dorsal/arxiv
View SchemaForget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models
| Authors | Kaiyuan Deng, Gen Li, Yang Xiao, Bo Hui, Xiaolong Ma |
|---|---|
| Categories | |
| ArXiv ID | 2601.06162vv1 |
| URL | https://arxiv.org/abs/2601.06162 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
Text-to-image diffusion models have achieved remarkable progress, yet their use raises copyright and misuse concerns, prompting research into machine unlearning. However, extending multi-concept unlearning to large-scale scenarios remains difficult due to three challenges: (i) conflicting weight updates that hinder unlearning or degrade generation; (ii) imprecise mechanisms that cause collateral damage to similar content; and (iii) reliance on additional data or modules, creating scalability bottlenecks. To address these, we propose Scalable-Precise Concept Unlearning (ScaPre), a unified framework tailored for large-scale unlearning. ScaPre introduces a conflict-aware stable design, integrating spectral trace regularization and geometry alignment to stabilize optimization, suppress conflicts, and preserve global structure. Furthermore, an Informax Decoupler identifies concept-relevant parameters and adaptively reweights updates, strictly confining unlearning to the target subspace. ScaPre yields an efficient closed-form solution without requiring auxiliary data or sub-models. Comprehensive experiments on objects, styles, and explicit content demonstrate that ScaPre effectively removes target concepts while maintaining generation quality. It forgets up to $\times \mathbf{5}$ more concepts than the best baseline within acceptable quality limits, achieving state-of-the-art precision and efficiency for large-scale unlearning.
{
"annotation_id": "fa62cf3b-2da7-4dc9-845b-44e7704d60ee",
"date_created": "2026-02-17T05:53:04.768000Z",
"date_modified": "2026-02-17T05:53:04.768000Z",
"file_hash": "3de37971d16612da7c417ff3aba2399124afacd117c6f6448028ff07286adee9",
"private": false,
"record": {
"abstract": "Text-to-image diffusion models have achieved remarkable progress, yet their use raises copyright and misuse concerns, prompting research into machine unlearning. However, extending multi-concept unlearning to large-scale scenarios remains difficult due to three challenges: (i) conflicting weight updates that hinder unlearning or degrade generation; (ii) imprecise mechanisms that cause collateral damage to similar content; and (iii) reliance on additional data or modules, creating scalability bottlenecks. To address these, we propose Scalable-Precise Concept Unlearning (ScaPre), a unified framework tailored for large-scale unlearning. ScaPre introduces a conflict-aware stable design, integrating spectral trace regularization and geometry alignment to stabilize optimization, suppress conflicts, and preserve global structure. Furthermore, an Informax Decoupler identifies concept-relevant parameters and adaptively reweights updates, strictly confining unlearning to the target subspace. ScaPre yields an efficient closed-form solution without requiring auxiliary data or sub-models. Comprehensive experiments on objects, styles, and explicit content demonstrate that ScaPre effectively removes target concepts while maintaining generation quality. It forgets up to $\\times \\mathbf{5}$ more concepts than the best baseline within acceptable quality limits, achieving state-of-the-art precision and efficiency for large-scale unlearning.",
"arxiv_id": "2601.06162",
"authors": [
"Kaiyuan Deng",
"Gen Li",
"Yang Xiao",
"Bo Hui",
"Xiaolong Ma"
],
"categories": [
"cs.LG",
"cs.CV"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models",
"url": "https://arxiv.org/abs/2601.06162",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "24b697fd-a954-4db8-bb53-2a60dd59d6a4",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}