3 papers
cs.LG2025
FedPURIN: Programmed Update and Reduced INformation for Sparse Personalized Federated Learning
Lunchen Xie, Zehua He, Qingjiang Shi
Personalized Federated Learning (PFL) has emerged as a critical research frontier addressing data heterogeneity issue across distributed clients. Novel model architectures and coll…
cs.CV2025
ZO-DARTS++: An Efficient and Size-Variable Zeroth-Order Neural Architecture Search Algorithm
Lunchen Xie, Eugenio Lomurno, Matteo Gambella +4
Differentiable Neural Architecture Search (NAS) provides a promising avenue for automating the complex design of deep learning (DL) models. However, current differentiable NAS meth…
cs.CV2024
A Lightweight Neural Architecture Search Model for Medical Image Classification
Lunchen Xie, Eugenio Lomurno, Matteo Gambella +4
Accurate classification of medical images is essential for modern diagnostics. Deep learning advancements led clinicians to increasingly use sophisticated models to make faster and…