{"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/ultragcn-ultra-simplification-of-graph","title":"UltraGCN: Ultra Simplification of Graph Convolutional Networks for Recommendation","arxiv_id":"2110.15114","date":"2021-10-28","proceeding":null,"authors":["Kelong Mao","Jieming Zhu","Xi Xiao","Biao Lu","Zhaowei Wang","Xiuqiang He"],"abstract":"With the recent success of graph convolutional networks (GCNs), they have been widely applied for recommendation, and achieved impressive performance gains. The core of GCNs lies in its message passing mechanism to aggregate neighborhood information. However, we observed that message passing largely slows down the convergence of GCNs during training, especially for large-scale recommender systems, which hinders their wide adoption. LightGCN makes an early attempt to simplify GCNs for collaborative filtering by omitting feature transformations and nonlinear activations. In this paper, we take one step further to propose an ultra-simplified formulation of GCNs (dubbed UltraGCN), which skips infinite layers of message passing for efficient recommendation. Instead of explicit message passing, UltraGCN resorts to directly approximate the limit of infinite-layer graph convolutions via a constraint loss. Meanwhile, UltraGCN allows for more appropriate edge weight assignments and flexible adjustment of the relative importances among different types of relationships. This finally yields a simple yet effective UltraGCN model, which is easy to implement and efficient to train. Experimental results on four benchmark datasets show that UltraGCN not only outperforms the state-of-the-art GCN models but also achieves more than 10x speedup over LightGCN. Our source code will be available at https://reczoo.github.io/UltraGCN.","url_abs":"https://arxiv.org/abs/2110.15114v2","url_pdf":"https://arxiv.org/pdf/2110.15114v2.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":"ultragcn-ultra-simplification-of-graph","repo_url":"https://github.com/reczoo/RecZoo/tree/main/matching/gnn/UltraGCN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"ultragcn-ultra-simplification-of-graph","repo_url":"https://github.com/shuyao-wang/dsl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"collaborative-filtering","task_name":"Collaborative Filtering"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[{"method_slug":"gcn","method_name":"GCN"},{"method_slug":"lightgcn","method_name":"LightGCN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/collaborative-filtering-on-gowalla","task":"Collaborative Filtering","dataset":"Gowalla","model":"UltraGCN","rank_in_archive_order":7,"of":11,"metrics":{"NDCG@20":"0.1580","Recall@20":"0.1862"},"uses_additional_data":false},{"leaderboard":"/sota/collaborative-filtering-on-gowalla","task":"Collaborative Filtering","dataset":"Gowalla","model":"Emb-GCN","rank_in_archive_order":8,"of":11,"metrics":{"Recall@20":"0.1862"},"uses_additional_data":false},{"leaderboard":"/sota/collaborative-filtering-on-movielens-1m-1","task":"Collaborative Filtering","dataset":"MovieLens 1M","model":"UltraGCN","rank_in_archive_order":2,"of":4,"metrics":{"NDCG@20":"0.2642","Recall@20":"0.2787"},"uses_additional_data":false},{"leaderboard":"/sota/collaborative-filtering-on-yelp2018","task":"Collaborative Filtering","dataset":"Yelp2018","model":"UltraGCN","rank_in_archive_order":6,"of":9,"metrics":{"NDCG@20":"0.0561","Recall@20":"0.0683"},"uses_additional_data":false},{"leaderboard":"/sota/recommendation-systems-on-amazon-book","task":"Recommendation Systems","dataset":"Amazon-Book","model":"Emb-GCN","rank_in_archive_order":7,"of":16,"metrics":{"Recall@20":"0.0681","nDCG@20":"0.0556"},"uses_additional_data":false},{"leaderboard":"/sota/recommendation-systems-on-gowalla","task":"Recommendation Systems","dataset":"Gowalla","model":"Emb-GCN","rank_in_archive_order":6,"of":13,"metrics":{"Recall@20":"0.1862","nDCG@20":"0.1580"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.15114","atlas_url":"https://app.syntology.ai/?focus=2110.15114","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":"2110.15114"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2110.15114\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2110.15114"},"call":"get_concepts_for_paper(arxiv_id=\"2110.15114\")"}],"by_repo":[{"repo":"reczoo/RecZoo","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"shuyao-wang/dsl","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":"bda97ffedae387fae53383c1d5ed8a0bc96593491e5c636aa47fe1f2f3e4f961","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}