SemFedXAI: A Semantic Framework for Explainable Federated Learning in Healthcare

Federated Learning (FL) is emerging as an encouraging paradigm for AI model training in healthcare that enables collaboration among institutions without revealing sensitive information. The lack of transparency in federated models makes their deployment in healthcare settings more difficult, as knowledge of the decision process is of primary importance. This paper introduces SemFedXAI, a new framework that combines Semantic Web technologies and federated learning to achieve better explainability of artificial intelligence models in healthcare. SemFedXAI extends traditional FL architectures with three key components: (1) Ontology-Enhanced Federated Learning that enriches models with domain knowledge, (2) a Semantic Aggregation Mechanism that uses semantic technologies to improve the consistency and interpretability of federated models, and (3) a Knowledge Graph-Based Explanation component that provides contextualized explanations of model decisions. We evaluated SemFedXAI within the context of e-health, reporting noteworthy advancements in explanation quality and predictive performance compared to conventional federated learning methods. The findings refer to the prospects of combining semantic technologies and federated learning as an avenue for building more explainable and resilient AI systems in healthcare.