{"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/gread-graph-neural-reaction-diffusion","title":"GREAD: Graph Neural Reaction-Diffusion Networks","arxiv_id":"2211.14208","date":"2022-11-25","proceeding":null,"authors":["Jeongwhan Choi","Seoyoung Hong","Noseong Park","Sung-Bae Cho"],"abstract":"Graph neural networks (GNNs) are one of the most popular research topics for deep learning. GNN methods typically have been designed on top of the graph signal processing theory. In particular, diffusion equations have been widely used for designing the core processing layer of GNNs, and therefore they are inevitably vulnerable to the notorious oversmoothing problem. Recently, a couple of papers paid attention to reaction equations in conjunctions with diffusion equations. However, they all consider limited forms of reaction equations. To this end, we present a reaction-diffusion equation-based GNN method that considers all popular types of reaction equations in addition to one special reaction equation designed by us. To our knowledge, our paper is one of the most comprehensive studies on reaction-diffusion equation-based GNNs. In our experiments with 9 datasets and 28 baselines, our method, called GREAD, outperforms them in a majority of cases. Further synthetic data experiments show that it mitigates the oversmoothing problem and works well for various homophily rates.","url_abs":"https://arxiv.org/abs/2211.14208v3","url_pdf":"https://arxiv.org/pdf/2211.14208v3.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":"gread-graph-neural-reaction-diffusion","repo_url":"https://github.com/jeongwhanchoi/gread","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"gcn","method_name":"GCN"},{"method_slug":"node","method_name":"NODE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-chameleon-48-32-20","task":"Node Classification","dataset":"Chameleon (48%/32%/20% fixed splits)","model":"GREAD-BS","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"67.98"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-48-32-20","task":"Node Classification","dataset":"Citeseer (48%/32%/20% fixed splits)","model":"GREAD-BS","rank_in_archive_order":26,"of":26,"metrics":{"Accuracy":"77.53"},"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":"GREAD-BS","rank_in_archive_order":26,"of":26,"metrics":{"Accuracy":"88.39"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell-48-32-20-fixed","task":"Node Classification","dataset":"Cornell (48%/32%/20% fixed splits)","model":"GREAD-AC","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"87.03"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell-48-32-20-fixed","task":"Node Classification","dataset":"Cornell (48%/32%/20% fixed splits)","model":"GREAD-BS","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"86.22"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell-48-32-20-fixed","task":"Node Classification","dataset":"Cornell (48%/32%/20% fixed splits)","model":"GREAD-F","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy":"85.41"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-film-48-32-20-fixed","task":"Node Classification","dataset":"Film(48%/32%/20% fixed splits)","model":"GREAD-BS","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"37.49"},"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":"GREAD-BS","rank_in_archive_order":26,"of":26,"metrics":{"Accuracy":"90.21"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel-48-32-20","task":"Node Classification","dataset":"Squirrel (48%/32%/20% fixed splits)","model":"GREAD-BS","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"51.01"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas-48-32-20-fixed","task":"Node Classification","dataset":"Texas (48%/32%/20% fixed splits)","model":"GREAD-F","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"88.11"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas-48-32-20-fixed","task":"Node Classification","dataset":"Texas (48%/32%/20% fixed splits)","model":"GREAD-BS","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"87.57"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin-48-32-20","task":"Node Classification","dataset":"Wisconsin (48%/32%/20% fixed splits)","model":"GREAD-BS","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"88.04"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin-48-32-20","task":"Node Classification","dataset":"Wisconsin (48%/32%/20% fixed splits)","model":"GREAD-F","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"86.47"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.14208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.14208"}},"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/jeongwhanchoi/gread","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":3,"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":3,"samples":[{"code_sha256_prefix":"2ca430b1c5874d57","entry":"add_labels","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"2ca430b1c5874d57"}},{"code_sha256_prefix":"5198723f26aa8e49","entry":"get_label_masks","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"5198723f26aa8e49"}},{"code_sha256_prefix":"dab3444777a2e6c7","entry":"get_optimizer","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"dab3444777a2e6c7"}},{"code_sha256_prefix":"34b68102305cf124","entry":"compute_enegry_evolution","repo":"jeongwhanchoi/gread","repo_kind":"official","path":"src/base_classes.py","file_url":"https://github.com/jeongwhanchoi/gread/blob/HEAD/src/base_classes.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"34b68102305cf124"}},{"code_sha256_prefix":"c68140584cc0e991","entry":"get_component","repo":"jeongwhanchoi/gread","repo_kind":"official","path":"src/data.py","file_url":"https://github.com/jeongwhanchoi/gread/blob/HEAD/src/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c68140584cc0e991"}},{"code_sha256_prefix":"5d74f163186ed970","entry":"hetero_params","repo":"jeongwhanchoi/gread","repo_kind":"official","path":"src/gread_params.py","file_url":"https://github.com/jeongwhanchoi/gread/blob/HEAD/src/gread_params.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5d74f163186ed970"}},{"code_sha256_prefix":"78ac42cc931414c2","entry":"run_evaluator","repo":"jeongwhanchoi/gread","repo_kind":"official","path":"src/early_stop_solver.py","file_url":"https://github.com/jeongwhanchoi/gread/blob/HEAD/src/early_stop_solver.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"78ac42cc931414c2"}},{"code_sha256_prefix":"9258a750860491c6","entry":"shared_grand_params","repo":"jeongwhanchoi/gread","repo_kind":"official","path":"src/gread_params.py","file_url":"https://github.com/jeongwhanchoi/gread/blob/HEAD/src/gread_params.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9258a750860491c6"}},{"code_sha256_prefix":"b55b354d7bbb6311","entry":"shared_gread_params","repo":"jeongwhanchoi/gread","repo_kind":"official","path":"src/gread_params.py","file_url":"https://github.com/jeongwhanchoi/gread/blob/HEAD/src/gread_params.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b55b354d7bbb6311"}},{"code_sha256_prefix":"bc4f44e9386e89e5","entry":"threshold_mat","repo":"jeongwhanchoi/gread","repo_kind":"official","path":"src/distances_kNN.py","file_url":"https://github.com/jeongwhanchoi/gread/blob/HEAD/src/distances_kNN.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bc4f44e9386e89e5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}