Skip to yearly menu bar Skip to main content

Workshop: Human in the Loop Learning (HiLL) Workshop at NeurIPS 2022

Interactive Concept Bottleneck Models

Kushal Chauhan · Rishabh Tiwari · Jan Freyberg · Pradeep Shenoy · Krishnamurthy Dvijotham


Concept bottleneck models (CBMs) are interpretable neural networks that first predict labels for human-interpretable concepts relevant to the prediction task, and then predict the final label based on the concept label predictions. We extend CBMs to interactive prediction settings where the model can query a human collaborator for the label to some concepts. We develop an interaction policy that, at prediction time, chooses which concepts to request a label for so as to maximally improve the final prediction. We demonstrate that a simple policy combining concept prediction uncertainty and influence of the concept on the final prediction achieves strong performance and outperforms a static approach proposed in as well as active feature acquisition methods proposed in the literature. We show that the interactive CBM can achieve accuracy gains of 5-10\% with only 5 interactions over competitive baselines on the Caltech UCSB Birds dataset and the Chexpert dataset.

Chat is not available.