SIGEcom Exchanges Annotated Reading List: Multiclass Calibration
ACM SIGecom Exchanges · 01.01.2026 · 23 (2) · 90-93
DOI: 10.1145/3817099.3817107 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM SIGecom Exchanges, online erschienen am 01.07.2026. Verfasst von Rabanus Derr und 1 weiteren Autor:innen. Die Arbeit nennt 10 Literaturangaben.
Abstract (Originalsprache)
ML model evaluation often takes one of two main approaches: risk minimization , associated with "high accuracy" or calibration , meaning that predictions are "trustworthy" and can be interpreted from a probabilistic lens. There is an extensive line of work which has studied the relationship between risk minimization and calibration, mostly focusing on the binary outcome setting. Even in the binary setting, there are a variety of proposed calibration metrics which non-trivially interact. In the multiclass label setting, the choices to be made are even more complex and particularly there are different semantics for different notions. Here, we briefly present an annotated reading list reviewing some of the proposed definitions and their relationships.
Zitieren
APA
Derr, R., & Finocchiaro, J. (2026). SIGEcom Exchanges Annotated Reading List: Multiclass Calibration. ACM SIGecom Exchanges, 23(2), 90-93. https://doi.org/10.1145/3817099.3817107
Vancouver
Derr R, Finocchiaro J. SIGEcom Exchanges Annotated Reading List: Multiclass Calibration. ACM SIGecom Exchanges. 2026;23(2):90-93. doi:10.1145/3817099.3817107
BibTeX
@article{Derr2026,
author = {Derr, Rabanus and Finocchiaro, Jessie},
title = {SIGEcom Exchanges Annotated Reading List: Multiclass Calibration},
journal = {ACM SIGecom Exchanges},
year = {2026},
volume = {23},
number = {2},
pages = {90--93},
doi = {10.1145/3817099.3817107}
}
EUVIMED