arrow
返回

Understanding imbalanced data: XAI & interpretable ML framework

delete2024-01-16
delete1
delete
OA
AI
D
Damien Dablain
C
Colin Bellinger
B
Bartosz Krawczyk
D
David W. Aha
N
Nitesh V. Chawla *
DOI:10.1007/s10994-023-06414-wdelete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
There is a gap between current methods that explain deep learning models that work on imbalanced image data and the needs of the imbalanced learning community. Existing methods that explain imbalanced data are geared toward binary classification, single layer machine learning models and low dimensional data. Current eXplainable Artificial Intelligence (XAI) techniques for vision data mainly focus on mapping predictions of specific instances to inputs, instead of examining global data properties and complexities of entire classes. Therefore, there is a need for a framework that is tailored to modern deep networks, that incorporates large, high dimensional, multi-class datasets, and uncovers data complexities commonly found in imbalanced data. We propose a set of techniques that can be used by both deep learning model users to identify, visualize and understand class prototypes, sub-concepts and outlier instances; and by imbalanced learning algorithm developers to detect features and class exemplars that are key to model performance. The components of our framework can be applied sequentially in their entirety or individually, making it fully flexible to the user's specific needs (https://github.com/dd1github/XAI_for_Imbalanced_Learning).
Keyword:
Explainable AI
Interpretable ML
Imbalanced learning
Deep learning

期刊

Machine Learning 封面图
Machine Learning
IF:
2.9
论文数:
2.7K
被引数:
3.4W

机构

U
University of Notre Dame
学者数:
1.2W
论文数: 1.1W
被引数: 1.7W
V
Virginia Commonwealth University
学者数:
2.2W
论文数: 1.8W
被引数: 1.9W
United States Department of Defense 封面图
United States Department of Defense
学者数:
2.8W
论文数: 2.3W
被引数: 172
N
National Research Council Canada
学者数:
7.9K
论文数: 7.9K
被引数: 6.8K
学者 查看更多机构
引用论文

引用论文

Understanding CNN fragility when learning with imbalanced data
err2023-04-11
err14
errOAAI
errDablain, Damien; Jacobson, Kristen N.; Bellinger, Colin; Roberts, Mark; Chawla, Nitesh V.
err分享
err收藏
Protonation Values for Other Ligands
err1976-01-01
err0
PREAI
errRobert M. Smith; Arthur E. Martell
err分享
err收藏
err分享
err收藏
学者 查看更多内容