Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learning
Mirko Konstantin, Stefan Zachow, Anirban Mukhopadhyay
Federated learning (FL) enables collaborative model training across distributed clients while keeping data local. A central challenge is determining which client updates are benefi…
cs.LG2025
ASMR: Angular Support for Malfunctioning Client Resilience in Federated Learning
Mirko Konstantin, Moritz Fuchs, Anirban Mukhopadhyay
Federated Learning (FL) allows the training of deep neural networks in a distributed and privacy-preserving manner. However, this concept suffers from malfunctioning updates sent b…
cs.LG2025
Don't Reach for the Stars: Rethinking Topology for Resilient Federated Learning
Mirko Konstantin, Anirban Mukhopadhyay
Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy by keeping data local. Traditional FL approaches rely on a cen…