FedADM: Adaptive Federated Learning via Dissimilarity Measure

Ning Yang, Yuan Xin, Hai Lin, Pin Lyu, Jun Wang

Keywords: Distributed Optimization, Federated Learning, Local Updates, Aggregation

Abstract: In federated learning, there are two critical challenges: 1) the data on distributed learners is heterogeneous; and 2) communication resources within the network are limited. In this work, we propose a framework, Federated Adaptive Dissimilarity Measure (FedADM), which can be regarded as an adaptively enhanced version of the Federated Proximal (FedProx) algorithm. This adaptiveness is primarily manifested in two aspects: (i) how it adaptively adjusts the proximity between the local models on different learners and the global model; and (ii) how it adaptively aggregates local model parameters. Building on the FedProx model, FedADM incorporates the concept of the Lagrangian multiplier to control the proximal coefficients of different learners, using “\textit{parameter dissimilarity}" to address data heterogeneity. It explicitly captures the essence of using “\textit{loss dissimilarity}" to adaptively adjust the aggregation frequency on distributed learners, thereby reducing communication overhead. Theoretically, we provide the performance upper bounds and convergence analysis of our proposed FedADM. Experiment results demonstrate that FedADM allows for higher accuracy and lower communication overhead compared to the baselines across a suite of realistic datasets.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 11139