Hierarchical Conformal Classification
By: Floris den Hengst , Inès Blin , Majid Mohammadi and more
Potential Business Impact:
Helps computers guess better by knowing how things relate.
Conformal prediction (CP) is a powerful framework for quantifying uncertainty in machine learning models, offering reliable predictions with finite-sample coverage guarantees. When applied to classification, CP produces a prediction set of possible labels that is guaranteed to contain the true label with high probability, regardless of the underlying classifier. However, standard CP treats classes as flat and unstructured, ignoring domain knowledge such as semantic relationships or hierarchical structure among class labels. This paper presents hierarchical conformal classification (HCC), an extension of CP that incorporates class hierarchies into both the structure and semantics of prediction sets. We formulate HCC as a constrained optimization problem whose solutions yield prediction sets composed of nodes at different levels of the hierarchy, while maintaining coverage guarantees. To address the combinatorial nature of the problem, we formally show that a much smaller, well-structured subset of candidate solutions suffices to ensure coverage while upholding optimality. An empirical evaluation on three new benchmarks consisting of audio, image, and text data highlights the advantages of our approach, and a user study shows that annotators significantly prefer hierarchical over flat prediction sets.
Similar Papers
Enhancing Conformal Prediction via Class Similarity
Machine Learning (CS)
Makes AI predictions more useful and accurate.
Cost-Sensitive Conformal Training with Provably Controllable Learning Bounds
Machine Learning (CS)
Makes AI predictions more accurate and reliable.
Provably Minimum-Length Conformal Prediction Sets for Ordinal Classification
Machine Learning (CS)
Helps doctors know how sure they are.