{"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/federated-collaborative-filtering-for-privacy","title":"Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System","arxiv_id":"1901.09888","date":"2019-01-29","proceeding":null,"authors":["Muhammad Ammad-Ud-Din","Elena Ivannikova","Suleiman A. Khan","Were Oyomno","Qiang Fu","Kuan Eeik Tan","Adrian Flanagan"],"abstract":"The increasing interest in user privacy is leading to new privacy preserving\nmachine learning paradigms. In the Federated Learning paradigm, a master\nmachine learning model is distributed to user clients, the clients use their\nlocally stored data and model for both inference and calculating model updates.\nThe model updates are sent back and aggregated on the server to update the\nmaster model then redistributed to the clients. In this paradigm, the user data\nnever leaves the client, greatly enhancing the user' privacy, in contrast to\nthe traditional paradigm of collecting, storing and processing user data on a\nbackend server beyond the user's control. In this paper we introduce, as far as\nwe are aware, the first federated implementation of a Collaborative Filter. The\nfederated updates to the model are based on a stochastic gradient approach. As\na classical case study in machine learning, we explore a personalized\nrecommendation system based on users' implicit feedback and demonstrate the\nmethod's applicability to both the MovieLens and an in-house dataset. Empirical\nvalidation confirms a collaborative filter can be federated without a loss of\naccuracy compared to a standard implementation, hence enhancing the user's\nprivacy in a widely used recommender application while maintaining recommender\nperformance.","url_abs":"http://arxiv.org/abs/1901.09888v1","url_pdf":"http://arxiv.org/pdf/1901.09888v1.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":"federated-collaborative-filtering-for-privacy","repo_url":"https://github.com/sciueferrara/fcf-huawei","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"collaborative-filtering","task_name":"Collaborative Filtering"},{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.09888","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}