3 citations · 9 across the 9 of their papers we have counts for
4 papers · 1 filter
Training-Free Dynamic Upcycling of Expert Language Models
Eros Fanì, Oğuzhan Ersoy
Large Language Models (LLMs) have achieved remarkable performance on a wide range of specialized tasks, exhibiting strong problem-solving capabilities. However, training these mode…
FedDiverse: Tackling Data Heterogeneity in Federated Learning with Diversity-Driven Client Selection
Gergely D. Németh, Eros Fanì, Yeat Jeng Ng +4
Federated Learning (FL) enables decentralized training of machine learning models on distributed data while preserving privacy. However, in real-world FL settings, client data is o…
Interaction-Aware Gaussian Weighting for Clustered Federated Learning
Alessandro Licciardi, Davide Leo, Eros Fanì +2
Federated Learning (FL) emerged as a decentralized paradigm to train models while preserving privacy. However, conventional FL struggles with data heterogeneity and class imbalance…
Accelerating Heterogeneous Federated Learning with Closed-form Classifiers
Eros Fanì, Raffaello Camoriano, Barbara Caputo +1
Federated Learning (FL) methods often struggle in highly statistically heterogeneous settings. Indeed, non-IID data distributions cause client drift and biased local solutions, par…