Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking

About

The widespread adoption of text-to-image (T2I) diffusion models has raised concerns about their potential to generate copyrighted, inappropriate, or sensitive imagery learned from massive training corpora. As a practical solution, machine unlearning aims to selectively erase unwanted concepts from a pre-trained model without retraining from scratch. While most existing methods are effective for single-concept unlearning, they often struggle in real-world scenarios that require removing multiple concepts, since extending them to this setting is both non-trivial and problematic, causing significant challenges in unlearning effectiveness, generation quality, and sensitivity to hyperparameters and datasets. In this paper, 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 only minimal hyperparameter tuning for new tasks, thereby promoting a plug-and-play paradigm. Extensive experiments across three distinct unlearning tasks demonstrate that FIA achieves more reliable multi-concept unlearning, improving forgetting effectiveness while maintaining semantic fidelity and image quality.

Kaiyuan Deng, Bo Hui, Gen Li, Jie Ji, Minghai Qin, Geng Yuan, Xiaolong Ma• 2026

Related benchmarks

TaskDatasetResultRank
Concept UnlearningUnlearnDiffAtk
UnlearnDiffAtk61.7
36
Image GenerationMS-COCO 30k (val)
FID16.7
22
Concept UnlearningRing-a-Bell
Ring-A-Bell Score87.9
20
Machine UnlearningImagenette
Accuracy (garbage truck)2.6
18
Explicit Content UnlearningI2P
Armpits6
11
Text-to-Image AlignmentMS-COCO
CLIP Score29.56
10
Concept UnlearningImagenette
Accuracy (garbage truck)0.5
10
Explicit Content UnlearningI2P v1.5 (test)
Armpits6
10
Object UnlearningImageNette (test)
Garbage Truck Accuracy0.5
10
Artist UnlearningFive Artist Styles Van Gogh, Monet, Picasso, Da Vinci, Dali
CLIP_a27.45
9
Showing 10 of 12 rows

Other info

Follow for update