Book
Open access
Nov 2026
FUCH: Non-IID Federated Unlearning via Classification-layer Hybrid-order Constraints
Federated unlearning (FU) aims to support the ''right to be forgotten'' by reducing the influence of target samples without full retraining. However, when applied to deep neural networks (DNNs) in practical non-IID scenarios, existing FU methods suffer from low unlearning efficiency and deviate from the retraining refe...
Teng-Yuan He, Yun-Fei Zi, Yue-Long Xia et al.
· Proceedings of the 35th ACM... · 0 citations