Graph-Assisted Communication-Efficient Ensemble Federated Learning

2022/02/27 by Pouya M. Ghari, Ghari, Pouya M, Yanning Shen +1
Computer Science · Social Sciences · #FOS: Computer and information sciences #Human Mobility and Location-Based Analysis #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data #Recommender Systems and Techniques

paper · pdf · doi:10.48550/arxiv.2202.13447

openalex publication_date 2022/02/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Communication efficiency arises as a necessity in federated learning due to limited communication bandwidth. To this end, the present paper develops an algorithmic framework where an ensemble of pre-trained models is learned. At each learning round, the server selects a subset of pre-trained models to construct the ensemble model based on the structure of a graph, which characterizes the server's confidence in the models. Then only the selected models are transmitted to the clients, such that certain budget constraints are not violated. Upon receiving updates from the clients, the server refines the structure of the graph accordingly. The proposed algorithm is proved to enjoy sub-linear regret bound. Experiments on real datasets demonstrate the effectiveness of our novel approach.

Related

• Federated Learning: Strategies for Improving Communication Efficiency
• Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning
• Joint Graph Estimation and Signal Restoration for Robust Federated Learning
• Rethinking Client-oriented Federated Graph Learning
• Graph-based Gossiping for Communication Efficiency in Decentralized Federated Learning