期刊
2022 21ST IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS, ICMLA
卷 -, 期 -, 页码 647-652出版社
IEEE COMPUTER SOC
DOI: 10.1109/ICMLA55696.2022.00107
关键词
privacy; non-negative matrix factorization; oneshot; federated learning; recommendation system
资金
- Los Alamos National Laboratory (LANL) Laboratory Directed Research and Development (LDRD) [20190020DR]
- U.S. Department of Energy National Nuclear Security Administration [89233218CNA000001]
This paper presents the first one-shot federated CF implementation, called One-FedCF, to address the privacy problem and communication bottleneck in collaborative filtering. In this approach, clients first apply local CF in parallel to build independent recommenders, then extract global item patterns through joint factorization and build local models through information retrieval transfer.
Non-negative matrix factorization (NMF) with missing-value completion is a well-known effective Collaborative Filtering (CF) method used to provide personalized user recommendations. However, traditional CF relies on a privacy-invasive collection of user data to build a central recommender model. One-shot federated learning has recently emerged as a method to mitigate the privacy problem while addressing the traditional communication bottleneck of federated learning. In this paper, we present the first one-shot federated CF implementation, named One-FedCF, for groups of users or collaborating organizations. In our solution, the clients first apply local CF in-parallel to build distinct, client-specific recommenders. Then, the privacypreserving local item patterns and biases from each client are shared with the processor to perform joint factorization in order to extract the global item patterns. Extracted patterns are then aggregated to each client to build the local models via information retrieval transfer. In our experiments, we demonstrate our approach with two MovieLens datasets and show results competitive with the state-of-the-art federated recommender systems at a substantial decrease in the number of communications.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据