Saved in:
Bibliographic Details
Main Authors: Cooper, Martin, Amgoud, Leila
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.12154
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910610523947008
author Cooper, Martin
Amgoud, Leila
author_facet Cooper, Martin
Amgoud, Leila
contents Abductive explanations (AXp's) are widely used for understanding decisions of classifiers. Existing definitions are suitable when features are independent. However, we show that ignoring constraints when they exist between features may lead to an explosion in the number of redundant or superfluous AXp's. We propose three new types of explanations that take into account constraints and that can be generated from the whole feature space or from a sample (such as a dataset). They are based on a key notion of coverage of an explanation, the set of instances it explains. We show that coverage is powerful enough to discard redundant and superfluous AXp's. For each type, we analyse the complexity of finding an explanation and investigate its formal properties. The final result is a catalogue of different forms of AXp's with different complexities and different formal guarantees.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12154
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Abductive explanations of classifiers under constraints: Complexity and properties
Cooper, Martin
Amgoud, Leila
Artificial Intelligence
68T01, 68Q17
I.2.4
Abductive explanations (AXp's) are widely used for understanding decisions of classifiers. Existing definitions are suitable when features are independent. However, we show that ignoring constraints when they exist between features may lead to an explosion in the number of redundant or superfluous AXp's. We propose three new types of explanations that take into account constraints and that can be generated from the whole feature space or from a sample (such as a dataset). They are based on a key notion of coverage of an explanation, the set of instances it explains. We show that coverage is powerful enough to discard redundant and superfluous AXp's. For each type, we analyse the complexity of finding an explanation and investigate its formal properties. The final result is a catalogue of different forms of AXp's with different complexities and different formal guarantees.
title Abductive explanations of classifiers under constraints: Complexity and properties
topic Artificial Intelligence
68T01, 68Q17
I.2.4
url https://arxiv.org/abs/2409.12154