冰川:引导时间序列分类的局部约束反事实解释

IF 4.3 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Machine Learning Pub Date : 2024-03-13 DOI:10.1007/s10994-023-06502-x
Zhendong Wang, Isak Samsten, Ioanna Miliou, Rami Mochaourab, Panagiotis Papapetrou
{"title":"冰川:引导时间序列分类的局部约束反事实解释","authors":"Zhendong Wang, Isak Samsten, Ioanna Miliou, Rami Mochaourab, Panagiotis Papapetrou","doi":"10.1007/s10994-023-06502-x","DOIUrl":null,"url":null,"abstract":"<p>In machine learning applications, there is a need to obtain predictive models of high performance and, most importantly, to allow end-users and practitioners to understand and act on their predictions. One way to obtain such understanding is via counterfactuals, that provide sample-based explanations in the form of recommendations on which features need to be modified from a test example so that the classification outcome of a given classifier changes from an undesired outcome to a desired one. This paper focuses on the domain of time series classification, more specifically, on defining counterfactual explanations for univariate time series. We propose <span>Glacier</span>, a model-agnostic method for generating locally-constrained counterfactual explanations for time series classification using gradient search either on the original space or on a latent space that is learned through an auto-encoder. An additional flexibility of our method is the inclusion of constraints on the counterfactual generation process that favour applying changes to particular time series points or segments while discouraging changing others. The main purpose of these constraints is to ensure more reliable counterfactuals, while increasing the efficiency of the counterfactual generation process. Two particular types of constraints are considered, i.e., example-specific constraints and global constraints. We conduct extensive experiments on 40 datasets from the UCR archive, comparing different instantiations of <span>Glacier</span> against three competitors. Our findings suggest that <span>Glacier</span> outperforms the three competitors in terms of two common metrics for counterfactuals, i.e., proximity and compactness. Moreover, <span>Glacier</span> obtains comparable counterfactual validity compared to the best of the three competitors. Finally, when comparing the unconstrained variant of <span>Glacier</span> to the constraint-based variants, we conclude that the inclusion of example-specific and global constraints yields a good performance while demonstrating the trade-off between the different metrics.</p>","PeriodicalId":49900,"journal":{"name":"Machine Learning","volume":null,"pages":null},"PeriodicalIF":4.3000,"publicationDate":"2024-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Glacier: guided locally constrained counterfactual explanations for time series classification\",\"authors\":\"Zhendong Wang, Isak Samsten, Ioanna Miliou, Rami Mochaourab, Panagiotis Papapetrou\",\"doi\":\"10.1007/s10994-023-06502-x\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>In machine learning applications, there is a need to obtain predictive models of high performance and, most importantly, to allow end-users and practitioners to understand and act on their predictions. One way to obtain such understanding is via counterfactuals, that provide sample-based explanations in the form of recommendations on which features need to be modified from a test example so that the classification outcome of a given classifier changes from an undesired outcome to a desired one. This paper focuses on the domain of time series classification, more specifically, on defining counterfactual explanations for univariate time series. We propose <span>Glacier</span>, a model-agnostic method for generating locally-constrained counterfactual explanations for time series classification using gradient search either on the original space or on a latent space that is learned through an auto-encoder. An additional flexibility of our method is the inclusion of constraints on the counterfactual generation process that favour applying changes to particular time series points or segments while discouraging changing others. The main purpose of these constraints is to ensure more reliable counterfactuals, while increasing the efficiency of the counterfactual generation process. Two particular types of constraints are considered, i.e., example-specific constraints and global constraints. We conduct extensive experiments on 40 datasets from the UCR archive, comparing different instantiations of <span>Glacier</span> against three competitors. Our findings suggest that <span>Glacier</span> outperforms the three competitors in terms of two common metrics for counterfactuals, i.e., proximity and compactness. Moreover, <span>Glacier</span> obtains comparable counterfactual validity compared to the best of the three competitors. Finally, when comparing the unconstrained variant of <span>Glacier</span> to the constraint-based variants, we conclude that the inclusion of example-specific and global constraints yields a good performance while demonstrating the trade-off between the different metrics.</p>\",\"PeriodicalId\":49900,\"journal\":{\"name\":\"Machine Learning\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2024-03-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Machine Learning\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1007/s10994-023-06502-x\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Machine Learning","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s10994-023-06502-x","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

