{"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/heterogeneous-graph-attention-network","title":"Heterogeneous Graph Attention Network","arxiv_id":"1903.07293","date":"2019-03-18","proceeding":null,"authors":["Xiao Wang","Houye Ji","Chuan Shi","Bai Wang","Peng Cui","P. Yu","Yanfang Ye"],"abstract":"Graph neural network, as a powerful graph representation technique based on deep learning, has shown superior performance and attracted considerable research interest. However, it has not been fully considered in graph neural network for heterogeneous graph which contains different types of nodes and links. The heterogeneity and rich semantic information bring great challenges for designing a graph neural network for heterogeneous graph. Recently, one of the most exciting advancements in deep learning is the attention mechanism, whose great potential has been well demonstrated in various areas. In this paper, we first propose a novel heterogeneous graph neural network based on the hierarchical attention, including node-level and semantic-level attentions. Specifically, the node-level attention aims to learn the importance between a node and its metapath based neighbors, while the semantic-level attention is able to learn the importance of different meta-paths. With the learned importance from both node-level and semantic-level attention, the importance of node and meta-path can be fully considered. Then the proposed model can generate node embedding by aggregating features from meta-path based neighbors in a hierarchical manner. Extensive experimental results on three real-world heterogeneous graphs not only show the superior performance of our proposed model over the state-of-the-arts, but also demonstrate its potentially good interpretability for graph analysis.","url_abs":"https://arxiv.org/abs/1903.07293v1","url_pdf":"https://arxiv.org/pdf/1903.07293v1.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"heterogeneous-graph-attention-network","repo_url":"https://github.com/Jhy1993/HAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"heterogeneous-graph-attention-network","repo_url":"https://github.com/calderkatyal/CPSC483FinalProject","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"heterogeneous-graph-attention-network","repo_url":"https://github.com/JasonZhangzy1757/Heterogeneous-Graph-Attention-Network-HAN-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"heterogeneous-graph-attention-network","repo_url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/han","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/heterogeneous-node-classification-on-dblp-1","task":"Heterogeneous Node Classification","dataset":"DBLP (PACT) 14k","model":"HAN","rank_in_archive_order":1,"of":14,"metrics":{"Macro-F1 (20% training data)":"92.24%","Macro-F1 (60% training data)":"93.70%","Macro-F1 (80% training data)":"93.08%","Micro-F1 (20% training data)":"93.11%","Micro-F1 (80% training data)":"93.99%"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-dblp-1","task":"Heterogeneous Node Classification","dataset":"DBLP (PACT) 14k","model":"HAN (sem)","rank_in_archive_order":2,"of":14,"metrics":{"Macro-F1 (20% training data)":"92.03%","Macro-F1 (60% training data)":"93.31%","Macro-F1 (80% training data)":"92.53%","Micro-F1 (20% training data)":"92.99%","Micro-F1 (80% training data)":"93.29%"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-dblp-1","task":"Heterogeneous Node Classification","dataset":"DBLP (PACT) 14k","model":"ESim","rank_in_archive_order":3,"of":14,"metrics":{"Macro-F1 (20% training data)":"91.64%","Macro-F1 (60% training data)":"93.39%","Macro-F1 (80% training data)":"93.44%","Micro-F1 (20% training data)":"92.73%","Micro-F1 (80% training data)":"92.53%"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-dblp-1","task":"Heterogeneous Node Classification","dataset":"DBLP (PACT) 14k","model":"HERec","rank_in_archive_order":4,"of":14,"metrics":{"Macro-F1 (20% training data)":"91.68%","Macro-F1 (60% training data)":"93.70%","Macro-F1 (80% training data)":"92.34%","Micro-F1 (20% training data)":"92.69%","Micro-F1 (80% training data)":"93.27%"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-dblp-1","task":"Heterogeneous Node Classification","dataset":"DBLP (PACT) 14k","model":"HAN (nd)","rank_in_archive_order":5,"of":14,"metrics":{"Macro-F1 (20% training data)":"91.17%","Macro-F1 (60% training data)":"92.69%","Macro-F1 (80% training data)":"91.80%","Micro-F1 (20% training data)":"92.05%","Micro-F1 (80% training data)":"92.69%"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-dblp-1","task":"Heterogeneous Node Classification","dataset":"DBLP (PACT) 14k","model":"GAT","rank_in_archive_order":6,"of":14,"metrics":{"Macro-F1 (20% training data)":"90.97%","Macro-F1 (60% training data)":"91.84%","Macro-F1 (80% training data)":"91.73%","Micro-F1 (20% training data)":"91.96%","Micro-F1 (80% training data)":"92.55%"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-dblp-1","task":"Heterogeneous Node Classification","dataset":"DBLP (PACT) 14k","model":"GCN","rank_in_archive_order":8,"of":14,"metrics":{"Macro-F1 (20% training data)":"90.79%","Macro-F1 (60% training data)":"92.62%","Macro-F1 (80% training data)":"92.38%","Micro-F1 (20% training data)":"91.71%","Micro-F1 (80% training data)":"93.09%"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-dblp-1","task":"Heterogeneous Node Classification","dataset":"DBLP (PACT) 14k","model":"metapath2vec","rank_in_archive_order":9,"of":14,"metrics":{"Macro-F1 (20% training data)":"90.16%","Macro-F1 (60% training data)":"92.48%","Macro-F1 (80% training data)":"91.89%","Micro-F1 (20% training data)":"91.53%","Micro-F1 (80% training data)":"92.80%"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-dblp-1","task":"Heterogeneous Node Classification","dataset":"DBLP (PACT) 14k","model":"DeepWalk","rank_in_archive_order":11,"of":14,"metrics":{"Macro-F1 (20% training data)":"77.43%","Macro-F1 (60% training data)":"85.27%","Macro-F1 (80% training data)":"84.81%","Micro-F1 (20% training data)":"79.37%","Micro-F1 (80% training data)":"86.26%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.07293","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.07293"}},"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/Jhy1993/HAN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JasonZhangzy1757/Heterogeneous-Graph-Attention-Network-HAN-PyTorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/han","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/calderkatyal/CPSC483FinalProject","reach":{"status":"ok"}}],"summary":{"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"b32fd748b4bbe3bf","entry":"sample_mask","repo":"Jhy1993/HAN","repo_kind":"official","path":"ex_acm3025.py","file_url":"https://github.com/Jhy1993/HAN/blob/HEAD/ex_acm3025.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b32fd748b4bbe3bf"}},{"code_sha256_prefix":"b3a1e906834f9af2","entry":"merge_dgl_graphs","repo":"JasonZhangzy1757/Heterogeneous-Graph-Attention-Network-HAN-PyTorch","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/JasonZhangzy1757/Heterogeneous-Graph-Attention-Network-HAN-PyTorch/blob/HEAD/utils.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":"b3a1e906834f9af2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}