2 papers
cs.LG2025
CLoVE: Personalized Federated Learning through Clustering of Loss Vector Embeddings
Randeep Bhatia, Nikos Papadis, Murali Kodialam +2
We propose CLoVE (Clustering of Loss Vector Embeddings), a novel algorithm for Clustered Federated Learning (CFL). In CFL, clients are naturally grouped into clusters based on thei…
cs.PF2023
Understanding the Benefits of Hardware-Accelerated Communication in Model-Serving Applications
Walid A. Hanafy, Limin Wang, Hyunseok Chang +3
It is commonly assumed that the end-to-end networking performance of edge offloading is purely dictated by that of the network connectivity between end devices and edge computing f…