CeFlow:使用规范化流的表格数据的鲁棒和有效的反事实解释框架

Tri Dung Duong, Qian Li, Guandong Xu
{"title":"CeFlow:使用规范化流的表格数据的鲁棒和有效的反事实解释框架","authors":"Tri Dung Duong, Qian Li, Guandong Xu","doi":"10.48550/arXiv.2303.14668","DOIUrl":null,"url":null,"abstract":"Counterfactual explanation is a form of interpretable machine learning that generates perturbations on a sample to achieve the desired outcome. The generated samples can act as instructions to guide end users on how to observe the desired results by altering samples. Although state-of-the-art counterfactual explanation methods are proposed to use variational autoencoder (VAE) to achieve promising improvements, they suffer from two major limitations: 1) the counterfactuals generation is prohibitively slow, which prevents algorithms from being deployed in interactive environments; 2) the counterfactual explanation algorithms produce unstable results due to the randomness in the sampling procedure of variational autoencoder. In this work, to address the above limitations, we design a robust and efficient counterfactual explanation framework, namely CeFlow, which utilizes normalizing flows for the mixed-type of continuous and categorical features. Numerical experiments demonstrate that our technique compares favorably to state-of-the-art methods. We release our source at https://github.com/tridungduong16/fairCE.git for reproducing the results.","PeriodicalId":91995,"journal":{"name":"Advances in Knowledge Discovery and Data Mining : 21st Pacific-Asia Conference, PAKDD 2017, Jeju, South Korea, May 23-26, 2017, Proceedings. Part I. Pacific-Asia Conference on Knowledge Discovery and Data Mining (21st : 2017 : Cheju Isl...","volume":"9 1","pages":"133-144"},"PeriodicalIF":0.0000,"publicationDate":"2023-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"CeFlow: A Robust and Efficient Counterfactual Explanation Framework for Tabular Data using Normalizing Flows\",\"authors\":\"Tri Dung Duong, Qian Li, Guandong Xu\",\"doi\":\"10.48550/arXiv.2303.14668\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Counterfactual explanation is a form of interpretable machine learning that generates perturbations on a sample to achieve the desired outcome. The generated samples can act as instructions to guide end users on how to observe the desired results by altering samples. Although state-of-the-art counterfactual explanation methods are proposed to use variational autoencoder (VAE) to achieve promising improvements, they suffer from two major limitations: 1) the counterfactuals generation is prohibitively slow, which prevents algorithms from being deployed in interactive environments; 2) the counterfactual explanation algorithms produce unstable results due to the randomness in the sampling procedure of variational autoencoder. In this work, to address the above limitations, we design a robust and efficient counterfactual explanation framework, namely CeFlow, which utilizes normalizing flows for the mixed-type of continuous and categorical features. Numerical experiments demonstrate that our technique compares favorably to state-of-the-art methods. We release our source at https://github.com/tridungduong16/fairCE.git for reproducing the results.\",\"PeriodicalId\":91995,\"journal\":{\"name\":\"Advances in Knowledge Discovery and Data Mining : 21st Pacific-Asia Conference, PAKDD 2017, Jeju, South Korea, May 23-26, 2017, Proceedings. Part I. Pacific-Asia Conference on Knowledge Discovery and Data Mining (21st : 2017 : Cheju Isl...\",\"volume\":\"9 1\",\"pages\":\"133-144\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-03-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Advances in Knowledge Discovery and Data Mining : 21st Pacific-Asia Conference, PAKDD 2017, Jeju, South Korea, May 23-26, 2017, Proceedings. Part I. Pacific-Asia Conference on Knowledge Discovery and Data Mining (21st : 2017 : Cheju Isl...\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2303.14668\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advances in Knowledge Discovery and Data Mining : 21st Pacific-Asia Conference, PAKDD 2017, Jeju, South Korea, May 23-26, 2017, Proceedings. Part I. Pacific-Asia Conference on Knowledge Discovery and Data Mining (21st : 2017 : Cheju Isl...","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2303.14668","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

反事实解释是一种可解释的机器学习形式,它在样本上产生扰动以达到预期的结果。生成的样品可以作为指导,指导最终用户如何通过改变样品来观察所需的结果。尽管最先进的反事实解释方法被提出使用变分自编码器(VAE)来实现有希望的改进,但它们受到两个主要限制:1)反事实生成非常缓慢,这阻碍了算法在交互式环境中部署;2)由于变分自编码器采样过程的随机性,反事实解释算法产生的结果不稳定。在这项工作中,为了解决上述限制,我们设计了一个鲁棒且高效的反事实解释框架,即CeFlow,它利用规范化流来处理连续和分类特征的混合类型。数值实验表明,我们的技术优于最先进的方法。我们在https://github.com/tridungduong16/fairCE.git上发布了我们的源代码以复制结果。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
CeFlow: A Robust and Efficient Counterfactual Explanation Framework for Tabular Data using Normalizing Flows
Counterfactual explanation is a form of interpretable machine learning that generates perturbations on a sample to achieve the desired outcome. The generated samples can act as instructions to guide end users on how to observe the desired results by altering samples. Although state-of-the-art counterfactual explanation methods are proposed to use variational autoencoder (VAE) to achieve promising improvements, they suffer from two major limitations: 1) the counterfactuals generation is prohibitively slow, which prevents algorithms from being deployed in interactive environments; 2) the counterfactual explanation algorithms produce unstable results due to the randomness in the sampling procedure of variational autoencoder. In this work, to address the above limitations, we design a robust and efficient counterfactual explanation framework, namely CeFlow, which utilizes normalizing flows for the mixed-type of continuous and categorical features. Numerical experiments demonstrate that our technique compares favorably to state-of-the-art methods. We release our source at https://github.com/tridungduong16/fairCE.git for reproducing the results.
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
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