Rethinking Federated Unlearning via the Lens of Memorization

ArXi:2605.24545v1 Announce Type: cross Federated learning (FL) increasingly needs machine unlearning to comply with privacy regulations. However, existing federated unlearning approaches may overlook the overlapping information between the unlearning and remaining data, leading to ineffective unlearning and unfairness between clients. In this work, we revisit federated unlearning through the lens of memorization.