arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.00451cs.LG
收藏

可控概念瓶颈模型

Controllable Concept Bottleneck Models

Hongbin Lin, Chenyang Ren, Juangui Xu, Zhengyu Hu, Cheng-Long Wang, Yao Shu, Hui Xiong, Jingfeng Zhang, Di Wang, Lijie Hu

AI总结:

本文提出可控概念瓶颈模型,通过支持多层次的模型编辑功能,实现无需重新训练的高效可编辑CBMs,以适应动态变化的环境需求。

摘要:

概念瓶颈模型(CBMs)因其通过人类可理解的概念层来阐明预测过程的能力而受到广泛关注。然而,大多数先前研究集中在静态场景中,假设数据和概念是固定且干净的。在现实应用中,部署的模型需要持续维护:我们经常需要删除错误或敏感的数据(反向学习),纠正错误标记的概念,或纳入新获取的样本(增量学习)以适应不断变化的环境。因此,推导出无需从头开始重新训练的高效可编辑CBMs仍是一个重大挑战,尤其是在大规模应用中。为了解决这些挑战,我们提出了可控概念瓶颈模型(CCBMs)。具体而言,CCBMs支持三种粒度的模型编辑:概念-标签级别、概念级别和数据级别,后者包括数据删除和数据添加。CCBMs通过影响函数推导出数学上严谨的闭式近似,从而避免了重新训练的需要。实验结果证明了我们CCBMs的效率和适应性,证实了其在使动态且可信的CBMs方面的实际价值。

英文摘要:

Concept Bottleneck Models (CBMs) have garnered much attention for their ability to elucidate the prediction process through a human-understandable concept layer. However, most previous studies focused on static scenarios where the data and concepts are assumed to be fixed and clean. In real-world applications, deployed models require continuous maintenance: we often need to remove erroneous or sensitive data (unlearning), correct mislabeled concepts, or incorporate newly acquired samples (incremental learning) to adapt to evolving environments. Thus, deriving efficient editable CBMs without retraining from scratch remains a significant challenge, particularly in large-scale applications. To address these challenges, we propose Controllable Concept Bottleneck Models (CCBMs). Specifically, CCBMs support three granularities of model editing: concept-label-level, concept-level, and data-level, the latter of which encompasses both data removal and data addition. CCBMs enjoy mathematically rigorous closed-form approximations derived from influence functions that obviate the need for retraining. Experimental results demonstrate the efficiency and adaptability of our CCBMs, affirming their practical value in enabling dynamic and trustworthy CBMs.

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。

↑