<ul><li>The joint implementation of federated learning (FL) and explainable artificial intelligence (XAI) could allow training models from distributed data and explaining their inner workings while preserving privacy.</li><li>This scoping review examines publications that explore the interplay between FL and XAI, particularly focusing on model interpretability or post-hoc explanations.</li><li>Out of the 37 studies analyzed, only one quantitatively examined the impact of FL on model explanations, highlighting a significant research gap.</li><li>There is a need for more quantitative research and transparent practices to understand the mutual impact and conditions of FL and XAI integration.</li></ul>

Interplay between Federated Learning and Explainable Artificial Intelligence: a Scoping Review

Discover more