摘要
Communication bottleneck and data privacy are two critical concerns in federated multi-armed bandit (MAB) problems, such as situations in decision-making and recommendations of connected vehicles via wireless. In this paper, we design the privacy-preserving communication-efficient algorithm in such problems and study the interactions among privacy, communication and learning performance in terms of the regret. To be specific, we design privacy-preserving learning algorithms and communication protocols and derive the learning regret when networked private agents are performing online bandit learning in a master-worker, a decentralized and a hybrid structure. Our bandit learning algorithms are based on epoch-wise sub-optimal arm eliminations at each agent and agents exchange learning knowledge with the server/each other at the end of each epoch. Furthermore, we adopt the differential privacy (DP) approach to protect the data privacy at each agent when exchanging information; and we curtail communication costs by making less frequent communications with fewer agents participation. By analyzing the regret of our proposed algorithmic framework in the master-worker, decentralized and hybrid structures, we theoretically show trade-offs between regret and communication costs/privacy. Finally, we empirically show these trade-offs which are consistent with our theoretical analysis.
学科与关键词
- Distributed online bandit linear regressions with differential privacyDai, Mingcheng; Ho, Daniel W. C.; Zhang, Baoyong; Yuan, Deming*; Xu, ShengyuanJOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 2023, 360(16): 11736-11759.
- Federated Multi-Armed Bandits With Vector Rewards for Aspect-Based RecommendationsLiu, Zengyan*; Song, Linqi*; Fragouli, ChristinaIEEE Global Communications Conference (GLOBECOM), Rio de Janeiro, BRAZIL, 2022-12-04 To 2022-12-08.
- Killing two birds with one stone: Quantization achieves privacy in distributed learningYan, Guangfeng; Li, Tan; Wu, Kui; Song, Linqi*Digital Signal Processing: A Review Journal , 2024, 146: 104353.
