{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/weisfeiler-and-lehman-go-cellular-cw-networks","title":"Weisfeiler and Lehman Go Cellular: CW Networks","arxiv_id":"2106.12575","date":"2021-06-23","proceeding":"NeurIPS 2021 12","authors":["Cristian Bodnar","Fabrizio Frasca","Nina Otter","Yu Guang Wang","Pietro Liò","Guido Montúfar","Michael Bronstein"],"abstract":"Graph Neural Networks (GNNs) are limited in their expressive power, struggle with long-range interactions and lack a principled way to model higher-order structures. These problems can be attributed to the strong coupling between the computational graph and the input graph structure. The recently proposed Message Passing Simplicial Networks naturally decouple these elements by performing message passing on the clique complex of the graph. Nevertheless, these models can be severely constrained by the rigid combinatorial structure of Simplicial Complexes (SCs). In this work, we extend recent theoretical results on SCs to regular Cell Complexes, topological objects that flexibly subsume SCs and graphs. We show that this generalisation provides a powerful set of graph \"lifting\" transformations, each leading to a unique hierarchical message passing procedure. The resulting methods, which we collectively call CW Networks (CWNs), are strictly more powerful than the WL test and not less powerful than the 3-WL test. In particular, we demonstrate the effectiveness of one such scheme, based on rings, when applied to molecular graph problems. The proposed architecture benefits from provably larger expressivity than commonly used GNNs, principled modelling of higher-order signals and from compressing the distances between nodes. We demonstrate that our model achieves state-of-the-art results on a variety of molecular datasets.","url_abs":"https://arxiv.org/abs/2106.12575v3","url_pdf":"https://arxiv.org/pdf/2106.12575v3.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":"weisfeiler-and-lehman-go-cellular-cw-networks","repo_url":"https://github.com/twitter-research/cwn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"weisfeiler-and-lehman-go-cellular-cw-networks","repo_url":"https://github.com/josefhoppe/cwn-random-ccs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-property-prediction","task_name":"Graph Property Prediction"},{"task_slug":"graph-regression","task_name":"Graph Regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-csl","task":"Graph Classification","dataset":"CSL","model":"CIN","rank_in_archive_order":1,"of":1,"metrics":{"Acc":"1"},"uses_additional_data":false},{"leaderboard":"/sota/graph-property-prediction-on-ogbg-molhiv","task":"Graph Property Prediction","dataset":"ogbg-molhiv","model":"CIN","rank_in_archive_order":10,"of":43,"metrics":{"Ext. data":"No","Number of params":"239745","Test ROC-AUC":"0.8094 ± 0.0057","Validation ROC-AUC":"0.8277 ± 0.0099"},"uses_additional_data":false},{"leaderboard":"/sota/graph-property-prediction-on-ogbg-molhiv","task":"Graph Property Prediction","dataset":"ogbg-molhiv","model":"CIN-small","rank_in_archive_order":14,"of":43,"metrics":{"Ext. data":"No","Number of params":"138337","Test ROC-AUC":"0.8055 ± 0.0104","Validation ROC-AUC":"0.8310 ± 0.0102"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-zinc","task":"Graph Regression","dataset":"ZINC","model":"CIN","rank_in_archive_order":16,"of":27,"metrics":{"MAE":"0.079"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-zinc","task":"Graph Regression","dataset":"ZINC","model":"CIN-small","rank_in_archive_order":19,"of":27,"metrics":{"MAE":"0.094"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-zinc-100k","task":"Graph Regression","dataset":"ZINC 100k","model":"CIN-small","rank_in_archive_order":1,"of":8,"metrics":{"MAE":"0.094"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-zinc-500k","task":"Graph Regression","dataset":"ZINC-500k","model":"CIN","rank_in_archive_order":15,"of":36,"metrics":{"MAE":"0.079"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-zinc-500k","task":"Graph Regression","dataset":"ZINC-500k","model":"CIN-small","rank_in_archive_order":19,"of":36,"metrics":{"MAE":"0.094"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.12575","atlas_url":"https://app.syntology.ai/?focus=2106.12575","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2106.12575"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2106.12575\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2106.12575"},"call":"get_concepts_for_paper(arxiv_id=\"2106.12575\")"}],"by_repo":[{"repo":"twitter-research/cwn","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"josefhoppe/cwn-random-ccs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f76eeadfafafca0a330fe89873adce6ba01b374eb95a2bb4807b9dda597a030c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}