Class-wise Federated Unlearning: Harnessing Active Forgetting with Teacher-Student Memory Generation
This addresses privacy concerns in federated learning by enabling class-wise unlearning, which is incremental as it builds on existing unlearning methods but focuses on more specific targets.
The paper tackles the problem of fine-grained data removal in federated learning by proposing a neuro-inspired federated unlearning framework that uses teacher-student memory generation and refined elastic weight consolidation, achieving satisfactory unlearning completeness against backdoor attacks in experiments on benchmark datasets.
Privacy concerns associated with machine learning models have driven research into machine unlearning, which aims to erase the memory of specific target training data from already trained models. This issue also arises in federated learning, creating the need to address the federated unlearning problem. However, federated unlearning remains a challenging task. On the one hand, current research primarily focuses on unlearning all data from a client, overlooking more fine-grained unlearning targets, e.g., class-wise and sample-wise removal. On the other hand, existing methods suffer from imprecise estimation of data influence and impose significant computational or storage burden. To address these issues, we propose a neuro-inspired federated unlearning framework based on active forgetting, which is independent of model architectures and suitable for fine-grained unlearning targets. Our framework distinguishes itself from existing methods by utilizing new memories to overwrite old ones. These new memories are generated through teacher-student learning. We further utilize refined elastic weight consolidation to mitigate catastrophic forgetting of non-target data. Extensive experiments on benchmark datasets demonstrate the efficiency and effectiveness of our method, achieving satisfactory unlearning completeness against backdoor attacks.