{"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/long-range-dependency-based-multi-layer","title":"Long-range Meta-path Search on Large-scale Heterogeneous Graphs","arxiv_id":"2307.08430","date":"2023-07-17","proceeding":null,"authors":["Chao Li","Zijie Guo","Qiuting He","Hao Xu","Kun He"],"abstract":"Utilizing long-range dependency, a concept extensively studied in homogeneous graphs, remains underexplored in heterogeneous graphs, especially on large ones, posing two significant challenges: Reducing computational costs while maximizing effective information utilization in the presence of heterogeneity, and overcoming the over-smoothing issue in graph neural networks. To address this gap, we investigate the importance of different meta-paths and introduce an automatic framework for utilizing long-range dependency on heterogeneous graphs, denoted as Long-range Meta-path Search through Progressive Sampling (LMSPS). Specifically, we develop a search space with all meta-paths related to the target node type. By employing a progressive sampling algorithm, LMSPS dynamically shrinks the search space with hop-independent time complexity. Through a sampling evaluation strategy, LMSPS conducts a specialized and effective meta-path selection, leading to retraining with only effective meta-paths, thus mitigating costs and over-smoothing. Extensive experiments across diverse heterogeneous datasets validate LMSPS's capability in discovering effective long-range meta-paths, surpassing state-of-the-art methods. Our code is available at https://github.com/JHL-HUST/LMSPS.","url_abs":"https://arxiv.org/abs/2307.08430v6","url_pdf":"https://arxiv.org/pdf/2307.08430v6.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":"long-range-dependency-based-multi-layer","repo_url":"https://github.com/jhl-hust/ldmlp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"long-range-dependency-based-multi-layer","repo_url":"https://github.com/jhl-hust/lmsps","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"long-range-dependency-based-multi-layer","repo_url":"https://github.com/JHL-HUST/LDMLP/tree/main/ogbn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"long-range-dependency-based-multi-layer","repo_url":"https://github.com/JHL-HUST/LMSPS/tree/main/ogbn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"node-property-prediction","task_name":"Node Property Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-property-prediction-on-ogbn-mag","task":"Node Property Prediction","dataset":"ogbn-mag","model":"LMSPS (w/o embs)","rank_in_archive_order":4,"of":39,"metrics":{"Ext. data":"No","Number of params":"16470044","Test Accuracy":"0.5784 ± 0.0022","Validation Accuracy":"0.5951 ± 0.0007"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-mag","task":"Node Property Prediction","dataset":"ogbn-mag","model":"LMSPS(w/o ComplEx embs)","rank_in_archive_order":6,"of":39,"metrics":{"Ext. data":"No","Number of params":"16470044","Test Accuracy":"0.5767 ± 0.0015","Validation Accuracy":"0.5902 ± 0.0016"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-mag","task":"Node Property Prediction","dataset":"ogbn-mag","model":"LDMLP(w/o ComplEx embs)","rank_in_archive_order":9,"of":39,"metrics":{"Ext. data":"No","Number of params":"13177884","Test Accuracy":"0.5739 ± 0.0012","Validation Accuracy":"0.5888 ± 0.0015"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2307.08430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08430"}},"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/jhl-hust/lmsps","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JHL-HUST/LDMLP/tree/main/ogbn","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jhl-hust/ldmlp","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JHL-HUST/LMSPS/tree/main/ogbn","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"bdd10a0559cd9f67","entry":"evaluator","repo":"jhl-hust/ldmlp","repo_kind":"official","path":"hgb/utils.py","file_url":"https://github.com/jhl-hust/ldmlp/blob/HEAD/hgb/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bdd10a0559cd9f67"}},{"code_sha256_prefix":"76cefceaf1693dd9","entry":"infer_eval","repo":"jhl-hust/ldmlp","repo_kind":"official","path":"hgb/utils.py","file_url":"https://github.com/jhl-hust/ldmlp/blob/HEAD/hgb/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"76cefceaf1693dd9"}},{"code_sha256_prefix":"6e0ca78e6b055583","entry":"project_op","repo":"jhl-hust/ldmlp","repo_kind":"official","path":"hgb/utils.py","file_url":"https://github.com/jhl-hust/ldmlp/blob/HEAD/hgb/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6e0ca78e6b055583"}},{"code_sha256_prefix":"8eb64db85c51b748","entry":"parse_args","repo":"jhl-hust/ldmlp","repo_kind":"official","path":"hgb/main_path.py","file_url":"https://github.com/jhl-hust/ldmlp/blob/HEAD/hgb/main_path.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":"8eb64db85c51b748"}},{"code_sha256_prefix":"d3e41752dea9554e","entry":"parse_args","repo":"jhl-hust/ldmlp","repo_kind":"official","path":"hgb/train_search.py","file_url":"https://github.com/jhl-hust/ldmlp/blob/HEAD/hgb/train_search.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":"d3e41752dea9554e"}},{"code_sha256_prefix":"87498f3a0ca6b721","entry":"parse_args","repo":"jhl-hust/ldmlp","repo_kind":"official","path":"ogbn/main_path.py","file_url":"https://github.com/jhl-hust/ldmlp/blob/HEAD/ogbn/main_path.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":"87498f3a0ca6b721"}},{"code_sha256_prefix":"423bc5659e28c499","entry":"parse_args","repo":"jhl-hust/ldmlp","repo_kind":"official","path":"ogbn/main_path_nested.py","file_url":"https://github.com/jhl-hust/ldmlp/blob/HEAD/ogbn/main_path_nested.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":"423bc5659e28c499"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}