{"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/improving-the-effective-receptive-field-of","title":"Improving the Effective Receptive Field of Message-Passing Neural Networks","arxiv_id":"2505.23185","date":"2025-05-29","proceeding":null,"authors":["Shahaf E. Finder","Ron Shapira Weber","Moshe Eliasof","Oren Freifeld","Eran Treister"],"abstract":"Message-Passing Neural Networks (MPNNs) have become a cornerstone for processing and analyzing graph-structured data. However, their effectiveness is often hindered by phenomena such as over-squashing, where long-range dependencies or interactions are inadequately captured and expressed in the MPNN output. This limitation mirrors the challenges of the Effective Receptive Field (ERF) in Convolutional Neural Networks (CNNs), where the theoretical receptive field is underutilized in practice. In this work, we show and theoretically explain the limited ERF problem in MPNNs. Furthermore, inspired by recent advances in ERF augmentation for CNNs, we propose an Interleaved Multiscale Message-Passing Neural Networks (IM-MPNN) architecture to address these problems in MPNNs. Our method incorporates a hierarchical coarsening of the graph, enabling message-passing across multiscale representations and facilitating long-range interactions without excessive depth or parameterization. Through extensive evaluations on benchmarks such as the Long-Range Graph Benchmark (LRGB), we demonstrate substantial improvements over baseline MPNNs in capturing long-range dependencies while maintaining computational efficiency.","url_abs":"https://arxiv.org/abs/2505.23185v1","url_pdf":"https://arxiv.org/pdf/2505.23185v1.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":"improving-the-effective-receptive-field-of","repo_url":"https://github.com/bgu-cs-vil/im-mpnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-regression","task_name":"Graph Regression"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[{"method_slug":"mpnn","method_name":"MPNN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-coco-sp","task":"Node Classification","dataset":"COCO-SP","model":"IM-GatedGCN","rank_in_archive_order":5,"of":19,"metrics":{"macro F1":"0.3501 ± 0.0061"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-coco-sp","task":"Node Classification","dataset":"COCO-SP","model":"IM-GCN","rank_in_archive_order":15,"of":19,"metrics":{"macro F1":"0.1960 ± 0.0023"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-log-angeles","task":"Node Classification","dataset":"Log Angeles","model":"IM-GCN","rank_in_archive_order":1,"of":5,"metrics":{"Average Top-1 Accuracy":"62.4 ± 0.3"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-london","task":"Node Classification","dataset":"London","model":"IM-GCN","rank_in_archive_order":1,"of":5,"metrics":{"Average Top-1 Accuracy":"58.9 ± 0.1"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-paris","task":"Node Classification","dataset":"Paris","model":"IM-GCN","rank_in_archive_order":1,"of":5,"metrics":{"Average Top-1 Accuracy":"55.3  ± 0.3"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pascalvoc-sp-1","task":"Node Classification","dataset":"PascalVOC-SP","model":"IM-GatedGCN","rank_in_archive_order":4,"of":21,"metrics":{"macro F1":"0.4332 ± 0.0078"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pascalvoc-sp-1","task":"Node Classification","dataset":"PascalVOC-SP","model":"IM-GCN","rank_in_archive_order":13,"of":21,"metrics":{"macro F1":"0.2929 ± 0.0058"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-shanghai","task":"Node Classification","dataset":"Shanghai","model":"IM-GCN","rank_in_archive_order":1,"of":5,"metrics":{"Average Top-1 Accuracy":"67.8 ± 0.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.23185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23185"}},"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/bgu-cs-vil/im-mpnn","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"b8c2e5edac5472b4","entry":"compute_dataset_stats","repo":"bgu-cs-vil/im-mpnn","repo_kind":"official","path":"main_city_networks.py","file_url":"https://github.com/bgu-cs-vil/im-mpnn/blob/HEAD/main_city_networks.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b8c2e5edac5472b4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}