Decoupling Concept Bottleneck Model

Rui Zhang, Xingbo Du, Junchi Yan, Shihua Zhang

Keywords: Interpretability, Concept-based Model

Abstract: Concept Bottleneck Model (CBM) is a kind of powerful interpretable neural network, which utilizes high-level concepts to explain model decisions and interact with humans. However, CBM cannot always work as expected due to the troublesome collection and commonplace insufficiency of high-level concepts in real-world scenarios. In this paper, we theoretically reveal that insufficient concept information will induce the mixture of explicit and implicit information, which further leads to the inherent dilemma of concept and label distortions in CBM. Motivated by the proposed theorem, we present Decoupling Concept Bottleneck Model (DCBM), a novel concept-based model decoupling heterogeneous information into explicit and implicit concepts, while still retaining high prediction performance and interpretability. Extensive experiments expose the success in the alleviation of concept/label distortions, where DCBM achieves state-of-the-art performances in both concept and label learning tasks. Especially for situations where concepts are insufficient, DCBM significantly outperforms other models based on concept bottleneck and respectively achieves error rates 24.95% and 20.09% lower than other CBMs on concept/label prediction. Moreover, to express effective human-machine interactions for DCBM, we devise two algorithms based on mutual information (MI) estimation, including forward intervention and backward rectification, which can automatically correct labels and trace back to wrong concepts. The construction of the interaction regime can be formulated as a light min-max optimization problem achieved within minutes. Multiple experiments show that such interactions can effectively promote concept/label accuracy.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)

TL;DR: We analyze the concept/label trade-off for Concept Bottleneck Model (CBM) and propose a new interactive and interpretable AI system to alleviate this issue.