Memory-aware curriculum federated learning for breast cancer classification

Amelia Jiménez-Sánchez, Mickael Tardy, Miguel Ángel González Ballester, Diana Mateus, Gemma Piella

Abstract: Highlights•Curriculum learning improves breast cancer classification on high-resolution mammograms in a federated setting.•Curriculum is implemented as a data scheduler, which penalizes inconsistent predictions, to improve the consistency of local models in a federated setting.•We track the predictions before and after the deployment of the global model, thus we refer to our method as memory-aware curriculum federated learning.•Memory-aware curriculum federated learning improves the classification and alignment between domain pairs.•Effective for the multi-site breast cancer classification on clinical datasets from different vendors.