Fast Online Value-Maximizing Prediction Sets with Conformal Cost Control
This work addresses the need for reliable and efficient set-valued predictions in real-world applications like healthcare, where balancing value and cost is critical, though it is incremental in building on prior conformal prediction methods.
The authors tackled the problem of making set-valued predictions that maximize value while controlling cost in multi-label scenarios, such as medical diagnosis, and developed FavMac, a pipeline that achieves higher value than baselines while maintaining strict cost control with distribution-free guarantees.
Many real-world multi-label prediction problems involve set-valued predictions that must satisfy specific requirements dictated by downstream usage. We focus on a typical scenario where such requirements, separately encoding $\textit{value}$ and $\textit{cost}$, compete with each other. For instance, a hospital might expect a smart diagnosis system to capture as many severe, often co-morbid, diseases as possible (the value), while maintaining strict control over incorrect predictions (the cost). We present a general pipeline, dubbed as FavMac, to maximize the value while controlling the cost in such scenarios. FavMac can be combined with almost any multi-label classifier, affording distribution-free theoretical guarantees on cost control. Moreover, unlike prior works, it can handle real-world large-scale applications via a carefully designed online update mechanism, which is of independent interest. Our methodological and theoretical contributions are supported by experiments on several healthcare tasks and synthetic datasets - FavMac furnishes higher value compared with several variants and baselines while maintaining strict cost control. Our code is available at https://github.com/zlin7/FavMac