Differentiated Aggregation to Improve Generalization in Federated Learning

TMLR Paper4512 Authors

Abstract: This paper focuses on reducing the communication cost of federated learning by exploring generalization bounds and representation learning. We first characterize a tighter generalization bound for one-round federated learning based on local clients’ generalizations and heterogeneity of data distribution (non-iid scenario). We also characterize a generalization bound in R-round federated learning and its relation to the number of local updates (local stochastic gradient descents (SGDs)). Then, based on our generalization bound analysis and its interpretation through representation learning, we infer that less frequent aggregations for the representation extractor (typically corresponds to initial layers) compared to the head (usually the final layers) leads to the creation of more generalizable models, particularly in non-iid scenarios. We design a novel Federated Learning with Adaptive Local Steps (FedALS) algorithm based on our generalization bound and representation learning analysis. FedALS employs varying aggregation frequencies for different parts of the model, so reduces the communication cost. The paper is followed with experimental results showing the effectiveness of FedALS. Our codes are available for reproducibility.

Submission Length: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Sai_Aparna_Aketi1

Submission Number: 4512