在机器学习应用中,需要获得高性能的预测模型,最重要的是,要让最终用户和从业人员能够理解其预测结果,并根据预测结果采取行动。反事实是获得这种理解的一种方法,它以建议的形式提供基于样本的解释,说明需要从测试示例中修改哪些特征,从而使给定分类器的分类结果从不尽人意变为理想结果。本文的重点是时间序列分类领域,更具体地说,是定义单变量时间序列的反事实解释。我们提出了一种与模型无关的方法--Glacier,这种方法可以在原始空间或通过自动编码器学习的潜在空间上使用梯度搜索,为时间序列分类生成局部受限的反事实解释。我们的方法还具有额外的灵活性,即在反事实生成过程中加入了一些约束条件,这些约束条件有利于对特定的时间序列点或片段进行更改,而不鼓励更改其他点或片段。这些约束的主要目的是确保更可靠的反事实,同时提高反事实生成过程的效率。我们考虑了两种特殊类型的约束,即特定实例约束和全局约束。我们在 UCR 档案中的 40 个数据集上进行了广泛的实验,将 Glacier 的不同实例与三个竞争对手进行了比较。我们的研究结果表明,Glacier 在反事实的两个通用指标(即接近性和紧凑性)方面优于三个竞争对手。此外,Glacier 还获得了与三位竞争者中最好的一位相当的反事实有效性。最后,在比较 Glacier 的无约束变体和基于约束的变体时,我们得出结论:包含特定实例约束和全局约束会产生良好的性能,同时证明了不同指标之间的权衡。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Glacier: guided locally constrained counterfactual explanations for time series classification

In machine learning applications, there is a need to obtain predictive models of high performance and, most importantly, to allow end-users and practitioners to understand and act on their predictions. One way to obtain such understanding is via counterfactuals, that provide sample-based explanations in the form of recommendations on which features need to be modified from a test example so that the classification outcome of a given classifier changes from an undesired outcome to a desired one. This paper focuses on the domain of time series classification, more specifically, on defining counterfactual explanations for univariate time series. We propose Glacier, a model-agnostic method for generating locally-constrained counterfactual explanations for time series classification using gradient search either on the original space or on a latent space that is learned through an auto-encoder. An additional flexibility of our method is the inclusion of constraints on the counterfactual generation process that favour applying changes to particular time series points or segments while discouraging changing others. The main purpose of these constraints is to ensure more reliable counterfactuals, while increasing the efficiency of the counterfactual generation process. Two particular types of constraints are considered, i.e., example-specific constraints and global constraints. We conduct extensive experiments on 40 datasets from the UCR archive, comparing different instantiations of Glacier against three competitors. Our findings suggest that Glacier outperforms the three competitors in terms of two common metrics for counterfactuals, i.e., proximity and compactness. Moreover, Glacier obtains comparable counterfactual validity compared to the best of the three competitors. Finally, when comparing the unconstrained variant of Glacier to the constraint-based variants, we conclude that the inclusion of example-specific and global constraints yields a good performance while demonstrating the trade-off between the different metrics.

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
Machine Learning
Machine Learning 工程技术-计算机:人工智能
CiteScore
11.00
自引率
2.70%
发文量
162
审稿时长
3 months
期刊介绍: Machine Learning serves as a global platform dedicated to computational approaches in learning. The journal reports substantial findings on diverse learning methods applied to various problems, offering support through empirical studies, theoretical analysis, or connections to psychological phenomena. It demonstrates the application of learning methods to solve significant problems and aims to enhance the conduct of machine learning research with a focus on verifiable and replicable evidence in published papers.
期刊最新文献
On metafeatures’ ability of implicit concept identification Persistent Laplacian-enhanced algorithm for scarcely labeled data classification Towards a foundation large events model for soccer Conformal prediction for regression models with asymmetrically distributed errors: application to aircraft navigation during landing maneuver In-game soccer outcome prediction with offline reinforcement learning
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1