ICED: 通过可解释的概念分解实现概念级机器去学习
ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
AI总结：
本文提出ICED框架，通过多模态大语言模型构建任务特定概念词汇，实现VLMs中概念级去学习，有效去除目标知识并保留非目标语义，实验表明其在目标遗忘和模型效用方面表现优异。
摘要：
在视觉-语言模型（VLMs）中，机器去学习通常在图像或实例级别进行，难以精确删除目标知识而不影响无关语义。本文提出一种可解释的概念级去学习框架，通过多模态大语言模型从遗忘集构建紧凑的任务特定概念词汇。除了模态对齐外，视觉表示被分解为稀疏、非负的语义概念组合，提供细粒度知识操作的显式接口。基于此分解，我们的方法将去学习转化为概念级优化，选择性抑制目标概念，同时保留实例内非目标语义和全局跨模态知识。在域内和域外遗忘设置的广泛实验表明，我们的方法实现了更全面的目标遗忘，更好地保留同一图像内的非目标知识，并与现有VLM去学习方法保持竞争力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
