面向异构无线多播网络的联合功率-隐私控制框架的去中心化学习
A Joint Power-Privacy Control Framework for Decentralized Learning over Heterogeneous Wireless Multicasting Networks
浏览论文内容
中文总结 AI 辅助
针对异构无线多播网络，提出融合功率控制与隐私保障的去中心化学习框架，通过功率拆分策略实现差分隐私，在CIFAR-10数据集实验中性能优于现有方法。
中文摘要 AI 辅助
本文提出了一种融合功率控制与隐私保障的去中心化学习框架。具体而言，我们使无线多播网络中的一组客户端能够联合训练同一模型，同时保持规定的每轮迭代最大隐私泄漏水平。该通信网络由行随机邻接矩阵表示，可捕捉非对称信道增益以及异构最大发射功率水平。差分隐私通过显式功率拆分策略实现，该策略将每个节点有限的最大发射功率分配给模型系数和注入的高斯噪声，从而联合控制学习性能与隐私泄漏。我们进一步证明，所提算法实现了O(logT)的累积遗憾界，其中T表示时间范围。为评估所提方法的实际性能，我们在CIFAR-10数据集上针对独立同分布（IID）与非独立同分布（non-IID）数据分布开展了综合实验，考虑了不同隐私水平、不同客户端数量及各种图拓扑结构。结果表明，所提算法在所有考虑的设置中均表现出强劲性能，且优于现有方法，凸显了其在现实无线通信约束下的有效性。
英文摘要
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.
