Browsing NTNU Open by Author "Lari, Ehsan"
Now showing items 1-5 of 5
-
Continual local updates for federated learning with enhanced robustness to link noise
Lari, Ehsan; Gogineni, Vinay Chakravarthi; Arablouei, Reza; Werner, Anders Stefan (Chapter, 2023)Communication errors caused by noisy links can negatively impact the accuracy of federated learning (FL) algorithms. To address this issue, we introduce an FL algorithm that is robust to communication errors while concurrently ... -
Distributed maximum consensus over noisy links
Lari, Ehsan; Arablouei, Reza; Dasanadoddi Venkategowda, Naveen Kumar; Werner, Stefan (Chapter, 2024) -
On the resilience of online federated learning to model poisoning attacks through partial sharing
Lari, Ehsan; Chakravarthi Gogineni, Vinay; Arablouei, Reza; Werner, Stefan (Chapter; Conference object, 2024)We investigate the robustness of the recently introduced partialsharing online federated learning (PSO-Fed) algorithm against model-poisoning attacks. To this end, we analyze the performance of the PSO-Fed algorithm in the ... -
Privacy-preserving distributed nonnegative matrix factorization
Lari, Ehsan; Arablouei, Reza; Werner, Stefan (Chapter, 2024) -
Resource-efficient federated learning robust to communication errors
Lari, Ehsan; Gogineni, Vinay Chakravarthi; Arablouei, Reza; Werner, Anders Stefan (Peer reviewed; Journal article, 2023)The effectiveness of federated learning (FL) in leveraging distributed datasets is highly contingent upon the accuracy of model exchanges between clients and servers. Communication errors caused by noisy links can negatively ...