{"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/mixhop-higher-order-graph-convolution","title":"MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing","arxiv_id":"1905.00067","date":"2019-04-30","proceeding":null,"authors":["Sami Abu-El-Haija","Bryan Perozzi","Amol Kapoor","Nazanin Alipourfard","Kristina Lerman","Hrayr Harutyunyan","Greg Ver Steeg","Aram Galstyan"],"abstract":"Existing popular methods for semi-supervised learning with Graph Neural Networks (such as the Graph Convolutional Network) provably cannot learn a general class of neighborhood mixing relationships. To address this weakness, we propose a new model, MixHop, that can learn these relationships, including difference operators, by repeatedly mixing feature representations of neighbors at various distances. Mixhop requires no additional memory or computational complexity, and outperforms on challenging baselines. In addition, we propose sparsity regularization that allows us to visualize how the network prioritizes neighborhood information across different graph datasets. Our analysis of the learned architectures reveals that neighborhood mixing varies per datasets.","url_abs":"https://arxiv.org/abs/1905.00067v3","url_pdf":"https://arxiv.org/pdf/1905.00067v3.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":"mixhop-higher-order-graph-convolution","repo_url":"https://github.com/samihaija/mixhop","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"mixhop-higher-order-graph-convolution","repo_url":"https://github.com/benedekrozemberczki/MixHop-and-N-GCN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"mixhop-higher-order-graph-convolution","repo_url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/mixhop","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-actor","task":"Node Classification","dataset":"Actor","model":"MixHop","rank_in_archive_order":54,"of":62,"metrics":{"Accuracy":"32.22 ± 2.34"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon","task":"Node Classification","dataset":"Chameleon","model":"MixHop","rank_in_archive_order":51,"of":61,"metrics":{"Accuracy":"60.50 ± 2.53"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon-60-20-20","task":"Node Classification","dataset":"Chameleon (60%/20%/20% random splits)","model":"MixHop","rank_in_archive_order":38,"of":38,"metrics":{"1:1 Accuracy":"36.28 ± 10.22"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-60-20-20","task":"Node Classification","dataset":"CiteSeer (60%/20%/20% random splits)","model":"MixHop","rank_in_archive_order":33,"of":33,"metrics":{"1:1 Accuracy":"49.52 ± 13.35"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer","task":"Node Classification","dataset":"Citeseer","model":"MixHop","rank_in_archive_order":54,"of":71,"metrics":{"Accuracy":"71.4%","Training Split":"20 per node","Validation":"YES"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-48-32-20","task":"Node Classification","dataset":"Citeseer (48%/32%/20% fixed splits)","model":"MixHop","rank_in_archive_order":20,"of":26,"metrics":{"1:1 Accuracy":"76.26 ± 1.33"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora","task":"Node Classification","dataset":"Cora","model":"MixHop","rank_in_archive_order":58,"of":73,"metrics":{"Accuracy":"81.9%","Training Split":"20 per node","Validation":"YES"},"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":"MixHop","rank_in_archive_order":17,"of":26,"metrics":{"1:1 Accuracy":"87.61 ± 0.85"},"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":"MixHop","rank_in_archive_order":33,"of":33,"metrics":{"1:1 Accuracy":"65.65 ± 11.31"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell","task":"Node Classification","dataset":"Cornell","model":"MixHop","rank_in_archive_order":48,"of":60,"metrics":{"Accuracy":"73.51 ± 6.34"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell-60-20-20","task":"Node Classification","dataset":"Cornell (60%/20%/20% random splits)","model":"MixHop","rank_in_archive_order":36,"of":36,"metrics":{"1:1 Accuracy":"60.33 ± 28.53"},"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":"MixHop","rank_in_archive_order":32,"of":37,"metrics":{"1:1 Accuracy":"33.13 ± 2.40"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-penn94","task":"Node Classification","dataset":"Penn94","model":"MixHop","rank_in_archive_order":13,"of":32,"metrics":{"Accuracy":"83.47 ± 0.71"},"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":"MixHop","rank_in_archive_order":25,"of":26,"metrics":{"1:1 Accuracy":"85.31 ± 0.61"},"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":"MixHop","rank_in_archive_order":30,"of":37,"metrics":{"1:1 Accuracy":"87.04 ± 4.10"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"MixHop","rank_in_archive_order":31,"of":70,"metrics":{"Accuracy":"80.8%","Training Split":"20 per node","Validation":"YES"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel","task":"Node Classification","dataset":"Squirrel","model":"MixHop","rank_in_archive_order":48,"of":59,"metrics":{"Accuracy":"43.80 ± 1.48"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel-60-20-20","task":"Node Classification","dataset":"Squirrel (60%/20%/20% random splits)","model":"MixHop","rank_in_archive_order":37,"of":37,"metrics":{"1:1 Accuracy":"24.55 ± 2.60"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas","task":"Node Classification","dataset":"Texas","model":"MixHop","rank_in_archive_order":51,"of":62,"metrics":{"Accuracy":"77.84 ± 7.73"},"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":"MixHop","rank_in_archive_order":33,"of":36,"metrics":{"1:1 Accuracy":"76.39 ± 7.66"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin","task":"Node Classification","dataset":"Wisconsin","model":"MixHop","rank_in_archive_order":55,"of":63,"metrics":{"Accuracy":"75.88 ± 4.90"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin-60-20-20","task":"Node Classification","dataset":"Wisconsin (60%/20%/20% random splits)","model":"MixHop","rank_in_archive_order":25,"of":35,"metrics":{"1:1 Accuracy":"77.25 ± 7.80"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-genius","task":"Node Classification","dataset":"genius","model":"MixHop","rank_in_archive_order":10,"of":26,"metrics":{"Accuracy":"90.58 ± 0.16"},"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":"MixHop","rank_in_archive_order":24,"of":29,"metrics":{"1:1 Accuracy":"60.50 ± 2.53 "},"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":"MixHop","rank_in_archive_order":32,"of":32,"metrics":{"1:1 Accuracy":"36.28 ± 10.22"},"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":"MixHop","rank_in_archive_order":24,"of":27,"metrics":{"1:1 Accuracy":"73.51 ± 6.34 "},"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":"MixHop","rank_in_archive_order":33,"of":33,"metrics":{"1:1 Accuracy":"60.33 ± 28.53"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-6","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Deezer-Europe","model":"MixHop","rank_in_archive_order":11,"of":28,"metrics":{"1:1 Accuracy":"66.80±0.58"},"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":"MixHop","rank_in_archive_order":23,"of":26,"metrics":{"1:1 Accuracy":"32.22 ± 2.34"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-13","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Penn94","model":"MixHop","rank_in_archive_order":8,"of":28,"metrics":{"1:1 Accuracy":"83.47 ± 0.71"},"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":"MixHop","rank_in_archive_order":23,"of":29,"metrics":{"1:1 Accuracy":" 43.80 ± 1.48 "},"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":"MixHop","rank_in_archive_order":20,"of":26,"metrics":{"1:1 Accuracy":"77.84 ± 7.73 "},"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":"MixHop","rank_in_archive_order":30,"of":32,"metrics":{"1:1 Accuracy":"76.39 ± 7.66"},"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":"MixHop","rank_in_archive_order":22,"of":26,"metrics":{"1:1 Accuracy":"75.88 ± 4.90 "},"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":"MixHop","rank_in_archive_order":22,"of":32,"metrics":{"1:1 Accuracy":"77.25 ± 7.80"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-14","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"genius","model":"MixHop","rank_in_archive_order":12,"of":26,"metrics":{"1:1 Accuracy":"90.58 ± 0.16"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-15","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"twitch-gamers","model":"MixHop","rank_in_archive_order":10,"of":26,"metrics":{"1:1 Accuracy":"65.64 ± 0.27"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.00067","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}