arXiv 2604.145192026-04-16cs.LGcs.CV

CI-CBM：用于可解释持续学习的类增量概念瓶颈模型

CI-CBM: Class-Incremental Concept Bottleneck Model for Interpretable Continual Learning

Department of Electrical and Computer Engineering, University of California San Diego（加州大学圣地亚哥分校电气与计算机工程系）；Department of Computer Science and Engineering, University of California San Diego（加州大学圣地亚哥分校计算机科学与工程系）；Halıcıoğlu Data Science Institute, University of California San Diego（加州大学圣地亚哥分校Halıcıoğlu数据科学研究所）

Amirhosein Javadi, Tuomas Oikarinen, Tara Javidi, Tsui-Wei Weng

备注：: 31 pages, 6 figures. Published in Transactions on Machine Learning Research (TMLR), 04/2026
发表信息：: Transactions on Machine Learning Research, 2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出CI-CBM模型，通过概念正则化和伪概念生成技术，在持续学习中保持可解释性，实验表明其在七种数据集上性能优异，比现有可解释方法平均提升36%。

摘要：

持续学习中灾难性遗忘仍是重大挑战，模型在新任务微调时易遗忘先前知识。在类增量学习（CIL）中，这一问题尤为突出。现有方法通常牺牲模型可解释性或准确性。为此，本文引入CI-CBM模型，利用概念正则化和伪概念生成等有效技术，在增量学习阶段维持可解释的决策过程。通过在七个数据集上的广泛评估，CI-CBM在性能上与黑盒模型相当，并在CIL中优于先前的可解释方法，平均准确率提升36%。实验表明，CI-CBM在单个输入上提供可解释的决策，并在全局上展示可理解的决策规则，从而证明在持续学习过程中可以保持人类可理解的概念，而不影响模型性能。本文方法在预训练和非预训练场景下均有效；后者在首次学习阶段从头训练骨干网络。代码已公开在github.com/importAmir/CI-CBM。

英文摘要：

Catastrophic forgetting remains a fundamental challenge in continual learning, in which models often forget previous knowledge when fine-tuned on a new task. This issue is especially pronounced in class incremental learning (CIL), which is the most challenging setting in continual learning. Existing methods to address catastrophic forgetting often sacrifice either model interpretability or accuracy. To address this challenge, we introduce ClassIncremental Concept Bottleneck Model (CI-CBM), which leverage effective techniques, including concept regularization and pseudo-concept generation to maintain interpretable decision processes throughout incremental learning phases. Through extensive evaluation on seven datasets, CI-CBM achieves comparable performance to black-box models and outperforms previous interpretable approaches in CIL, with an average 36% accuracy gain. CICBM provides interpretable decisions on individual inputs and understandable global decision rules, as shown in our experiments, thereby demonstrating that human understandable concepts can be maintained during incremental learning without compromising model performance. Our approach is effective in both pretrained and non-pretrained scenarios; in the latter, the backbone is trained from scratch during the first learning phase. Code is publicly available at github.com/importAmir/CI-CBM.

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。