Multiclass Performance Metric Elicitation
Abstract
Metric Elicitation is a principled framework for selecting the performance metric that best reflects implicit user preferences. However, available strategies have so far been limited to binary classification. In this paper, we propose novel strategies for eliciting multiclass classification performance metrics using only relative preference feedback. We also show that the strategies are robust to both finite sample and feedback noise.
Cite
Text
Hiranandani et al. "Multiclass Performance Metric Elicitation." Neural Information Processing Systems, 2019.Markdown
[Hiranandani et al. "Multiclass Performance Metric Elicitation." Neural Information Processing Systems, 2019.](https://mlanthology.org/neurips/2019/hiranandani2019neurips-multiclass/)BibTeX
@inproceedings{hiranandani2019neurips-multiclass,
title = {{Multiclass Performance Metric Elicitation}},
author = {Hiranandani, Gaurush and Boodaghians, Shant and Mehta, Ruta and Koyejo, Oluwasanmi O},
booktitle = {Neural Information Processing Systems},
year = {2019},
pages = {9356-9365},
url = {https://mlanthology.org/neurips/2019/hiranandani2019neurips-multiclass/}
}