{"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/neural-network-matrix-factorization","title":"Neural Network Matrix Factorization","arxiv_id":"1511.06443","date":"2015-11-19","proceeding":null,"authors":["Gintare Karolina Dziugaite","Daniel M. Roy"],"abstract":"Data often comes in the form of an array or matrix. Matrix factorization\ntechniques attempt to recover missing or corrupted entries by assuming that the\nmatrix can be written as the product of two low-rank matrices. In other words,\nmatrix factorization approximates the entries of the matrix by a simple, fixed\nfunction---namely, the inner product---acting on the latent feature vectors for\nthe corresponding row and column. Here we consider replacing the inner product\nby an arbitrary function that we learn from the data at the same time as we\nlearn the latent feature vectors. In particular, we replace the inner product\nby a multi-layer feed-forward neural network, and learn by alternating between\noptimizing the network for fixed latent features, and optimizing the latent\nfeatures for a fixed network. The resulting approach---which we call neural\nnetwork matrix factorization or NNMF, for short---dominates standard low-rank\ntechniques on a suite of benchmark but is dominated by some recent proposals\nthat take advantage of the graph features. Given the vast range of\narchitectures, activation functions, regularizers, and optimization techniques\nthat could be used within the NNMF framework, it seems likely the true\npotential of the approach has yet to be reached.","url_abs":"http://arxiv.org/abs/1511.06443v2","url_pdf":"http://arxiv.org/pdf/1511.06443v2.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":"neural-network-matrix-factorization","repo_url":"https://github.com/jstol/neural-net-matrix-factorization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"neural-network-matrix-factorization","repo_url":"https://github.com/nzhinusoftcm/review-on-collaborative-filtering","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"collaborative-filtering","task_name":"Collaborative Filtering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/collaborative-filtering-on-movielens-1m","task":"Recommendation Systems","dataset":"MovieLens 1M","model":"NNMF","rank_in_archive_order":11,"of":31,"metrics":{"RMSE":"0.843"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.06443","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}