Preprint
Aug 2026
Robust and Personalized Federated Learning for Aircraft-Engine Prognostics under Benign and Adversarial Client Heterogeneity
A controlled, safety-oriented evaluation using a multi-task one-dimensional convolutional neural network and a structurally non-IID partition of the Commercial Modular Aero-Propulsion System Simulation benchmark reveals a trade-off between robust update selection and collaborative representation learning.
Chinmoy Mitra, Md Mehedi Hasan Nipu, Mohammad Sakib Mahmood et al.
· 0 citations