ATC-FL: Adaptive Thompson Sampling for Efficient Clustering in Federated Learning

Federated Learning (FL) enables collaborative model training across decentralized clients without sharing raw data. To improve scalability and address client heterogeneity, clustering-based FL methods group similar clients to train specialized models. However, under realistic network constraints, ex...

Cijeli opis

Bibliografski detalji

Glavni autori:	Shivani Sanjay Kolekar, Jisoo Shin, David J. Richter, Kyungbaek Kim
Format:	Artigo
Jezik:	Inglês
Izdano:	IEEE 2026-01-01
Serija:	IEEE Access
Teme:	Federated learning client clustering multi-armed bandits Thompson sampling distributed optimization
Online pristup:	https://ieeexplore.ieee.org/document/11450082/
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!