{"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/edge-directionality-improves-learning-on","title":"Edge Directionality Improves Learning on Heterophilic Graphs","arxiv_id":"2305.10498","date":"2023-05-17","proceeding":null,"authors":["Emanuele Rossi","Bertrand Charpentier","Francesco Di Giovanni","Fabrizio Frasca","Stephan Günnemann","Michael Bronstein"],"abstract":"Graph Neural Networks (GNNs) have become the de-facto standard tool for modeling relational data. However, while many real-world graphs are directed, the majority of today's GNN models discard this information altogether by simply making the graph undirected. The reasons for this are historical: 1) many early variants of spectral GNNs explicitly required undirected graphs, and 2) the first benchmarks on homophilic graphs did not find significant gain from using direction. In this paper, we show that in heterophilic settings, treating the graph as directed increases the effective homophily of the graph, suggesting a potential gain from the correct use of directionality information. To this end, we introduce Directed Graph Neural Network (Dir-GNN), a novel general framework for deep learning on directed graphs. Dir-GNN can be used to extend any Message Passing Neural Network (MPNN) to account for edge directionality information by performing separate aggregations of the incoming and outgoing edges. We prove that Dir-GNN matches the expressivity of the Directed Weisfeiler-Lehman test, exceeding that of conventional MPNNs. In extensive experiments, we validate that while our framework leaves performance unchanged on homophilic datasets, it leads to large gains over base models such as GCN, GAT and GraphSage on heterophilic benchmarks, outperforming much more complex methods and achieving new state-of-the-art results.","url_abs":"https://arxiv.org/abs/2305.10498v3","url_pdf":"https://arxiv.org/pdf/2305.10498v3.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":"edge-directionality-improves-learning-on","repo_url":"https://github.com/emalgorithm/directed-graph-neural-network","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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"}],"methods":[{"method_slug":"gat","method_name":"GAT"},{"method_slug":"gcn","method_name":"GCN"},{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"},{"method_slug":"graphsage","method_name":"GraphSAGE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-chameleon","task":"Node Classification","dataset":"Chameleon","model":"Dir-GNN","rank_in_archive_order":3,"of":61,"metrics":{"Accuracy":"79.71±1.26"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel","task":"Node Classification","dataset":"Squirrel","model":"Dir-GNN","rank_in_archive_order":3,"of":59,"metrics":{"Accuracy":"75.31±1.92"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-arxiv-year","task":"Node Classification","dataset":"arXiv-year","model":"Dir-GNN","rank_in_archive_order":3,"of":12,"metrics":{"Accuracy":"64.08±0.26"},"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":"Dir-GNN","rank_in_archive_order":2,"of":29,"metrics":{"1:1 Accuracy":"79.71±1.26"},"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":"Dir-GNN","rank_in_archive_order":2,"of":29,"metrics":{"1:1 Accuracy":"75.31±1.92"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.10498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10498"}},"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/emalgorithm/directed-graph-neural-network","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"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":0,"samples":[{"code_sha256_prefix":"aa7b67adc8e742a7","entry":"even_quantile_labels","repo":"emalgorithm/directed-graph-neural-network","repo_kind":"official","path":"src/utils/third_party.py","file_url":"https://github.com/emalgorithm/directed-graph-neural-network/blob/HEAD/src/utils/third_party.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa7b67adc8e742a7"}},{"code_sha256_prefix":"3c3affd0e729d7f6","entry":"generate_synthetic_directed_pa_graph","repo":"emalgorithm/directed-graph-neural-network","repo_kind":"official","path":"src/datasets/synthetic.py","file_url":"https://github.com/emalgorithm/directed-graph-neural-network/blob/HEAD/src/datasets/synthetic.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c3affd0e729d7f6"}},{"code_sha256_prefix":"921807f811fcb94a","entry":"process_fixed_splits","repo":"emalgorithm/directed-graph-neural-network","repo_kind":"official","path":"src/utils/third_party.py","file_url":"https://github.com/emalgorithm/directed-graph-neural-network/blob/HEAD/src/utils/third_party.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"921807f811fcb94a"}},{"code_sha256_prefix":"1b4e100d3857a49a","entry":"node_class_split","repo":"emalgorithm/directed-graph-neural-network","repo_kind":"official","path":"src/datasets/telegram.py","file_url":"https://github.com/emalgorithm/directed-graph-neural-network/blob/HEAD/src/datasets/telegram.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1b4e100d3857a49a"}},{"code_sha256_prefix":"7c6099619413280b","entry":"use_best_hyperparams","repo":"emalgorithm/directed-graph-neural-network","repo_kind":"official","path":"src/utils/utils.py","file_url":"https://github.com/emalgorithm/directed-graph-neural-network/blob/HEAD/src/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7c6099619413280b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}