{"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/towards-quantifying-long-range-interactions","title":"Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement","arxiv_id":"2503.09008","date":"2025-03-12","proceeding":null,"authors":["Huidong Liang","Haitz Sáez de Ocáriz Borde","Baskaran Sripathmanathan","Michael Bronstein","Xiaowen Dong"],"abstract":"Long-range dependencies are critical for effective graph representation learning, yet most existing datasets focus on small graphs tailored to inductive tasks, offering limited insight into long-range interactions. Current evaluations primarily compare models employing global attention (e.g., graph transformers) with those using local neighborhood aggregation (e.g., message-passing neural networks) without a direct measurement of long-range dependency. In this work, we introduce City-Networks, a novel large-scale transductive learning dataset derived from real-world city roads. This dataset features graphs with over $10^5$ nodes and significantly larger diameters than those in existing benchmarks, naturally embodying long-range information. We annotate the graphs using an eccentricity-based approach, ensuring that the classification task inherently requires information from distant nodes. Furthermore, we propose a model-agnostic measurement based on the Jacobians of neighbors from distant hops, offering a principled quantification of long-range dependencies. Finally, we provide theoretical justifications for both our dataset design and the proposed measurement - particularly by focusing on over-smoothing and influence score dilution - which establishes a robust foundation for further exploration of long-range interactions in graph neural networks.","url_abs":"https://arxiv.org/abs/2503.09008v1","url_pdf":"https://arxiv.org/pdf/2503.09008v1.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":"towards-quantifying-long-range-interactions","repo_url":"https://github.com/leonresearch/city-networks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-representation-learning","task_name":"Graph Representation Learning"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"transductive-learning","task_name":"Transductive Learning"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[{"slug":"city-networks","name":"City-Networks","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-log-angeles","task":"Node Classification","dataset":"Log Angeles","model":"ChebNet","rank_in_archive_order":2,"of":5,"metrics":{"Average Top-1 Accuracy":"54.1 ± 0.2"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-log-angeles","task":"Node Classification","dataset":"Log Angeles","model":"GraphSAGE","rank_in_archive_order":3,"of":5,"metrics":{"Average Top-1 Accuracy":"53.3 ± 0.7"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-log-angeles","task":"Node Classification","dataset":"Log Angeles","model":"SGFormer","rank_in_archive_order":4,"of":5,"metrics":{"Average Top-1 Accuracy":"47.2 ± 0.5"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-log-angeles","task":"Node Classification","dataset":"Log Angeles","model":"GCN","rank_in_archive_order":5,"of":5,"metrics":{"Average Top-1 Accuracy":"45.9 ± 1.0"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-london","task":"Node Classification","dataset":"London","model":"ChebNet","rank_in_archive_order":2,"of":5,"metrics":{"Average Top-1 Accuracy":"49.4 ± 0.4"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-london","task":"Node Classification","dataset":"London","model":"GraphSAGE","rank_in_archive_order":3,"of":5,"metrics":{"Average Top-1 Accuracy":"48.2 ± 0.8"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-london","task":"Node Classification","dataset":"London","model":"SGFormer","rank_in_archive_order":4,"of":5,"metrics":{"Average Top-1 Accuracy":"45.7 ± 0.3"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-london","task":"Node Classification","dataset":"London","model":"GCN","rank_in_archive_order":5,"of":5,"metrics":{"Average Top-1 Accuracy":"43.8 ± 0.3"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-paris","task":"Node Classification","dataset":"Paris","model":"ChebNet","rank_in_archive_order":2,"of":5,"metrics":{"Average Top-1 Accuracy":"49.5  ± 0.4"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-paris","task":"Node Classification","dataset":"Paris","model":"GraphSAGE","rank_in_archive_order":3,"of":5,"metrics":{"Average Top-1 Accuracy":"49.1 ± 0.6"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-paris","task":"Node Classification","dataset":"Paris","model":"GCN","rank_in_archive_order":4,"of":5,"metrics":{"Average Top-1 Accuracy":"47.3 ± 0.2"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-paris","task":"Node Classification","dataset":"Paris","model":"SGFormer","rank_in_archive_order":5,"of":5,"metrics":{"Average Top-1 Accuracy":"45.0 ± 0.2"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-shanghai","task":"Node Classification","dataset":"Shanghai","model":"GraphSAGE","rank_in_archive_order":2,"of":5,"metrics":{"Average Top-1 Accuracy":"60.4 ± 0.3"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-shanghai","task":"Node Classification","dataset":"Shanghai","model":"ChebNet","rank_in_archive_order":3,"of":5,"metrics":{"Average Top-1 Accuracy":"57.9 ± 1.4"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-shanghai","task":"Node Classification","dataset":"Shanghai","model":"SGFormer","rank_in_archive_order":4,"of":5,"metrics":{"Average Top-1 Accuracy":"53.5 ± 0.3"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-shanghai","task":"Node Classification","dataset":"Shanghai","model":"GCN","rank_in_archive_order":5,"of":5,"metrics":{"Average Top-1 Accuracy":"52.4  ± 0.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.09008","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09008"}},"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":"deterministic:regex_extraction","url":"https://github.com/LeonResearch/City-Networks","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leonresearch/city-networks","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran_fixture":2},"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":"3fcb47df1cd821d3","entry":"jacobian_l1","repo":"leonresearch/city-networks","repo_kind":"official","path":"influence/influence.py","file_url":"https://github.com/leonresearch/city-networks/blob/HEAD/influence/influence.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3fcb47df1cd821d3"}},{"code_sha256_prefix":"c7329955ef54debb","entry":"k_hop_subsets_exact","repo":"leonresearch/city-networks","repo_kind":"official","path":"influence/influence.py","file_url":"https://github.com/leonresearch/city-networks/blob/HEAD/influence/influence.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c7329955ef54debb"}},{"code_sha256_prefix":"d69d53cccdbbd6ad","entry":"k_hop_subsets_rough","repo":"leonresearch/city-networks","repo_kind":"official","path":"influence/influence.py","file_url":"https://github.com/leonresearch/city-networks/blob/HEAD/influence/influence.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d69d53cccdbbd6ad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}