{"Accuracy":"86.98 ± 3.78"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin","task":"Node Classification","dataset":"Wisconsin","model":"FAGCN","rank_in_archive_order":53,"of":63,"metrics":{"Accuracy":"79.61 ± 1.58"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin-60-20-20","task":"Node Classification","dataset":"Wisconsin (60%/20%/20% random splits)","model":"FAGCN","rank_in_archive_order":18,"of":35,"metrics":{"1:1 Accuracy":"89.75 ± 6.37"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-11","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Chameleon (48%/32%/20% fixed splits)","model":"FAGCN","rank_in_archive_order":29,"of":29,"metrics":{"1:1 Accuracy":"46.07 ± 2.11"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-4","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Chameleon(60%/20%/20% random splits)","model":"FAGCN","rank_in_archive_order":30,"of":32,"metrics":{"1:1 Accuracy":"49.47 ± 2.84"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-7","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Cornell (48%/32%/20% fixed splits)","model":"FAGCN","rank_in_archive_order":23,"of":27,"metrics":{"1:1 Accuracy":"76.76 ± 5.87"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Cornell (60%/20%/20% random splits)","model":"FAGCN","rank_in_archive_order":21,"of":33,"metrics":{"1:1 Accuracy":"88.03 ± 5.6"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-6","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Deezer-Europe","model":"FAGCN","rank_in_archive_order":10,"of":28,"metrics":{"1:1 Accuracy":"66.86±0.53"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-10","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Film(48%/32%/20% fixed splits)","model":"FAGCN","rank_in_archive_order":22,"of":26,"metrics":{"1:1 Accuracy":"34.82 ± 1.35"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-12","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Squirrel (48%/32%/20% fixed splits)","model":"FAGCN","rank_in_archive_order":29,"of":29,"metrics":{"1:1 Accuracy":"30.83 ± 0.69"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-9","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Texas (48%/32%/20% fixed splits)","model":"H2GCN","rank_in_archive_order":10,"of":26,"metrics":{"1:1 Accuracy":"84.86 ± 7.23"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-9","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Texas (48%/32%/20% fixed splits)","model":"FAGCN","rank_in_archive_order":22,"of":26,"metrics":{"1:1 Accuracy":"76.49 ± 2.87"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-2","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Texas(60%/20%/20% random splits)","model":"FAGCN","rank_in_archive_order":18,"of":32,"metrics":{"1:1 Accuracy":"88.85 ± 4.39"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-8","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Wisconsin (48%/32%/20% fixed splits)","model":"FAGCN","rank_in_archive_order":21,"of":26,"metrics":{"1:1 Accuracy":"79.61 ± 1.58"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-1","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Wisconsin(60%/20%/20% random splits)","model":"FAGCN","rank_in_archive_order":18,"of":32,"metrics":{"1:1 Accuracy":"89.75 ± 6.37"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2101.00797","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}