无需重训练，一键清除多个敏感概念，同时保持图像生成质量。
Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking
- 通过敏感神经元识别，精准定位需删除的概念相关权重。
- 在三个任务中实现更可靠遗忘，生成质量损失低于5%。
- 无需调参，可直接用于新概念删除，适合实际部署。
文本到图像扩散模型的广泛应用引发了对生成版权、不当或敏感内容的担忧。机器遗忘作为一种实用解决方案，旨在不从头训练的情况下移除特定概念。现有方法在单概念遗忘上表现良好，但在多概念删除时常出现遗忘效果差、生成质量下降及对超参数和数据集敏感等问题。本文提出无训练的忘我（Forget It All, FIA）框架，利用模型稀疏性，首次引入对比概念显著性量化权重连接对目标概念的贡献，并结合时空信息识别对特定概念敏感的神经元。随后构建掩码并融合为统一的多概念掩码，保留通用生成所需的无关神经元，仅修剪概念特异性神经元以实现删除。FIA无需重训练且新任务极少调参，支持即插即用。在三个不同遗忘任务上的实验表明，FIA显著提升多概念遗忘可靠性，在保持生成保真度的同时，有效消除目标概念。代码已开源：https://github.com/kaiyuan02415/Forget-It-All。
原文摘要 · Abstract (English)
The widespread adoption of text-to-image (T2I) diffusion models has raised concerns about their potential to generate copyrighted, inappropriate, or sensitive imagery. As a practical solution, machine unlearning aims to erase unwanted concepts without retraining from scratch. While most existing methods are effective for single-concept unlearning, they often struggle when removing multiple concepts, causing significant challenges in unlearning effectiveness, generation quality, and sensitivity to hyperparameters and datasets. We take a unique perspective on multi-concept unlearning by leveraging model sparsity and propose the Forget It All (FIA) framework. FIA first introduces Contrastive Concept Saliency to quantify each weight connection's contribution to a target concept. It then identifies Concept Sensitive Neurons by combining temporal and spatial information, ensuring that only neurons consistently responsive to the target concept are selected. Finally, FIA constructs masks from the identified neurons and fuses them into a unified multi-concept mask, where Concept Agnostic Neurons that broadly support general content generation are preserved while concept-specific neurons are pruned to remove the targets. FIA is training-free and requires minimal hyperparameter tuning for new tasks, enabling plug-and-play use. Extensive experiments across three distinct unlearning tasks demonstrate that FIA achieves more reliable multi-concept unlearning, improving forgetting effectiveness while maintaining generation fidelity and quality. Code is available at https://github.com/kaiyuan02415/Forget-It-All
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。