Practical Continual Forgetting for Pre-trained Vision Models Article Swipe

MAKE IMPACT

Hongbo Zhao , Fei Zhu , Bolin Ni , Feng Zhu , Gaofeng Meng , Zhaoxiang Zhang · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2501.09705

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, and 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 three 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. (iii) In real-world scenarios, the training samples may be scarce or partially missing during the process of forgetting. To address them, we first propose Group Sparse LoRA (GS-LoRA). Specifically, towards (i), we introduce 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. To further extend GS-LoRA to more practical scenarios, we incorporate prototype information as additional supervision and introduce a more practical approach, GS-LoRA++. For each forgotten class, we move the logits away from its original prototype. For the remaining classes, we pull the logits closer to their respective prototypes. We conduct extensive experiments on face recognition, object detection and image classification and demonstrate that our method manages to forget specific classes with minimal impact on other classes. Codes have been released on https://github.com/bjzhb666/GS-LoRA.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2501.09705

PDF

https://arxiv.org/pdf/2501.09705

OA Status

green

Related Works

10

OpenAlex ID

https://openalex.org/W4406549415

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4406549415

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2501.09705

Digital Object Identifier

Title

Practical Continual Forgetting for Pre-trained Vision Models

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-01-16

Full publication date if available

Authors

Hongbo Zhao, Fei Zhu, Bolin Ni, Feng Zhu, Gaofeng Meng, Zhaoxiang Zhang

List of authors in order

Landing page

https://arxiv.org/abs/2501.09705

Publisher landing page

PDF URL

https://arxiv.org/pdf/2501.09705

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2501.09705

Direct OA link when available

Concepts

Forgetting, Artificial intelligence, Computer science, Psychology, Computer vision, Cognitive psychology

Top concepts (fields/topics) attached by OpenAlex

Cited by

0

Total citation count in OpenAlex

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload