Use of Fitness Sharing in the Local Rule-Based Explanations Method

Daniel A. Santos, J. A. Baranauskas, R. Tinós
{"title":"Use of Fitness Sharing in the Local Rule-Based Explanations Method","authors":"Daniel A. Santos, J. A. Baranauskas, R. Tinós","doi":"10.1109/LA-CCI48322.2021.9769789","DOIUrl":null,"url":null,"abstract":"Recent machine learning algorithms present remarkable results in many problems. However, the decisions made by some of these algorithms are very often difficult for human experts to interpret. Some recent works in the literature try to minimize this disadvantage, proposing algorithms that explain the decisions taken by any black-box model. One of these models is the Local Rule Based Explanations (LORE), that generates local explanations by using a Decision Tree (DT) that locally reproduces the decision boundaries of the black-box model. In LORE, the DT is trained by using an artificial dataset generated by a standard Genetic Algorithm (GA). In this paper, we show that the GA employed in LORE does not necessarily preserve the diversity of solutions in the final population. The diversity of the population is important to generate DTs that can more accurately reproduce the decision boundaries of the black-box model close to the instance to be explained. We then propose the use of fitness sharing in the GA in order to preserve the diversity of the population and generate local decision boundaries of the DT more similar to those of the black-box model. Experimental results show that LORE with fitness sharing generally produces better local explanations.","PeriodicalId":431041,"journal":{"name":"2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI)","volume":"342 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/LA-CCI48322.2021.9769789","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Recent machine learning algorithms present remarkable results in many problems. However, the decisions made by some of these algorithms are very often difficult for human experts to interpret. Some recent works in the literature try to minimize this disadvantage, proposing algorithms that explain the decisions taken by any black-box model. One of these models is the Local Rule Based Explanations (LORE), that generates local explanations by using a Decision Tree (DT) that locally reproduces the decision boundaries of the black-box model. In LORE, the DT is trained by using an artificial dataset generated by a standard Genetic Algorithm (GA). In this paper, we show that the GA employed in LORE does not necessarily preserve the diversity of solutions in the final population. The diversity of the population is important to generate DTs that can more accurately reproduce the decision boundaries of the black-box model close to the instance to be explained. We then propose the use of fitness sharing in the GA in order to preserve the diversity of the population and generate local decision boundaries of the DT more similar to those of the black-box model. Experimental results show that LORE with fitness sharing generally produces better local explanations.
适应度共享在局部规则解释方法中的应用
最近的机器学习算法在许多问题上都取得了显著的成果。然而,其中一些算法做出的决定对于人类专家来说通常很难解释。最近的一些文献试图将这一缺点最小化,提出了解释任何黑盒模型所做决定的算法。其中一种模型是基于局部规则的解释(LORE),它通过使用决策树(DT)生成局部解释,该决策树在局部再现黑箱模型的决策边界。在LORE中,DT通过使用由标准遗传算法(GA)生成的人工数据集进行训练。在本文中,我们证明了在LORE中使用的遗传算法不一定能保持最终种群中解的多样性。种群的多样性对于生成能够更准确地再现接近待解释实例的黑箱模型的决策边界的dt非常重要。然后,我们提出在遗传算法中使用适应度共享,以保持种群的多样性,并生成更类似于黑盒模型的DT的局部决策边界。实验结果表明,具有适应度共享的LORE通常能产生更好的局部解释。
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