{"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/joint-adaptive-feature-smoothing-and-topology","title":"Adaptive Universal Generalized PageRank Graph Neural Network","arxiv_id":"2006.07988","date":"2020-06-14","proceeding":"ICLR 2021 1","authors":["Eli Chien","Jianhao Peng","Pan Li","Olgica Milenkovic"],"abstract":"In many important graph data processing applications the acquired information includes both node features and observations of the graph topology. Graph neural networks (GNNs) are designed to exploit both sources of evidence but they do not optimally trade-off their utility and integrate them in a manner that is also universal. Here, universality refers to independence on homophily or heterophily graph assumptions. We address these issues by introducing a new Generalized PageRank (GPR) GNN architecture that adaptively learns the GPR weights so as to jointly optimize node feature and topological information extraction, regardless of the extent to which the node labels are homophilic or heterophilic. Learned GPR weights automatically adjust to the node label pattern, irrelevant on the type of initialization, and thereby guarantee excellent learning performance for label patterns that are usually hard to handle. Furthermore, they allow one to avoid feature over-smoothing, a process which renders feature information nondiscriminative, without requiring the network to be shallow. Our accompanying theoretical analysis of the GPR-GNN method is facilitated by novel synthetic benchmark datasets generated by the so-called contextual stochastic block model. We also compare the performance of our GNN architecture with that of several state-of-the-art GNNs on the problem of node-classification, using well-known benchmark homophilic and heterophilic datasets. The results demonstrate that GPR-GNN offers significant performance improvement compared to existing techniques on both synthetic and benchmark data.","url_abs":"https://arxiv.org/abs/2006.07988v6","url_pdf":"https://arxiv.org/pdf/2006.07988v6.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":"joint-adaptive-feature-smoothing-and-topology","repo_url":"https://github.com/jianhao2016/GPRGNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"gpr","task_name":"GPR"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"node-classification-on-non-homophilic","task_name":"Node Classification on Non-Homophilic (Heterophilic) Graphs"},{"task_slug":"stochastic-block-model","task_name":"Stochastic Block Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-actor","task":"Node Classification","dataset":"Actor","model":"GPRGCN","rank_in_archive_order":47,"of":62,"metrics":{"Accuracy":"35.16 ± 0.9"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon","task":"Node Classification","dataset":"Chameleon","model":"GPRGCN","rank_in_archive_order":49,"of":61,"metrics":{"Accuracy":"62.59 ± 2.04"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon-60-20-20","task":"Node Classification","dataset":"Chameleon (60%/20%/20% random splits)","model":"GPRGNN","rank_in_archive_order":15,"of":38,"metrics":{"1:1 Accuracy":"67.48 ±  0.40"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-60-20-20","task":"Node Classification","dataset":"CiteSeer (60%/20%/20% random splits)","model":"GPRGNN","rank_in_archive_order":31,"of":33,"metrics":{"1:1 Accuracy":"67.63 ± 0.38"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-48-32-20","task":"Node Classification","dataset":"Citeseer (48%/32%/20% fixed splits)","model":"GPRGCN","rank_in_archive_order":11,"of":26,"metrics":{"1:1 Accuracy":"77.13 ± 1.67"},"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":"GPRGCN","rank_in_archive_order":13,"of":26,"metrics":{"1:1 Accuracy":"87.95 ± 1.18"},"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":"GPRGNN","rank_in_archive_order":29,"of":33,"metrics":{"1:1 Accuracy":"79.51 ± 0.36"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell","task":"Node Classification","dataset":"Cornell","model":"GPRGCN","rank_in_archive_order":43,"of":60,"metrics":{"Accuracy":"78.11 ± 6.55"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell-60-20-20","task":"Node Classification","dataset":"Cornell (60%/20%/20% random splits)","model":"GPRGNN","rank_in_archive_order":17,"of":36,"metrics":{"1:1 Accuracy":"91.36 ± 0.70"},"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":"GPRGNN","rank_in_archive_order":21,"of":37,"metrics":{"1:1 Accuracy":"39.30 ± 0.27"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-penn94","task":"Node Classification","dataset":"Penn94","model":"GPRGCN","rank_in_archive_order":20,"of":32,"metrics":{"Accuracy":"81.38 ±  0.16"},"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":"GPRGCN","rank_in_archive_order":24,"of":26,"metrics":{"1:1 Accuracy":"87.54 ± 