On Computing Probabilistic Abductive Explanations

Yacine Izza, Xuanxiang Huang, Alexey Ignatiev, Nina Narodytska, Martin C. Cooper, Joao Marques-Silva
{"title":"On Computing Probabilistic Abductive Explanations","authors":"Yacine Izza, Xuanxiang Huang, Alexey Ignatiev, Nina Narodytska, Martin C. Cooper, Joao Marques-Silva","doi":"10.48550/arXiv.2212.05990","DOIUrl":null,"url":null,"abstract":"The most widely studied explainable AI (XAI) approaches are unsound. This is the case with well-known model-agnostic explanation approaches, and it is also the case with approaches based on saliency maps. One solution is to consider intrinsic interpretability, which does not exhibit the drawback of unsoundness. Unfortunately, intrinsic interpretability can display unwieldy explanation redundancy. Formal explainability represents the alternative to these non-rigorous approaches, with one example being PI-explanations. Unfortunately, PI-explanations also exhibit important drawbacks, the most visible of which is arguably their size. Recently, it has been observed that the (absolute) rigor of PI-explanations can be traded off for a smaller explanation size, by computing the so-called relevant sets. Given some positive {\\delta}, a set S of features is {\\delta}-relevant if, when the features in S are fixed, the probability of getting the target class exceeds {\\delta}. However, even for very simple classifiers, the complexity of computing relevant sets of features is prohibitive, with the decision problem being NPPP-complete for circuit-based classifiers. In contrast with earlier negative results, this paper investigates practical approaches for computing relevant sets for a number of widely used classifiers that include Decision Trees (DTs), Naive Bayes Classifiers (NBCs), and several families of classifiers obtained from propositional languages. Moreover, the paper shows that, in practice, and for these families of classifiers, relevant sets are easy to compute. Furthermore, the experiments confirm that succinct sets of relevant features can be obtained for the families of classifiers considered.","PeriodicalId":13685,"journal":{"name":"Int. J. Approx. Reason.","volume":"57 1 1","pages":"108939"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Int. J. Approx. Reason.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2212.05990","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7

Abstract

The most widely studied explainable AI (XAI) approaches are unsound. This is the case with well-known model-agnostic explanation approaches, and it is also the case with approaches based on saliency maps. One solution is to consider intrinsic interpretability, which does not exhibit the drawback of unsoundness. Unfortunately, intrinsic interpretability can display unwieldy explanation redundancy. Formal explainability represents the alternative to these non-rigorous approaches, with one example being PI-explanations. Unfortunately, PI-explanations also exhibit important drawbacks, the most visible of which is arguably their size. Recently, it has been observed that the (absolute) rigor of PI-explanations can be traded off for a smaller explanation size, by computing the so-called relevant sets. Given some positive {\delta}, a set S of features is {\delta}-relevant if, when the features in S are fixed, the probability of getting the target class exceeds {\delta}. However, even for very simple classifiers, the complexity of computing relevant sets of features is prohibitive, with the decision problem being NPPP-complete for circuit-based classifiers. In contrast with earlier negative results, this paper investigates practical approaches for computing relevant sets for a number of widely used classifiers that include Decision Trees (DTs), Naive Bayes Classifiers (NBCs), and several families of classifiers obtained from propositional languages. Moreover, the paper shows that, in practice, and for these families of classifiers, relevant sets are easy to compute. Furthermore, the experiments confirm that succinct sets of relevant features can be obtained for the families of classifiers considered.
论计算概率溯因解释
最广泛研究的可解释人工智能(XAI)方法是不健全的。这是众所周知的模型不可知论解释方法的情况,也是基于显著性图的方法的情况。一种解决办法是考虑内在的可解释性,它不会表现出不合理的缺点。不幸的是,内在的可解释性会显示出笨拙的解释冗余。形式可解释性代表了这些非严格方法的替代方案,其中一个例子是pi解释。不幸的是,pi解释也显示出重要的缺点,其中最明显的是它们的规模。最近,人们观察到pi解释的(绝对)严谨性可以通过计算所谓的相关集来换取较小的解释规模。给定一个正的{\delta},如果S中的特征是固定的,得到目标类的概率超过{\delta},则特征集S是{\delta}相关的。然而,即使对于非常简单的分类器,计算相关特征集的复杂性也是令人难以接受的,对于基于电路的分类器来说,决策问题是nppp完全的。与之前的否定结果相反,本文研究了计算一些广泛使用的分类器的相关集的实用方法,这些分类器包括决策树(dt),朴素贝叶斯分类器(nbc)和从命题语言中获得的几种分类器。此外,本文还表明,在实践中,对于这些分类器族,相关集易于计算。此外,实验证实,对于所考虑的分类器族,可以获得简洁的相关特征集。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信