
JA
Jebacyril Arockiaraj, Dhruv Parikh, Jayashree Adivarahan, Rajgopal Kannan, Viktor Prasanna
· 1 min read
ResearcharXiv cs.LG
FedRAN: Accurate and Efficient Analytic Federated Continual Learning
arXiv:2606.11480v2 Announce Type: replace
Abstract: Federated continual learning (FCL) enables distributed clients to learn from evolving data streams while retaining knowledge from previously observed tasks. Existing optimization-based FCL methods often rely on repeated local training, incurring communication overhead and feature drift across clients. Analytic alternatives avoid iterative training, but high-dimensional random features used to improve accuracy require communicating a Gram matrix whose cost grows quadratically with feature dimension. Communication-efficient alternatives reduce this cost by statistically reconstructing the Gram matrix from first-order summaries. We propose FedRAN, a low-rank analytic FCL framework that instead compresses the required second-order structure directly through spectral summaries that are merged across clients and tasks. The retained rank explicitly controls the tradeoff between approximation fidelity and communication, reducing second-order communication from quadratic to linear in feature dimension for a fixed rank. FedRAN further supports label scarcity through prototype-based pseudo-labeling. Across CIFAR-100, ImageNet-R, and VTAB, FedRAN improves average accuracy by up to 4.8 percentage points over the strongest baseline, uses 30.6-121.8x less per-client communication, and is 190.3x faster than optimization-based baselines.
Original source
This story was published by arXiv cs.LG and written by Jebacyril Arockiaraj, Dhruv Parikh, Jayashree Adivarahan, Rajgopal Kannan, Viktor Prasanna. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


