AI RESEARCH

Federated Concept-Based Models: Interpretable models with distributed supervision

arXiv CS.LG

ArXi:2602.04093v2 Announce Type: replace Concept-based Models (CMs) enhance interpretability in deep learning by grounding predictions in human-understandable concepts. However, concept annotations are costly and rarely available at scale within a single data source. Federated Learning (FL) could alleviate this limitation by enabling cross-institutional