{"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/simplifying-the-theory-on-over-smoothing","title":"Simplifying the Theory on Over-Smoothing","arxiv_id":"2407.11876","date":"2024-07-16","proceeding":null,"authors":["Andreas Roth"],"abstract":"Graph convolutions have gained popularity due to their ability to efficiently operate on data with an irregular geometric structure. However, graph convolutions cause over-smoothing, which refers to representations becoming more similar with increased depth. However, many different definitions and intuitions currently coexist, leading to research efforts focusing on incompatible directions. This paper attempts to align these directions by showing that over-smoothing is merely a special case of power iteration. This greatly simplifies the existing theory on over-smoothing, making it more accessible. Based on the theory, we provide a novel comprehensive definition of rank collapse as a generalized form of over-smoothing and introduce the rank-one distance as a corresponding metric. Our empirical evaluation of 14 commonly used methods shows that more models than were previously known suffer from this issue.","url_abs":"https://arxiv.org/abs/2407.11876v2","url_pdf":"https://arxiv.org/pdf/2407.11876v2.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":"simplifying-the-theory-on-over-smoothing","repo_url":"https://github.com/roth-andreas/simplifying-over-smoothing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.11876","atlas_url":"https://app.syntology.ai/?focus=2407.11876","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11876"}},"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/roth-andreas/simplifying-over-smoothing","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"d09b85daa9c46610","entry":"dirichlet_energy","repo":"roth-andreas/simplifying-over-smoothing","repo_kind":"official","path":"models/models.py","file_url":"https://github.com/roth-andreas/simplifying-over-smoothing/blob/HEAD/models/models.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":"d09b85daa9c46610"}},{"code_sha256_prefix":"9a29dcab8c683964","entry":"get_data","repo":"roth-andreas/simplifying-over-smoothing","repo_kind":"official","path":"plot_all.py","file_url":"https://github.com/roth-andreas/simplifying-over-smoothing/blob/HEAD/plot_all.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":"9a29dcab8c683964"}},{"code_sha256_prefix":"be99db31acb1a2ef","entry":"rank_diff","repo":"roth-andreas/simplifying-over-smoothing","repo_kind":"official","path":"models/models.py","file_url":"https://github.com/roth-andreas/simplifying-over-smoothing/blob/HEAD/models/models.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":"be99db31acb1a2ef"}},{"code_sha256_prefix":"8ae8a5b920821a87","entry":"gcn_norm","repo":"roth-andreas/simplifying-over-smoothing","repo_kind":"official","path":"models/SumAggregation.py","file_url":"https://github.com/roth-andreas/simplifying-over-smoothing/blob/HEAD/models/SumAggregation.py","link_basis":"harvester_set","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":"8ae8a5b920821a87"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}