Problem
Research questions and friction points this paper is trying to address.
Decentralized Learning
Power Control
Privacy Guarantees
Wireless Multicast Network
Differential Privacy
A Joint Power-Privacy Control Framework for Decentralized Learning over Heterogeneous Wireless Multicasting Networks
๐ค AI Summary
ๆฌๆๆๅบไธ็ง่ๅๅ็-้็งๆงๅถๆกๆถ๏ผ้่ฟๅ้
่็น็ไผ ่พๅ็ๅๆณจๅ
ฅๅชๅฃฐๆฅๅจๅผๆๆ ็บฟๅคๆญ็ฝ็ปไธญๅฎ็ฐๅๅธๅผๅญฆไน ็ๅๆถไฟ่ฏ้็งใ
๐ Abstract
In this paper, we propose a decentralized learning framework that incorporates both power control and privacy guarantees. Specifically, we enable a set of clients in a wireless multicast network to jointly train a common model while maintaining a prescribed per-iteration maximum privacy leakage level. The communication network is represented by a rowstochastic adjacency matrix, allowing us to capture asymmetric channel gains as well as heterogeneous maximum transmit power levels. Differential privacy is enforced through an explicit powersplitting strategy that allocates each node's limited maximum transmit power between model coefficients and injected Gaussian noise, thereby jointly controlling learning performance and privacy leakage. We further prove that the proposed algorithm achieves a cumulative regret bound of O(logT), whereTdenotes the time horizon. To evaluate the practical performance of our approach, we perform comprehensive experiments on the CIFAR-10 dataset under both IID and non-IID data distributions, considering different privacy levels, diverse numbers of clients, and various graph topologies. The results demonstrate strong performance across the considered settings and improved performance over existing methods, highlighting the effectiveness of the proposed algorithm under realistic wireless communication constraints.
Innovation
Methods, ideas, or system contributions that make the work stand out.
decentralized learning
power control
differential privacy
wireless multicasting networks
cumulative regret bound
๐ Similar Papers
No similar papers found.