0.38"},"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":"GPRGNN","rank_in_archive_order":35,"of":37,"metrics":{"1:1 Accuracy":"85.07 ± 0.09"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel","task":"Node Classification","dataset":"Squirrel","model":"GPRGCN","rank_in_archive_order":44,"of":59,"metrics":{"Accuracy":"46.31 ± 2.46"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel-60-20-20","task":"Node Classification","dataset":"Squirrel (60%/20%/20% random splits)","model":"GPRGNN","rank_in_archive_order":15,"of":37,"metrics":{"1:1 Accuracy":"49.93 ± 0.53"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas","task":"Node Classification","dataset":"Texas","model":"GPRGCN","rank_in_archive_order":48,"of":62,"metrics":{"Accuracy":"81.35 ± 5.32"},"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":"GPRGNN","rank_in_archive_order":15,"of":36,"metrics":{"1:1 Accuracy":"92.92 ± 0.61"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin","task":"Node Classification","dataset":"Wisconsin","model":"GPRGCN","rank_in_archive_order":48,"of":63,"metrics":{"Accuracy":"82.55 ± 6.23"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin-60-20-20","task":"Node Classification","dataset":"Wisconsin (60%/20%/20% random splits)","model":"GPRGNN","rank_in_archive_order":15,"of":35,"metrics":{"1:1 Accuracy":"93.75 ± 2.37"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-genius","task":"Node Classification","dataset":"genius","model":"GPRGCN","rank_in_archive_order":12,"of":26,"metrics":{"Accuracy":"90.05 ± 0.31"},"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":"GPRGCN","rank_in_archive_order":23,"of":29,"metrics":{"1:1 Accuracy":"62.59 ± 2.04"},"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":"GPRGNN","rank_in_archive_order":12,"of":32,"metrics":{"1:1 Accuracy":"67.48 ±  0.40"},"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":"GPRGCN","rank_in_archive_order":20,"of":27,"metrics":{"1:1 Accuracy":"78.11 ± 6.55"},"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":"GPRGNN","rank_in_archive_order":17,"of":33,"metrics":{"1:1 Accuracy":"91.36 ± 0.70"},"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":"MLP-2","rank_in_archive_order":18,"of":33,"metrics":{"1:1 Accuracy":"91.30 ± 0.70"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-6","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Deezer-Europe","model":"GPRGNN","rank_in_archive_order":9,"of":28,"metrics":{"1:1 Accuracy":"66.90±0.50"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-13","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Penn94","model":"GPRGCN","rank_in_archive_order":15,"of":28,"metrics":{"1:1 Accuracy":"81.38 ± 0.16"},"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":"GPRGCN","rank_in_archive_order":21,"of":29,"metrics":{"1:1 Accuracy":"46.31 ± 2.46"},"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":"GPRGCN","rank_in_archive_order":19,"of":26,"metrics":{"1:1 Accuracy":"81.35 ± 5.32"},"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":"GPRGNN","rank_in_archive_order":14,"of":32,"metrics":{"1:1 Accuracy":"92.92 ± 0.61"},"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":"MLP-2","rank_in_archive_order":16,"of":32,"metrics":{"1:1 Accuracy":"92.26 ± 0.71"},"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":"GPRGCN","rank_in_archive_order":19,"of":26,"metrics":{"1:1 Accuracy":"82.55 ± 6.23"},"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":"GPRGNN","rank_in_archive_order":15,"of":32,"metrics":{"1:1 Accuracy":"93.75 ± 2.37"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-14","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"genius","model":"GPRGCN","rank_in_archive_order":14,"of":26,"metrics":{"1:1 Accuracy":"90.05 ± 0.31"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-15","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"twitch-gamers","model":"GPRGCN","rank_in_archive_order":21,"of":26,"metrics":{"1:1 Accuracy":"61.89 ± 0.29"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.07988","atlas_url":"https://app.syntology.ai/?focus=2006.07988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07988"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jianhao2016/GPRGNN","reach":{"status":"ok"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"ddcec3dc58a4763f","entry":"GPRGNN","repo":"jianhao2016/gprgnn","repo_kind":"official","path":"src/GNN_models.py","file_url":"https://github.com/jianhao2016/gprgnn/blob/HEAD/src/GNN_models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ddcec3dc58a4763f"}},{"code_sha256_prefix":"82499cce1427e40b","entry":"GPR_prop","repo":"jianhao2016/gprgnn","repo_kind":"official","path":"src/GNN_models.py","file_url":"https://github.com/jianhao2016/gprgnn/blob/HEAD/src/GNN_models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"82499cce1427e40b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}