{"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/why-is-normalization-necessary-for-linear","title":"Why is Normalization Necessary for Linear Recommenders?","arxiv_id":"2504.05805","date":"2025-04-08","proceeding":null,"authors":["Seongmin Park","Mincheol Yoon","Hye-Young Kim","Jongwuk Lee"],"abstract":"Despite their simplicity, linear autoencoder (LAE)-based models have shown comparable or even better performance with faster inference speed than neural recommender models. However, LAEs face two critical challenges: (i) popularity bias, which tends to recommend popular items, and (ii) neighborhood bias, which overly focuses on capturing local item correlations. To address these issues, this paper first analyzes the effect of two existing normalization methods for LAEs, i.e., random-walk and symmetric normalization. Our theoretical analysis reveals that normalization highly affects the degree of popularity and neighborhood biases among items. Inspired by this analysis, we propose a versatile normalization solution, called Data-Adaptive Normalization (DAN), which flexibly controls the popularity and neighborhood biases by adjusting item- and user-side normalization to align with unique dataset characteristics. Owing to its model-agnostic property, DAN can be easily applied to various LAE-based models. Experimental results show that DAN-equipped LAEs consistently improve existing LAE-based models across six benchmark datasets, with significant gains of up to 128.57% and 12.36% for long-tail items and unbiased evaluations, respectively. Refer to our code in https://github.com/psm1206/DAN.","url_abs":"https://arxiv.org/abs/2504.05805v2","url_pdf":"https://arxiv.org/pdf/2504.05805v2.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":"why-is-normalization-necessary-for-linear","repo_url":"https://github.com/psm1206/dan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"collaborative-filtering","task_name":"Collaborative Filtering"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/collaborative-filtering-on-amazon-book","task":"Collaborative Filtering","dataset":"Amazon-Book","model":"RLAE-DAN","rank_in_archive_order":2,"of":6,"metrics":{"NDCG@20":"0.0630","Recall@20":"0.0762"},"uses_additional_data":false},{"leaderboard":"/sota/collaborative-filtering-on-gowalla","task":"Collaborative Filtering","dataset":"Gowalla","model":"RLAE-DAN","rank_in_archive_order":1,"of":11,"metrics":{"NDCG@20":"0.1605","Recall@20":"0.1922"},"uses_additional_data":false},{"leaderboard":"/sota/collaborative-filtering-on-yelp2018","task":"Collaborative Filtering","dataset":"Yelp2018","model":"RLAE-DAN","rank_in_archive_order":3,"of":9,"metrics":{"NDCG@20":"0.0587","Recall@20":"0.0706"},"uses_additional_data":false},{"leaderboard":"/sota/recommendation-systems-on-amazon-book","task":"Recommendation Systems","dataset":"Amazon-Book","model":"RLAE-DAN","rank_in_archive_order":3,"of":16,"metrics":{"Recall@20":"0.0762","nDCG@20":"0.0630"},"uses_additional_data":false},{"leaderboard":"/sota/recommendation-systems-on-gowalla","task":"Recommendation Systems","dataset":"Gowalla","model":"RLAE-DAN","rank_in_archive_order":3,"of":13,"metrics":{"Recall@20":"0.1922","nDCG@20":"0.1605"},"uses_additional_data":false},{"leaderboard":"/sota/recommendation-systems-on-yelp2018","task":"Recommendation Systems","dataset":"Yelp2018","model":"RLAE-DAN","rank_in_archive_order":3,"of":11,"metrics":{"NDCG@20":"0.0587","Recall@20":"0.0706"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"psm1206/dan","kind":"official","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":"d5ec3c04723c686e0206485dd3e917f9b8252e74ea2dc0be9e5783dd71076ec9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}