论文标题
非IID数据的个性化跨核联合学习
Personalized Cross-Silo Federated Learning on Non-IID Data
论文作者
论文摘要
非IID数据对联合学习提出了艰巨的挑战。在本文中，我们探讨了一个新颖的想法，即通过相似的数据来促进客户之间的成对协作。我们提出了FedAmp，这是一种采用联合细心信息传递的新方法，以促进类似的客户进行更多的协作。我们为凸模型和非凸模型建立了FedAmp的融合，并提出了一种启发式方法，以进一步提高FedAmp的性能，当客户采用深层神经网络作为个性化模型。我们对基准数据集的广泛实验证明了所提出的方法的出色性能。
Non-IID data present a tough challenge for federated learning. In this paper, we explore a novel idea of facilitating pairwise collaborations between clients with similar data. We propose FedAMP, a new method employing federated attentive message passing to facilitate similar clients to collaborate more. We establish the convergence of FedAMP for both convex and non-convex models, and propose a heuristic method to further improve the performance of FedAMP when clients adopt deep neural networks as personalized models. Our extensive experiments on benchmark data sets demonstrate the superior performance of the proposed methods.
