{"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/probabilistically-rewired-message-passing","title":"Probabilistically Rewired Message-Passing Neural Networks","arxiv_id":"2310.02156","date":"2023-10-03","proceeding":null,"authors":["Chendi Qian","Andrei Manolache","Kareem Ahmed","Zhe Zeng","Guy Van Den Broeck","Mathias Niepert","Christopher Morris"],"abstract":"Message-passing graph neural networks (MPNNs) emerged as powerful tools for processing graph-structured input. However, they operate on a fixed input graph structure, ignoring potential noise and missing information. Furthermore, their local aggregation mechanism can lead to problems such as over-squashing and limited expressive power in capturing relevant graph structures. Existing solutions to these challenges have primarily relied on heuristic methods, often disregarding the underlying data distribution. Hence, devising principled approaches for learning to infer graph structures relevant to the given prediction task remains an open challenge. In this work, leveraging recent progress in exact and differentiable $k$-subset sampling, we devise probabilistically rewired MPNNs (PR-MPNNs), which learn to add relevant edges while omitting less beneficial ones. For the first time, our theoretical analysis explores how PR-MPNNs enhance expressive power, and we identify precise conditions under which they outperform purely randomized approaches. Empirically, we demonstrate that our approach effectively mitigates issues like over-squashing and under-reaching. In addition, on established real-world datasets, our method exhibits competitive or superior predictive performance compared to traditional MPNN models and recent graph transformer architectures.","url_abs":"https://arxiv.org/abs/2310.02156v4","url_pdf":"https://arxiv.org/pdf/2310.02156v4.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":"probabilistically-rewired-message-passing","repo_url":"https://github.com/chendiqian/PR-MPNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"graph-transformer","method_name":"Graph Transformer"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"lapeigen","method_name":"LapEigen"},{"method_slug":"laplacian-pe","method_name":"Laplacian PE"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"mpnn","method_name":"MPNN"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.02156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02156"}},"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/chendiqian/PR-MPNN","reach":{"status":"ok"}}],"summary":{"ran":6,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"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":8,"samples":[{"code_sha256_prefix":"4f6577e25fe70103","entry":"batch_repeat_edge_index","repo":"chendiqian/PR-MPNN","repo_kind":"official","path":"models/rewire_utils.py","file_url":"https://github.com/chendiqian/PR-MPNN/blob/HEAD/models/rewire_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4f6577e25fe70103"}},{"code_sha256_prefix":"8905abdce603331c","entry":"entropy","repo":"chendiqian/PR-MPNN","repo_kind":"official","path":"models/aux_loss.py","file_url":"https://github.com/chendiqian/PR-MPNN/blob/HEAD/models/aux_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8905abdce603331c"}},{"code_sha256_prefix":"3200a255eeb1ff8e","entry":"get_degree_regularization","repo":"chendiqian/PR-MPNN","repo_kind":"official","path":"models/aux_loss.py","file_url":"https://github.com/chendiqian/PR-MPNN/blob/HEAD/models/aux_loss.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":"3200a255eeb1ff8e"}},{"code_sha256_prefix":"79ce4cc6a5dfbf15","entry":"get_variance_regularization","repo":"chendiqian/PR-MPNN","repo_kind":"official","path":"models/aux_loss.py","file_url":"https://github.com/chendiqian/PR-MPNN/blob/HEAD/models/aux_loss.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":"79ce4cc6a5dfbf15"}},{"code_sha256_prefix":"6628a2cd8c22a0cb","entry":"non_merge_coalesce","repo":"chendiqian/PR-MPNN","repo_kind":"official","path":"models/rewire_utils.py","file_url":"https://github.com/chendiqian/PR-MPNN/blob/HEAD/models/rewire_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":"6628a2cd8c22a0cb"}},{"code_sha256_prefix":"fbe819589c89fc7a","entry":"residual","repo":"chendiqian/PR-MPNN","repo_kind":"official","path":"models/my_convs.py","file_url":"https://github.com/chendiqian/PR-MPNN/blob/HEAD/models/my_convs.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fbe819589c89fc7a"}},{"code_sha256_prefix":"9547ff542f9823ef","entry":"create_exactly_k","repo":"chendiqian/PR-MPNN","repo_kind":"official","path":"simple/create_simple_constraint.py","file_url":"https://github.com/chendiqian/PR-MPNN/blob/HEAD/simple/create_simple_constraint.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":"9547ff542f9823ef"}},{"code_sha256_prefix":"773ead944e34af17","entry":"lookup_node","repo":"chendiqian/PR-MPNN","repo_kind":"official","path":"simple/create_simple_constraint.py","file_url":"https://github.com/chendiqian/PR-MPNN/blob/HEAD/simple/create_simple_constraint.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":"773ead944e34af17"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}