arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2208.14865cs.LG
收藏

联邦在线集群的强盗

Federated Online Clustering of Bandits

The Chinese University of Hong Kong(香港中文大学);Shanghai Jiao Tong University(上海交通大学);Adobe Research(奥多比研究院)

Xutong Liu, Haoru Zhao, Tong Yu, Shuai Li, John C. S. Lui

摘要:

上下文多臂强盗(MAB)是推荐系统中一个重要的序贯决策问题。一系列的作品,被称为土匪集群(CLUB),利用用户之间的协作效应,并显着提高推荐质量。由于应用规模的不断扩大和公众对隐私的担忧,越来越多的人要求保持用户数据分散,并将强盗学习推到本地服务器端。然而,现有的CLUB算法是在集中式设置下设计的,其中数据在中央服务器处可用。我们专注于研究联邦在线集群的强盗(FCUB)问题,其目的是最大限度地减少总遗憾,同时满足隐私和通信的考虑。针对这个问题,我们设计了一种新的基于相位的簇检测方案和一种新的异步通信协议。为了保护用户的隐私,以前的差分隐私(DP)的定义是不是很合适,我们提出了一个新的DP的概念,作用于用户集群级别。我们提供了严格的证据表明,我们的算法同时实现(聚类)DP,次线性通信复杂性和次线性遗憾。最后,实验评估表明,我们优越的性能与基准算法相比。

英文摘要:

Contextual multi-armed bandit (MAB) is an important sequential decision-making problem in recommendation systems. A line of works, called the clustering of bandits (CLUB), utilize the collaborative effect over users and dramatically improve the recommendation quality. Owing to the increasing application scale and public concerns about privacy, there is a growing demand to keep user data decentralized and push bandit learning to the local server side. Existing CLUB algorithms, however, are designed under the centralized setting where data are available at a central server. We focus on studying the federated online clustering of bandit (FCLUB) problem, which aims to minimize the total regret while satisfying privacy and communication considerations. We design a new phase-based scheme for cluster detection and a novel asynchronous communication protocol for cooperative bandit learning for this problem. To protect users' privacy, previous differential privacy (DP) definitions are not very suitable, and we propose a new DP notion that acts on the user cluster level. We provide rigorous proofs to show that our algorithm simultaneously achieves (clustered) DP, sublinear communication complexity and sublinear regret. Finally, experimental evaluations show our superior performance compared with benchmark algorithms.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