{"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/infinite-recommendation-networks-a-data","title":"Infinite Recommendation Networks: A Data-Centric Approach","arxiv_id":"2206.02626","date":"2022-06-03","proceeding":null,"authors":["Noveen Sachdeva","Mehak Preet Dhaliwal","Carole-Jean Wu","Julian McAuley"],"abstract":"We leverage the Neural Tangent Kernel and its equivalence to training infinitely-wide neural networks to devise $\\infty$-AE: an autoencoder with infinitely-wide bottleneck layers. The outcome is a highly expressive yet simplistic recommendation model with a single hyper-parameter and a closed-form solution. Leveraging $\\infty$-AE's simplicity, we also develop Distill-CF for synthesizing tiny, high-fidelity data summaries which distill the most important knowledge from the extremely large and sparse user-item interaction matrix for efficient and accurate subsequent data-usage like model training, inference, architecture search, etc. This takes a data-centric approach to recommendation, where we aim to improve the quality of logged user-feedback data for subsequent modeling, independent of the learning algorithm. We particularly utilize the concept of differentiable Gumbel-sampling to handle the inherent data heterogeneity, sparsity, and semi-structuredness, while being scalable to datasets with hundreds of millions of user-item interactions. Both of our proposed approaches significantly outperform their respective state-of-the-art and when used together, we observe 96-105% of $\\infty$-AE's performance on the full dataset with as little as 0.1% of the original dataset size, leading us to explore the counter-intuitive question: Is more data what you need for better recommendation?","url_abs":"https://arxiv.org/abs/2206.02626v3","url_pdf":"https://arxiv.org/pdf/2206.02626v3.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":"infinite-recommendation-networks-a-data","repo_url":"https://github.com/noveens/distill_cf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"infinite-recommendation-networks-a-data","repo_url":"https://github.com/noveens/infinite_ae_cf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"infinite-recommendation-networks-a-data","repo_url":"https://github.com/AmazingDD/daisyRec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"infinite-recommendation-networks-a-data","repo_url":"https://github.com/Guang000/Awesome-Dataset-Distillation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"infinite-recommendation-networks-a-data","repo_url":"https://github.com/recsys-benchmark/daisyrec-v2.0","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[{"method_slug":"ntk","method_name":"NTK"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/collaborative-filtering-on-douban","task":"Recommendation Systems","dataset":"Douban","model":"∞-AE","rank_in_archive_order":7,"of":7,"metrics":{"AUC":"0.9523","HR@10":"0.2356","HR@100":"0.2837","PSP@10":"0.0128","nDCG@10":"0.2494","nDCG@100":"0.2326"},"uses_additional_data":false},{"leaderboard":"/sota/collaborative-filtering-on-movielens-1m","task":"Recommendation Systems","dataset":"MovieLens 1M","model":"∞-AE","rank_in_archive_order":24,"of":31,"metrics":{"HR@10":"0.3151","HR@100":"0.6005","PSP@10":"0.0322","nDCG@10":"0.3282","nDCG@100":"0.4253"},"uses_additional_data":false},{"leaderboard":"/sota/collaborative-filtering-on-netflix","task":"Recommendation Systems","dataset":"Netflix","model":"∞-AE","rank_in_archive_order":7,"of":10,"metrics":{"AUC":"0.9728","PSP@10":"0.0375","Recall@10":"0.2969","Recall@100":"0.5088","nDCG@10":"0.3059","nDCG@100":"0.3659"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.02626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.02626"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/noveens/infinite_ae_cf","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Guang000/Awesome-Dataset-Distillation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/recsys-benchmark/daisyrec-v2.0","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AmazingDD/daisyRec","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/noveens/distill_cf","reach":null}],"summary":{"ran":4,"ran_fixture":1,"ran_draft_wrong":1,"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":3,"repositories":2},"listed":{"samples":6,"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":0,"samples":[{"code_sha256_prefix":"44e9a7fc60c3de3c","entry":"BPRLoss","repo":"AmazingDD/daisyRec","repo_kind":"listed","path":"daisy/model/EASERecommender.py","file_url":"https://github.com/AmazingDD/daisyRec/blob/HEAD/daisy/model/EASERecommender.