Conformal Prediction Meets Long-tail Classification
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (28) · 23828-23836
DOI: 10.1609/aaai.v40i28.39558 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Shuqi Liu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Conformal Prediction (CP) is a popular method for uncertainty quantification that converts a pretrained model's point prediction into a prediction set, with the set size reflecting the model's confidence. Although existing CP methods are guaranteed to achieve marginal coverage, they often exhibit imbalanced coverage across classes under long-tailed label distributions, tending to over cover the head classes at the expense of under covering the remaining tail classes. This under coverage is particularly concerning, as it undermines the reliability of the prediction sets for minority classes, even with coverage ensured on average. In this paper, we propose the Tail-Aware Conformal Prediction (TACP) method to mitigate the under coverage of the tail classes by utilizing the long-tailed structure and narrowing the head-tail coverage gap. Theoretical analysis shows that it consistently achieves a smaller head-tail coverage gap than standard methods. To further improve coverage balance across all classes, we introduce an extension of TACP: soft TACP (sTACP) via a reweighting mechanism. The proposed framework can be combined with various non-conformity scores, and experiments on multiple long-tailed benchmark datasets demonstrate the effectiveness of our methods.
Zitieren
APA
Liu, S., Huang, J., & Ong, L. (2026). Conformal Prediction Meets Long-tail Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 40(28), 23828-23836. https://doi.org/10.1609/aaai.v40i28.39558
Vancouver
Liu S, Huang J, Ong L. Conformal Prediction Meets Long-tail Classification. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(28):23828-23836. doi:10.1609/aaai.v40i28.39558
BibTeX
@article{Liu2026,
author = {Liu, Shuqi and Huang, Jianguo and Ong, Luke},
title = {Conformal Prediction Meets Long-tail Classification},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {28},
pages = {23828--23836},
doi = {10.1609/aaai.v40i28.39558}
}
EUVIMED