Appro-Fun: Approximate Machine Unlearning in Federated Setting

Machine learning models contain much information about the training dataset, so even if some data points are deleted, the private information can still be inferred. To counteract this problem, "machine unlearning", as an emerging data management approach, is proposed to remove data from the databases and the influence of data from the trained models. Such a technique is vital in the current era of data-driven applications, where the privacy and security of users can be guaranteed. Yet, machine unlearning is still in its early stage, and there are rare existing methods for machine unlearning in the federated setting that is a more practical and crucial scenario. Therefore, this paper investigates the federated machine unlearning problem where the local clients of a federated system intend to delete their local private data appropriately. The proposed method is termed Approximate Federated unlearning (Appro-Fun), which adopts differential privacy and second-order optimization to achieve (ϵ, δ)-approximate unlearning on trained models. Rigorous theoretic analysis presents the performance guarantee of Appro-Fun, and real-data experiments validate the advantages of Appro-Fun compared with the state-of-the-art.