vix.ing · top · new · best · stats · spec

Controversy Rules - Discovering Regions Where Classifiers (Dis-)Agree\n Exceptionally

2018/08/22 by Oren Zeev-Ben-Mordehai, Zeev-Ben-Mordehai, Oren, Wouter Duivesteijn +3
Computer Science · #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Imbalanced Data Classification Techniques #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Statistical and Computational Modeling

paper · pdf · doi:10.48550/arxiv.1808.07243

openalex publication_date 2018/08/22 · openalex created_date 2022/08/04 · openalex updated_date 2026/07/28

Abstract

Finding regions for which there is higher controversy among different\nclassifiers is insightful with regards to the domain and our models. Such\nevaluation can falsify assumptions, assert some, or also, bring to the\nattention unknown phenomena. The present work describes an algorithm, which is\nbased on the Exceptional Model Mining framework, and enables that kind of\ninvestigations. We explore several public datasets and show the usefulness of\nthis approach in classification tasks. We show in this paper a few interesting\nobservations about those well explored datasets, some of which are general\nknowledge, and other that as far as we know, were not reported before.\n

Citations

Related