Optimizing Server-side Aggregation For Robust Federated Learning via Subspace Training. (arXiv:2211.05554v1 [cs.LG])

Non-IID data distribution across clients and poisoning attacks are two main
challenges in real-world federated learning systems. While both of them have
attracted great research interest with specific strategies developed, no known
solution manages to address them in a unified framework. To jointly overcome
both challenges, we propose SmartFL, a generic approach that optimizes the
server-side aggregation process with a small clean server-collected proxy
dataset (e.g., around one hundred samples, 0.2% of the dataset) via a subspace
training technique. Specifically, …

aggregation arxiv federated learning server training