Taehong Kim

AUG 10, 2026 · PREPRINT

FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning

arXiv

This is an unrefereed technical preprint proposing a novel algorithmic method for federated learning, demonstrating computational improvements in simulation but lacking peer review, clinical relevance, or human validation.

AUG 10, 2026 · PREPRINT

FedTVD: Balancing Data Quality and Quantity for Robust Federated Learning

arXiv

This is an algorithm development paper presenting a computational method without clinical or real-world validation; it demonstrates improved performance on image classification benchmarks but does not address whether the approach solves a genuine problem in federated learning deployment or generalize beyond simulation.

AUG 7, 2026 · PREPRINT

FedLBW: A Loss-Based Weighting Strategy for Federated Learning on Non-IID Data in Wireless Networks

arXiv

Simulation-based algorithmic study demonstrating improved federated learning convergence on benchmark datasets; lacks clinical validation, real-world deployment evidence, or comparison to state-of-the-art methods in applied settings.

AUG 7, 2026 · PREPRINT

FedVAR: Prototype-Aligned Federated Framework for Video Anomaly Recognition

arXiv

This is an unrefereed preprint describing a novel federated learning framework for video anomaly recognition; it presents a methodological contribution with experimental validation but lacks peer review and clinical/direct clinical application.