Exploring Explainability in Federated Learning: A Comparative Study on Brain Age Prediction

Giuseppe Fasano, Angela Lombardi, Antonio Ferrara, Eugenio Di Sciascio, Tommaso Di Noia

Abstract: Predicting brain age from neuroimaging data is increasingly used to study aging trajectories and detect deviations linked to neurological conditions. Machine learning models trained on large datasets have shown promising results, but data privacy regulations and the challenge of sharing medical data across institutions limit the feasibility of centralized training. Federated Learning (FL) offers a solution by allowing multiple sites to collaboratively train a model without sharing raw data. However, it remains unclear how FL affects the explainability of these models, raising concerns about the consistency and reliability of their predictions.

External IDs:dblp:conf/xai/FasanoL0SN25