Enhancing Robustness of Federated Learning via Server Learning

arXiv cs.LG / 4/6/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper proposes using “server learning” together with client update filtering to improve federated learning robustness against malicious client attacks under non-IID client data.
It combines a heuristic training approach with geometric median aggregation to reduce the impact of poisoned or adversarial client updates.
Experiments indicate notable model accuracy gains even when the proportion of malicious clients is high, surpassing 50% in some scenarios.
The method is tested with a small server dataset that may be synthetic and whose distribution need not closely match the clients’ aggregated data, suggesting flexibility in deployment settings.

Abstract

This paper explores the use of server learning for enhancing the robustness of federated learning against malicious attacks even when clients' training data are not independent and identically distributed. We propose a heuristic algorithm that uses server learning and client update filtering in combination with geometric median aggregation. We demonstrate via experiments that this approach can achieve significant improvement in model accuracy even when the fraction of malicious clients is high, even more than

50\%

in some cases, and the dataset utilized by the server is small and could be synthetic with its distribution not necessarily close to that of the clients' aggregated data.