2 papers
cs.LG2026
Partial Model Sharing Improves Byzantine Resilience in Federated Conformal Prediction
Ehsan Lari, Reza Arablouei, Stefan Werner
We propose a Byzantine-resilient federated conformal prediction (FCP) method that leverages partial model sharing, where only a subset of model parameters is exchanged each round.…
cs.LG2026
SA-PEF: Step-Ahead Partial Error Feedback for Efficient Federated Learning
Dawit Kiros Redie, Reza Arablouei, Stefan Werner
Biased gradient compression with error feedback (EF) reduces communication in federated learning (FL), but under non-IID data, the residual error can decay slowly, causing gradient…