ACU: Analytic Continual Unlearning for Efficient and Exact Forgetting with Privacy Preservation

TL;DR

This paper introduces ACU, a gradient-free method for continual unlearning that efficiently and exactly forgets specific knowledge while preserving data privacy, addressing limitations of existing gradient-based approaches.

Contribution

The paper proposes a novel analytical approach for continual unlearning that avoids gradient reliance, improving efficiency, accuracy, and privacy preservation in model forgetting.

Findings

ACU achieves superior unlearning effectiveness compared to existing methods.

ACU maintains high model fidelity after unlearning.

ACU demonstrates improved system efficiency and privacy preservation.

Abstract

The development of artificial intelligence demands that models incrementally update knowledge by Continual Learning (CL) to adapt to open-world environments. To meet privacy and security requirements, Continual Unlearning (CU) emerges as an important problem, aiming to sequentially forget particular knowledge acquired during the CL phase. However, existing unlearning methods primarily focus on single-shot joint forgetting and face significant limitations when applied to CU. First, most existing methods require access to the retained dataset for re-training or fine-tuning, violating the inherent constraint in CL that historical data cannot be revisited. Second, these methods often suffer from a poor trade-off between system efficiency and model fidelity, making them vulnerable to being overwhelmed or degraded by adversaries through deliberately frequent requests. In this paper, we identify that the limitations of existing unlearning methods stem fundamentally from their reliance on gradient-based updates. To bridge the research gap at its root, we propose a novel gradient-free method for CU, named Analytic Continual Unlearning (ACU), for efficient and exact forgetting with historical data privacy preservation. In response to each unlearning request, our ACU recursively derives an analytical (i.e., closed-form) solution in an interpretable manner using the least squares method. Theoretical and experimental evaluations validate the superiority of our ACU on unlearning effectiveness, model fidelity, and system efficiency.