为 XAI 制定以实例为中心的反事实算法基准:从白箱到黑箱

IF 23.8 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS
Catarina Moreira, Yu-Liang Chou, Chihcheng Hsieh, Chun Ouyang, João Pereira, Joaquim Jorge
{"title":"为 XAI 制定以实例为中心的反事实算法基准:从白箱到黑箱","authors":"Catarina Moreira, Yu-Liang Chou, Chihcheng Hsieh, Chun Ouyang, João Pereira, Joaquim Jorge","doi":"10.1145/3672553","DOIUrl":null,"url":null,"abstract":"<p>This study investigates the impact of machine learning models on the generation of counterfactual explanations by conducting a benchmark evaluation over three different types of models: a decision tree (fully transparent, interpretable, white-box model), a random forest (semi-interpretable, grey-box model), and a neural network (fully opaque, black-box model). We tested the counterfactual generation process using four algorithms (DiCE, WatcherCF, prototype, and GrowingSpheresCF) in the literature in 25 different datasets. Our findings indicate that: (1) Different machine learning models have little impact on the generation of counterfactual explanations; (2) Counterfactual algorithms based uniquely on proximity loss functions are not actionable and will not provide meaningful explanations; (3) One cannot have meaningful evaluation results without guaranteeing plausibility in the counterfactual generation. Algorithms that do not consider plausibility in their internal mechanisms will lead to biased and unreliable conclusions if evaluated with the current state-of-the-art metrics; (4) A counterfactual inspection analysis is strongly recommended to ensure a robust examination of counterfactual explanations and the potential identification of biases.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":null,"pages":null},"PeriodicalIF":23.8000,"publicationDate":"2024-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Box\",\"authors\":\"Catarina Moreira, Yu-Liang Chou, Chihcheng Hsieh, Chun Ouyang, João Pereira, Joaquim Jorge\",\"doi\":\"10.1145/3672553\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>This study investigates the impact of machine learning models on the generation of counterfactual explanations by conducting a benchmark evaluation over three different types of models: a decision tree (fully transparent, interpretable, white-box model), a random forest (semi-interpretable, grey-box model), and a neural network (fully opaque, black-box model). We tested the counterfactual generation process using four algorithms (DiCE, WatcherCF, prototype, and GrowingSpheresCF) in the literature in 25 different datasets. Our findings indicate that: (1) Different machine learning models have little impact on the generation of counterfactual explanations; (2) Counterfactual algorithms based uniquely on proximity loss functions are not actionable and will not provide meaningful explanations; (3) One cannot have meaningful evaluation results without guaranteeing plausibility in the counterfactual generation. Algorithms that do not consider plausibility in their internal mechanisms will lead to biased and unreliable conclusions if evaluated with the current state-of-the-art metrics; (4) A counterfactual inspection analysis is strongly recommended to ensure a robust examination of counterfactual explanations and the potential identification of biases.</p>\",\"PeriodicalId\":50926,\"journal\":{\"name\":\"ACM Computing Surveys\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":23.8000,\"publicationDate\":\"2024-06-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACM Computing Surveys\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1145/3672553\",\"RegionNum\":1,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, THEORY & METHODS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM Computing Surveys","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1145/3672553","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, THEORY & METHODS","Score":null,"Total":0}
引用次数: 0

摘要

本研究通过对三种不同类型的模型:决策树(完全透明、可解释、白盒模型)、随机森林(半可解释、灰盒模型)和神经网络(完全不透明、黑盒模型)进行基准评估,研究机器学习模型对反事实解释生成的影响。我们使用文献中的四种算法(DiCE、WatcherCF、原型和 GrowingSpheresCF)在 25 个不同的数据集中测试了反事实生成过程。我们的研究结果表明(1) 不同的机器学习模型对反事实解释的生成影响不大;(2) 完全基于近似损失函数的反事实算法不具有可操作性,也不会提供有意义的解释;(3) 如果不保证反事实生成的可信度,就无法获得有意义的评估结果。如果算法的内部机制不考虑可信度,那么用目前最先进的指标进行评估,就会得出有偏差和不可靠的结论;(4) 强烈建议进行反事实检查分析,以确保对反事实解释进行有力的检查,并找出可能存在的偏差。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Box

This study investigates the impact of machine learning models on the generation of counterfactual explanations by conducting a benchmark evaluation over three different types of models: a decision tree (fully transparent, interpretable, white-box model), a random forest (semi-interpretable, grey-box model), and a neural network (fully opaque, black-box model). We tested the counterfactual generation process using four algorithms (DiCE, WatcherCF, prototype, and GrowingSpheresCF) in the literature in 25 different datasets. Our findings indicate that: (1) Different machine learning models have little impact on the generation of counterfactual explanations; (2) Counterfactual algorithms based uniquely on proximity loss functions are not actionable and will not provide meaningful explanations; (3) One cannot have meaningful evaluation results without guaranteeing plausibility in the counterfactual generation. Algorithms that do not consider plausibility in their internal mechanisms will lead to biased and unreliable conclusions if evaluated with the current state-of-the-art metrics; (4) A counterfactual inspection analysis is strongly recommended to ensure a robust examination of counterfactual explanations and the potential identification of biases.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
ACM Computing Surveys
ACM Computing Surveys 工程技术-计算机:理论方法
CiteScore
33.20
自引率
0.60%
发文量
372
审稿时长
12 months
期刊介绍: ACM Computing Surveys is an academic journal that focuses on publishing surveys and tutorials on various areas of computing research and practice. The journal aims to provide comprehensive and easily understandable articles that guide readers through the literature and help them understand topics outside their specialties. In terms of impact, CSUR has a high reputation with a 2022 Impact Factor of 16.6. It is ranked 3rd out of 111 journals in the field of Computer Science Theory & Methods. ACM Computing Surveys is indexed and abstracted in various services, including AI2 Semantic Scholar, Baidu, Clarivate/ISI: JCR, CNKI, DeepDyve, DTU, EBSCO: EDS/HOST, and IET Inspec, among others.
×
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