Federated learning (FL) is a distributed learning paradigm that allows multiple decentralized clients to collaboratively learn a common model without sharing local data. Although local data is not exposed directly, privacy concerns nonetheless exist as clients' sensitive information can be inferred from intermediate computations. Moreover, such information leakage accumulates substantially over time as the same data is repeatedly used during the iterative learning process. As a result, it can be particularly difficult to balance the privacy-accuracy trade-off when designing privacy-preserving FL algorithms. In this paper, we introduce Upcycled-FL, a novel federated learning framework with first-order approximation applied at every even iteration. Under this framework, half of the FL updates incur no information leakage and require much less computation. We first conduct the theoretical analysis on the convergence (rate) of Upcycled-FL, and then apply perturbation mechanisms to preserve privacy. Experiments on real-world data show that Upcycled-FL consistently outperforms existing methods over heterogeneous data, and significantly improves privacy-accuracy trade-off while reducing 48% of the training time on average.

Upcycled-FL是一种新颖的联邦学习框架，应用在每个偶数迭代中的一阶逼近，以在保持隐私的同时提高隐私-准确性平衡，并通过引入扰动机制来保护隐私。实验表明，Upcycled-FL在异构数据上持续优于现有方法，并且平均减少48％的训练时间。

降低信息泄漏和计算的联邦学习