{"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/non-local-graph-neural-networks","title":"Non-Local Graph Neural Networks","arxiv_id":"2005.14612","date":"2020-05-29","proceeding":null,"authors":["Meng Liu","Zhengyang Wang","Shuiwang Ji"],"abstract":"Modern graph neural networks (GNNs) learn node embeddings through multilayer local aggregation and achieve great success in applications on assortative graphs. However, tasks on disassortative graphs usually require non-local aggregation. In addition, we find that local aggregation is even harmful for some disassortative graphs. In this work, we propose a simple yet effective non-local aggregation framework with an efficient attention-guided sorting for GNNs. Based on it, we develop various non-local GNNs. We perform thorough experiments to analyze disassortative graph datasets and evaluate our non-local GNNs. Experimental results demonstrate that our non-local GNNs significantly outperform previous state-of-the-art methods on seven benchmark datasets of disassortative graphs, in terms of both model performance and efficiency.","url_abs":"https://arxiv.org/abs/2005.14612v2","url_pdf":"https://arxiv.org/pdf/2005.14612v2.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":"non-local-graph-neural-networks","repo_url":"https://github.com/divelab/Non-Local-GNN","is_official":1,"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":"NLMLP","rank_in_archive_order":13,"of":62,"metrics":{"Accuracy":"37.9 ± 1.3"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-actor","task":"Node Classification","dataset":"Actor","model":"NLGCN","rank_in_archive_order":57,"of":62,"metrics":{"Accuracy":"31.6 ± 1.0"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-actor","task":"Node Classification","dataset":"Actor","model":"NLGAT","rank_in_archive_order":59,"of":62,"metrics":{"Accuracy":"29.5 ± 1.3"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon","task":"Node Classification","dataset":"Chameleon","model":"NLGCN","rank_in_archive_order":29,"of":61,"metrics":{"Accuracy":"70.1 ± 2.9"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon","task":"Node Classification","dataset":"Chameleon","model":"NLGAT","rank_in_archive_order":43,"of":61,"metrics":{"Accuracy":"65.7 ± 1.4"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon","task":"Node Classification","dataset":"Chameleon","model":"NLMLP","rank_in_archive_order":58,"of":61,"metrics":{"Accuracy":"50.7 ± 2.2"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-48-32-20","task":"Node Classification","dataset":"Citeseer (48%/32%/20% fixed splits)","model":"NLGAT","rank_in_archive_order":21,"of":26,"metrics":{"1:1 Accuracy":"76.2 ± 1.6"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-48-32-20","task":"Node Classification","dataset":"Citeseer (48%/32%/20% fixed splits)","model":"NLGCN","rank_in_archive_order":22,"of":26,"metrics":{"1:1 Accuracy":"75.2 ± 1.4"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-48-32-20","task":"Node Classification","dataset":"Citeseer (48%/32%/20% fixed splits)","model":"NLMLP","rank_in_archive_order":24,"of":26,"metrics":{"1:1 Accuracy":"73.4 ± 1.9"},"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":"NLGAT","rank_in_archive_order":1,"of":26,"metrics":{"1:1 Accuracy":"88.5 ± 1.8"},"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":"NLGCN","rank_in_archive_order":9,"of":26,"metrics":{"1:1 Accuracy":"88.1 ± 1.0"},"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":"NLMLP","rank_in_archive_order":25,"of":26,"metrics":{"1:1 Accuracy":"76.9 ± 1.8"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell","task":"Node Classification","dataset":"Cornell","model":"NLMLP","rank_in_archive_order":25,"of":60,"metrics":{"Accuracy":"84.9 ± 5.7"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell","task":"Node Classification","dataset":"Cornell","model":"NLGCN","rank_in_archive_order":55,"of":60,"metrics":{"Accuracy":"57.6 ± 5.5"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell","task":"Node Classification","dataset":"Cornell","model":"NLGAT","rank_in_archive_order":58,"of":60,"metrics":{"Accuracy":"54.7 ±  7.6"},"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":"NLGCN","rank_in_archive_order":17,"of":26,"metrics":{"1:1 Accuracy":"89.0 ± 0.5"},"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":"NLMLP","rank_in_archive_order":20,"of":26,"metrics":{"1:1 Accuracy":"88.2 ± 0.5"},"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":"NLGAT","rank_in_archive_order":21,"of":26,"metrics":{"1:1 Accuracy":"88.2 ± 0.3"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel","task":"Node Classification","dataset":"Squirrel","model":"NLGCN","rank_in_archive_order":27,"of":59,"metrics":{"Accuracy":"59.0 ± 1.2"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel","task":"Node Classification","dataset":"Squirrel","model":"NLGAT","rank_in_archive_order":32,"of":59,"metrics":{"Accuracy":"56.8 ± 2.5"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel","task":"Node