ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition

• URL: http://arxiv.org/abs/2605.14309v2
• Date: Fri, 15 May 2026 04:01:43 GMT
• Title: ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
• Abstract summary: We propose an interpretable concept-level unlearning framework for Vision-Language Models (VLMs)<n>Our method formulates unlearning as concept-level optimization, where target concepts are selectively suppressed while intra-instance non-target semantics and global cross-modal knowledge are preserved.
• Score: 44.733160260712054
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove target knowledge without affecting unrelated semantics. This issue is especially pronounced since a single image often contains multiple entangled concepts, including both target concepts to be forgotten and contextual information that should be preserved. In this paper, we propose an interpretable concept-level unlearning framework for VLMs, which constructs a compact task-specific concept vocabulary from the forgetting set using a multimodal large language model. In addition to modality alignment, visual representations are decomposed into sparse, nonnegative combinations of semantic concepts, providing an explicit interface for fine-grained knowledge manipulation. Based on this decomposition, our method formulates unlearning as concept-level optimization, where target concepts are selectively suppressed while intra-instance non-target semantics and global cross-modal knowledge are preserved. Extensive experiments across both in-domain and out-of-domain forgetting settings demonstrate that our method enables more comprehensive target forgetting, better preserves non-target knowledge within the same image, and maintains competitive model utility compared with existing VLM unlearning methods.

Related papers

• Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning [17.479156121859827]
  We propose SAEParate, which organizes latent representations into concept-specific clusters via a concept-aware contrastive objective.<n>We also enhance the encoder with a GeLU-based nonlinear transformation to increase its expressive capacity under this separation objective.
  arXiv  Detail & Related papers  (2026-05-12T13:39:07Z)
• Null Space Constrained Contrastive Visual Forgetting for MLLM Unlearning [22.667378623339527]
  We introduce an MLLM unlearning approach that aims to forget target visual knowledge while preserving non-target visual knowledge and all textual knowledge.<n>First, we propose a Contrastive Visual Forgetting (CVF) mechanism to separate target visual knowledge from retained visual knowledge.<n>Second, we identify the null space associated with retained knowledge and constrain the unlearning process within this space, thereby significantly mitigating degradation in knowledge retention.
  arXiv  Detail & Related papers  (2026-05-07T09:18:58Z)
• A Concept is More Than a Word: Diversified Unlearning in Text-to-Image Diffusion Models [2.124297073085513]
  Concept unlearning is a promising direction for reducing the risks of harmful content generation in text-to-image diffusion models.<n>Existing approaches typically rely on keywords to identify the target concept to be unlearned.<n>We propose Diversified Unlearning, a distributional framework that represents a concept through a set of contextually diverse prompts.
  arXiv  Detail & Related papers  (2026-03-19T11:20:40Z)
• MeGU: Machine-Guided Unlearning with Target Feature Disentanglement [73.49657372882082]
  We propose a novel framework that guides unlearning through concept-aware re-alignment.<n>MeGU enables controlled and selective forgetting, effectively mitigating both under-unlearning and over-unlearning.
  arXiv  Detail & Related papers  (2026-02-19T05:20:31Z)
• AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models [63.05306474002547]
  Regulatory frameworks mandating the 'right to be forgotten' drive the need for machine unlearning.<n>We introduce AUVIC, a novel visual concept unlearning framework for MLLMs.<n>We show that AUVIC achieves state-of-the-art target forgetting rates while incurs minimal performance degradation on non-target concepts.
  arXiv  Detail & Related papers  (2025-11-14T13:35:32Z)
• Augmenting Continual Learning of Diseases with LLM-Generated Visual Concepts [1.1883838320818292]
  We propose a novel framework that harnesses visual concepts generated by large language models (LLMs) as discriminative semantic guidance.<n>Our method dynamically constructs a visual concept pool with a similarity-based filtering mechanism to prevent redundancy.<n>Through attention, the module can leverage the semantic knowledge from relevant visual concepts and produce class-representative fused features for classification.
  arXiv  Detail & Related papers  (2025-08-05T05:15:54Z)
• Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models [56.35484513848296]
  FADE (Fine grained Attenuation for Diffusion Erasure) is an adjacency-aware unlearning algorithm for text-to-image generative models.<n>It removes target concepts with minimal impact on correlated concepts, achieving a 12% improvement in retention performance over state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-25T15:49:48Z)
• Imitation Learning-based Implicit Semantic-aware Communication Networks: Multi-layer Representation and Collaborative Reasoning [68.63380306259742]
  Despite its promising potential, semantic communications and semantic-aware networking are still at their infancy. We propose a novel reasoning-based implicit semantic-aware communication network architecture that allows multiple tiers of CDC and edge servers to collaborate. We introduce a new multi-layer representation of semantic information taking into consideration both the hierarchical structure of implicit semantics as well as the personalized inference preference of individual users.
  arXiv  Detail & Related papers  (2022-10-28T13:26:08Z)
• Concept Learners for Few-Shot Learning [76.08585517480807]
  We propose COMET, a meta-learning method that improves generalization ability by learning to learn along human-interpretable concept dimensions. We evaluate our model on few-shot tasks from diverse domains, including fine-grained image classification, document categorization and cell type annotation.
  arXiv  Detail & Related papers  (2020-07-14T22:04:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.