Continual Forgetting for Pre-trained Vision Models

TL;DR

This paper introduces GS-LoRA, a method for continual forgetting in pre-trained vision models that efficiently erases specific information while preserving remaining knowledge, addressing privacy and security concerns.

Contribution

The paper proposes GS-LoRA, a parameter-efficient, data-efficient method for continual forgetting in vision models using LoRA modules with group sparse regularization.

Findings

Effective forgetting of specific classes demonstrated

Minimal impact on remaining knowledge achieved

Applicable to face recognition, object detection, and image classification

Abstract

For privacy and security concerns, the need to erase unwanted information from pre-trained vision models is becoming evident nowadays. In real-world scenarios, erasure requests originate at any time from both users and model owners. These requests usually form a sequence. Therefore, under such a setting, selective information is expected to be continuously removed from a pre-trained model while maintaining the rest. We define this problem as continual forgetting and identify two key challenges. (i) For unwanted knowledge, efficient and effective deleting is crucial. (ii) For remaining knowledge, the impact brought by the forgetting procedure should be minimal. To address them, we propose Group Sparse LoRA (GS-LoRA). Specifically, towards (i), we use LoRA modules to fine-tune the FFN layers in Transformer blocks for each forgetting task independently, and towards (ii), a simple group sparse regularization is adopted, enabling automatic selection of specific LoRA groups and zeroing out the others. GS-LoRA is effective, parameter-efficient, data-efficient, and easy to implement. We conduct extensive experiments on face recognition, object detection and image classification and demonstrate that GS-LoRA manages to forget specific classes with minimal impact on other classes. Codes will be released on \url{https://github.com/bjzhb666/GS-LoRA}.