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"44e9a7fc60c3de3c"}},{"code_sha256_prefix":"1e23ad42f13d3766","entry":"HingeLoss","repo":"AmazingDD/daisyRec","repo_kind":"listed","path":"daisy/model/EASERecommender.py","file_url":"https://github.com/AmazingDD/daisyRec/blob/HEAD/daisy/model/EASERecommender.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1e23ad42f13d3766"}},{"code_sha256_prefix":"4819c6d8b7646571","entry":"TOP1Loss","repo":"AmazingDD/daisyRec","repo_kind":"listed","path":"daisy/model/EASERecommender.py","file_url":"https://github.com/AmazingDD/daisyRec/blob/HEAD/daisy/model/EASERecommender.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4819c6d8b7646571"}},{"code_sha256_prefix":"39c4594180be0c7c","entry":"get_item_propensity","repo":"noveens/infinite_ae_cf","repo_kind":"official","path":"utils.py","file_url":"https://github.com/noveens/infinite_ae_cf/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39c4594180be0c7c"}},{"code_sha256_prefix":"0030ec204abad735","entry":"get_update_functions","repo":"noveens/distill_cf","repo_kind":"official","path":"distill.py","file_url":"https://github.com/noveens/distill_cf/blob/HEAD/distill.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0030ec204abad735"}},{"code_sha256_prefix":"ba82c8f5022469d4","entry":"initialize","repo":"noveens/distill_cf","repo_kind":"official","path":"distill.py","file_url":"https://github.com/noveens/distill_cf/blob/HEAD/distill.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ba82c8f5022469d4"}},{"code_sha256_prefix":"56616f78c00e1103","entry":"AbstractRecommender","repo":"AmazingDD/daisyRec","repo_kind":"listed","path":"daisy/model/EASERecommender.py","file_url":"https://github.com/AmazingDD/daisyRec/blob/HEAD/daisy/model/EASERecommender.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"56616f78c00e1103"}},{"code_sha256_prefix":"bfd5c06502832fdf","entry":"EASE","repo":"AmazingDD/daisyRec","repo_kind":"listed","path":"daisy/model/EASERecommender.py","file_url":"https://github.com/AmazingDD/daisyRec/blob/HEAD/daisy/model/EASERecommender.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bfd5c06502832fdf"}},{"code_sha256_prefix":"695d9cfdcb0be46e","entry":"GeneralRecommender","repo":"AmazingDD/daisyRec","repo_kind":"listed","path":"daisy/model/EASERecommender.py","file_url":"https://github.com/AmazingDD/daisyRec/blob/HEAD/daisy/model/EASERecommender.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"695d9cfdcb0be46e"}},{"code_sha256_prefix":"3ab0f054172cf3f8","entry":"get_common_path","repo":"noveens/infinite_ae_cf","repo_kind":"official","path":"utils.py","file_url":"https://github.com/noveens/infinite_ae_cf/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ab0f054172cf3f8"}},{"code_sha256_prefix":"dc1e506d9e302f57","entry":"get_item_count_map","repo":"noveens/infinite_ae_cf","repo_kind":"official","path":"utils.py","file_url":"https://github.com/noveens/infinite_ae_cf/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dc1e506d9e302f57"}},{"code_sha256_prefix":"a16c3bab848068f1","entry":"load_raw_dataset","repo":"noveens/infinite_ae_cf","repo_kind":"official","path":"data.py","file_url":"https://github.com/noveens/infinite_ae_cf/blob/HEAD/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a16c3bab848068f1"}},{"code_sha256_prefix":"ca4b9f603f7b24a2","entry":"prep_movielens","repo":"noveens/infinite_ae_cf","repo_kind":"official","path":"preprocess.py","file_url":"https://github.com/noveens/infinite_ae_cf/blob/HEAD/preprocess.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca4b9f603f7b24a2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}