Federated Concept-Based Models: Interpretable models with distributed supervision
This work addresses the problem of scalable interpretable AI for institutions with distributed data, offering a novel integration of concept-based models with federated learning, though it appears incremental in combining existing paradigms.
The paper tackles the challenge of training interpretable concept-based models in federated learning settings where concept annotations are distributed across institutions, proposing Federated Concept-based Models (F-CMs) that adapt to evolving supervision while preserving accuracy and enabling interpretable inference on unseen concepts.
Concept-based models (CMs) enhance interpretability in deep learning by grounding predictions in human-understandable concepts. However, concept annotations are expensive to obtain and rarely available at scale within a single data source. Federated learning (FL) could alleviate this limitation by enabling cross-institutional training that leverages concept annotations distributed across multiple data owners. Yet, FL lacks interpretable modeling paradigms. Integrating CMs with FL is non-trivial: CMs assume a fixed concept space and a predefined model architecture, whereas real-world FL is heterogeneous and non-stationary, with institutions joining over time and bringing new supervision. In this work, we propose Federated Concept-based Models (F-CMs), a new methodology for deploying CMs in evolving FL settings. F-CMs aggregate concept-level information across institutions and efficiently adapt the model architecture in response to changes in the available concept supervision, while preserving institutional privacy. Empirically, F-CMs preserve the accuracy and intervention effectiveness of training settings with full concept supervision, while outperforming non-adaptive federated baselines. Notably, F-CMs enable interpretable inference on concepts not available to a given institution, a key novelty with respect to existing approaches.