Classification","dataset":"Squirrel","model":"NLMLP","rank_in_archive_order":55,"of":59,"metrics":{"Accuracy":"33.7 ± 1.5"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas","task":"Node Classification","dataset":"Texas","model":"NLMLP","rank_in_archive_order":29,"of":62,"metrics":{"Accuracy":"85.4 ± 3.8"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas","task":"Node Classification","dataset":"Texas","model":"NLGCN","rank_in_archive_order":57,"of":62,"metrics":{"Accuracy":"65.5 ± 6.6"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas","task":"Node Classification","dataset":"Texas","model":"NLGAT","rank_in_archive_order":59,"of":62,"metrics":{"Accuracy":"62.6 ± 7.1"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin","task":"Node Classification","dataset":"Wisconsin","model":"NLMLP","rank_in_archive_order":30,"of":63,"metrics":{"Accuracy":"87.3 ± 4.3"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin","task":"Node Classification","dataset":"Wisconsin","model":"NLGCN","rank_in_archive_order":59,"of":63,"metrics":{"Accuracy":"60.2 ± 5.3"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin","task":"Node Classification","dataset":"Wisconsin","model":"NLGAT","rank_in_archive_order":61,"of":63,"metrics":{"Accuracy":"56.9 ± 7.3"},"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":"NLGCN","rank_in_archive_order":11,"of":29,"metrics":{"1:1 Accuracy":"70.1 ± 2.9"},"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":"NLGAT","rank_in_archive_order":19,"of":29,"metrics":{"1:1 Accuracy":"65.7 ± 1.4"},"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":"NLMLP","rank_in_archive_order":28,"of":29,"metrics":{"1:1 Accuracy":"50.7 ± 2.2"},"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":"NLMLP","rank_in_archive_order":12,"of":27,"metrics":{"1:1 Accuracy":"84.9 ± 5.7"},"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":"NLGCN","rank_in_archive_order":26,"of":27,"metrics":{"1:1 Accuracy":"57.6 ± 5.5"},"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":"NLGAT","rank_in_archive_order":27,"of":27,"metrics":{"1:1 Accuracy":"54.7 ± 7.6"},"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":"NLMLP","rank_in_archive_order":1,"of":26,"metrics":{"1:1 Accuracy":"37.9 ± 1.3"},"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":"NLGCN","rank_in_archive_order":24,"of":26,"metrics":{"1:1 Accuracy":"31.6 ± 1.0"},"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":"NLGAT","rank_in_archive_order":26,"of":26,"metrics":{"1:1 Accuracy":"29.5 ± 1.3"},"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":"NLGCN","rank_in_archive_order":10,"of":29,"metrics":{"1:1 Accuracy":"59.0 ± 1.2"},"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":"NLGAT","rank_in_archive_order":13,"of":29,"metrics":{"1:1 Accuracy":"56.8 ± 2.5"},"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":"NLMLP","rank_in_archive_order":28,"of":29,"metrics":{"1:1 Accuracy":"33.7 ± 1.5"},"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":"NLMLP","rank_in_archive_order":9,"of":26,"metrics":{"1:1 Accuracy":"85.4 ± 3.8"},"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":"NLGCN","rank_in_archive_order":25,"of":26,"metrics":{"1:1 Accuracy":"65.5 ± 6.6"},"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":"NLGAT","rank_in_archive_order":26,"of":26,"metrics":{"1:1 Accuracy":"62.6 ± 7.1"},"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":"NLMLP","rank_in_archive_order":12,"of":26,"metrics":{"1:1 Accuracy":"87.3 ± 4.3 "},"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":"NLGCN","rank_in_archive_order":25,"of":26,"metrics":{"1:1 Accuracy":"60.2 ± 5.3 "},"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":"NLGAT","rank_in_archive_order":26,"of":26,"metrics":{"1:1 Accuracy":"56.9 ± 7.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.14612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14612"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/divelab/Non-Local-GNN","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"da80a2b9fd449bd2","entry":"index_to_mask","repo":"divelab/Non-Local-GNN","repo_kind":"official","path":"NLGNN/src/train_eval.py","file_url":"https://github.com/divelab/Non-Local-GNN/blob/HEAD/NLGNN/src/train_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"da80a2b9fd449bd2"}},{"code_sha256_prefix":"ca063eb1dc48ac9f","entry":"random_disassortative_splits","repo":"divelab/Non-Local-GNN","repo_kind":"official","path":"NLGNN/src/train_eval.py","file_url":"https://github.com/divelab/Non-Local-GNN/blob/HEAD/NLGNN/src/train_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"ca063eb1dc48ac9f"}},{"code_sha256_prefix":"12f00e9b50fb314f","entry":"random_planetoid_splits","repo":"divelab/Non-Local-GNN","repo_kind":"official","path":"NLGNN/src/train_eval.py","file_url":"https://github.com/divelab/Non-Local-GNN/blob/HEAD/NLGNN/src/train_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"12f00e9b50fb314f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}