Author

Bulent Bolat

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#federated learning Open access Sep 2026

FedLucra: Federated Learning With Loss‐Utility Controlled Robust Aggregation

FedLucra, a modular loss‐aware aggregation framework that jointly uses client validation loss and local data volume to determine aggregation weights, is proposed and the proposed loss‐aware privacy mechanisms can improve model utility relative to uniform‐budget differential privacy in several evaluated settings.

Emin Akpinar, M. Taşkıran, Bulent Bolat · Expert systems · 0 citations