Poster
Classification with Conceptual Safeguards
Hailey Joren · Charles Marx · Berk Ustun
Halle B
Machine learning models are often used to automate routine tasks. In settings where mistakes are costly, we can trade off accuracy for coverage by abstaining from making a prediction on instances for which the model is uncertain. In this work, we present a new approach to selective classification in deep learning with concepts. Our approach constructs a concept bottleneck model where the front-end model can make predictions given soft concepts and leverage concept confirmation to improve coverage and performance under abstention. We develop techniques to propagate uncertainty and identify concepts for confirmation. We evaluate our approach on real-world and synthetic datasets, showing that it can improve coverage while maintaining performance across a range of tasks.