AAAI 2025technical0 citations
Things Machine Learning Models Know That They Don’t Know
Salvatore Ruggieri, Andrea Pugnana
Abstract
This paper surveys Machine Learning approaches to build predictive models that know what they don't know. The consequential action of this knowledge can consist of abstaining from providing an output (rejection), deferring to another model (dynamic model selection), deferring to a human expert (learning to defer), or informing the user (uncertainty estimation). We formally state the problems each approach solves and point to key references. We discuss open issues that deserve investigation from the scientific community.
BibTeX
@article{Ruggieri_Pugnana_2025, title={Things Machine Learning Models Know That They Don’t Know}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/35094}, DOI={10.1609/aaai.v39i27.35094}, abstractNote={This paper surveys Machine Learning approaches to build predictive models that know what they don’t know. The consequential action of this knowledge can consist of abstaining from providing an output (rejection), deferring to another model (dynamic model selection), deferring to a human expert (learning to defer), or informing the user (uncertainty estimation). We formally state the problems each approach solves and point to key references. We discuss open issues that deserve investigation from the scientific community.}, number={27}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Ruggieri, Salvatore and Pugnana, Andrea}, year={2025}, month={Apr.}, pages={28684-28693} }