Author

T. Dagiuklas

h-index 25 View on Semantic Scholar

We have 2 of 230 papers

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.

#machine learning Preprint Sep 2026

Hidden in Rounds: Predicting the Time Cost of 802.11 Contention in Federated Learning

Federated learning over IEEE~802.11 shares the wireless channel among clients that send model updates with ns-3 to measure the frame-delivery ratio and saturation throughput for different client densities and offered loads and compares uniform participation with persistent heterogeneous participation.

Satwat Bashir, T. Dagiuklas · 0 citations

Preprint Aug 2026

FedOrbit: Adaptive Personalized Federated Learning for Non-IID LEO Satellite Constellations

FedOrbit is presented, which combines continuous orbit-level training over inter-satellite links, class-aware hierarchical aggregation, quality-weighted feature aggregation with return-rate dampening, and adaptive feature decomposition based on inter-orbit class similarity.

Satwat Bashir, T. Dagiuklas, M. Iqbal · 0 citations