6 papers
Local Epochs as Optimal Stopping: Theory and Evidence in Federated Learning
Ke Xiao, Qiyuan Wang, Christos Anagnostopoulos
How long should each client train before communicating? Federated learning usually answers with a fixed, hand-tuned number of local epochs, yet an extra epoch helps only while the…
SAGE: Optimal-Stopping Peer Selection for Decentralised Federated Learning
Ke Xiao, Qiyuan Wang, Christos Anagnostopoulos
Decentralised federated learning replaces server aggregation with peer-to-peer model exchange, making collaborator selection a local decision under uncertainty. Fixed probe budgets…
Multi-Partner Project: COIN-3D -- Collaborative Innovation in 3D VLSI Reliability
George Rafael Gourdoumanis, Fotoini Oikonomou, Maria Pantazi-Kypraiou +10
As semiconductor manufacturing advances from the 3-nm process toward the sub-nanometer regime and transitions from FinFETs to gate-all-around field-effect transistors (GAAFETs), th…
FedPhD: Federated Pruning with Hierarchical Learning of Diffusion Models
Qianyu Long, Qiyuan Wang, Christos Anagnostopoulos +1
Federated Learning (FL), as a distributed learning paradigm, trains models over distributed clients' data. FL is particularly beneficial for distributed training of Diffusion Model…
Decentralized Personalized Federated Learning based on a Conditional Sparse-to-Sparser Scheme
Qianyu Long, Qiyuan Wang, Christos Anagnostopoulos +1
Decentralized Federated Learning (DFL) has become popular due to its robustness and avoidance of centralized coordination. In this paradigm, clients actively engage in training by…
FedDIP: Federated Learning with Extreme Dynamic Pruning and Incremental Regularization
Qianyu Long, Christos Anagnostopoulos, Shameem Puthiya Parambath +1
Federated Learning (FL) has been successfully adopted for distributed training and inference of large-scale Deep Neural Networks (DNNs). However, DNNs are characterized by an extre…