User-differentiated federated unlearning algorithm inspired by collaborative memory modulation

Graphical abstract

References

[1] Liu G, Ma X, Yang Y, Wang C, Liu J. FedEraser: enabling efficient client-level data removal from federated learning models. In: Proceedings of the 29th IEEE/ACM International Symposium on Quality of Service (IWQoS). 2021, 1−10

[2] Ding N, Wei E, Berry R. Strategic data revocation in federated unlearning. In: Proceedings of IEEE INFOCOM 2024 - IEEE Conference on Computer Communications. 2024, 1151−1160

[3] Zou W, Zhuang Z, Geng X, Huang S, Liu J, Chen J . Improved paraphrase generation via controllable latent diffusion. Frontiers of Computer Science, 2026, 20( 1): 2001302

[4] Kandel E R, Schwartz J H . Molecular biology of learning: modulation of transmitter release. Science, 1982, 218( 4571): 433–443

[5] Nguyen T H, Vu H P, Nguyen T D, Nguyen T M, Doan K D, Wong K S. Empirical study of federated unlearning: efficiency and effectiveness. In: Proceedings of the Asian Conference on Machine Learning (ACML). 2023, 959−974

[6] Fraboni Y, Van Waerebeke M, Scaman K, Vidal R, Kameni L, Lorenzi M. SIFU: sequential informed federated unlearning for efficient and provable client unlearning in federated optimization. In: Proceedings of the 27th International Conference on Artificial Intelligence and Statistics. 2024, 3457−3465

[7] Pan Z, Wang Z, Li C, Zheng K, Wang B, Tang X, Zhao J. Federated unlearning with gradient descent and conflict mitigation. In: Proceedings of the 39th AAAI Conference on Artificial Intelligence. 2025, 19804−19812

RIGHTS & PERMISSIONS

Higher Education Press