{"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/oversquashing-in-gnns-through-the-lens-of","title":"Oversquashing in GNNs through the lens of information contraction and graph expansion","arxiv_id":"2208.03471","date":"2022-08-06","proceeding":null,"authors":["Pradeep Kr. Banerjee","Kedar Karhadkar","Yu Guang Wang","Uri Alon","Guido Montúfar"],"abstract":"The quality of signal propagation in message-passing graph neural networks (GNNs) strongly influences their expressivity as has been observed in recent works. In particular, for prediction tasks relying on long-range interactions, recursive aggregation of node features can lead to an undesired phenomenon called \"oversquashing\". We present a framework for analyzing oversquashing based on information contraction. Our analysis is guided by a model of reliable computation due to von Neumann that lends a new insight into oversquashing as signal quenching in noisy computation graphs. Building on this, we propose a graph rewiring algorithm aimed at alleviating oversquashing. Our algorithm employs a random local edge flip primitive motivated by an expander graph construction. We compare the spectral expansion properties of our algorithm with that of an existing curvature-based non-local rewiring strategy. Synthetic experiments show that while our algorithm in general has a slower rate of expansion, it is overall computationally cheaper, preserves the node degrees exactly and never disconnects the graph.","url_abs":"https://arxiv.org/abs/2208.03471v1","url_pdf":"https://arxiv.org/pdf/2208.03471v1.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":"oversquashing-in-gnns-through-the-lens-of","repo_url":"https://github.com/kedar2/oversquashing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-construction","task_name":"graph construction"}],"methods":[{"method_slug":"flip","method_name":"FLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.03471","atlas_url":"https://app.syntology.ai/?focus=2208.03471","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.03471"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/kedar2/oversquashing","reach":null}],"summary":{"ran_honours":3},"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":"0423eb8145c21250","entry":"dumbbell_graph","repo":"kedar2/oversquashing","repo_kind":"official","path":"plots.py","file_url":"https://github.com/kedar2/oversquashing/blob/HEAD/plots.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0423eb8145c21250"}},{"code_sha256_prefix":"d1eaf95fa58f88b5","entry":"path_of_cliques","repo":"kedar2/oversquashing","repo_kind":"official","path":"plots.py","file_url":"https://github.com/kedar2/oversquashing/blob/HEAD/plots.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d1eaf95fa58f88b5"}},{"code_sha256_prefix":"6ccc7b1f23c4c552","entry":"ring_of_cliques","repo":"kedar2/oversquashing","repo_kind":"official","path":"plots.py","file_url":"https://github.com/kedar2/oversquashing/blob/HEAD/plots.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ccc7b1f23c4c552"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}