论文标题
互动概念瓶颈模型
Interactive Concept Bottleneck Models
论文作者
论文摘要
概念瓶颈模型（CBM）是可解释的神经网络，它首先预测与预测任务相关的人解剖概念的标签，然后根据概念标签预测来预测最终标签。我们将CBM扩展到交互式预测设置，在该设置中，该模型可以将人类合作者查询标签中的某些概念。我们制定了一种交互策略，该策略在预测时选择哪些概念要求标签以最大程度地改善最终预测。我们证明，将概念预测的不确定性和概念对最终预测的影响结合起来的简单政策可以实现强大的效果，并且优于静态方法以及文献中提出的积极特征获取方法。我们表明，交互式CBM可以实现5-10％的准确性提高，而在Caltech-UCSD鸟类，CHEXPERT和OAI数据集的竞争基准中仅进行了5个相互作用。
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.
