FedInf: An Efficient and Secure Inference With Federated Participants

Bowen Zhao, Weibin Guo, Jiahui Chen, Yang Xiao, Liang Zhai, Qingqi Pei

Abstract: Federated learning is a machine learning paradigm through training on locally private data and aggregating local models to generate a federated model. However, due to the heterogeneity problems (data heterogeneity and model heterogeneity), federated learning suffers from convergence difficulties and excessive aggregation overhead on decentralized participants. Additionally, federated learning faces privacy concerns during the aggregation of local models. To this end, in this work, we propose FedInf, an efficient and secure inference with federated participants. Specifically, FedInf features the following characteristics. FedInf overcomes convergence challenges through federated inference instead of federated training, which reduces computation and communication overhead. Moreover, we design secure computation protocols and aggregation mechanisms to measure contributions, and handle both data and model heterogeneity without sacrificing privacy. Results of experimental evaluations on common datasets demonstrate that the proposed FedInf outperforms the existing federated learning approaches in terms of efficiency and heterogeneity.

External IDs:dblp:journals/tc/ZhaoGCXZP26