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 static approaches 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-UCSD Birds, CheXpert and OAI datasets.

翻译：概念瓶颈模型（CBMs）是一种可解释的神经网络，它首先预测与预测任务相关的人类可理解概念的标签，然后基于这些概念标签的预测结果来预测最终标签。我们将CBMs扩展到交互式预测场景，其中模型可以请求人类协作员为某些概念提供标签。我们开发了一种交互策略，在预测阶段，该策略会选择请求哪些概念的标签，以最大程度地改进最终预测。我们证明，结合概念预测不确定性及概念对最终预测影响程度的简单策略能够实现强劲性能，并优于文献中提出的静态方法以及主动特征获取方法。在Caltech-UCSD Birds、CheXpert和OAI数据集上，我们展示了交互式CBM仅通过5次交互就能在竞争基线方法的基础上实现5-10%的准确率提升。