Alejandro Kuratomi, Ioanna Miliou, Zed Lee, Tony Lindgren, Panagiotis Papapetrou
{"title":"Ijuice: integer JUstIfied counterfactual explanations","authors":"Alejandro Kuratomi, Ioanna Miliou, Zed Lee, Tony Lindgren, Panagiotis Papapetrou","doi":"10.1007/s10994-024-06530-1","DOIUrl":null,"url":null,"abstract":"<p>Counterfactual explanations modify the feature values of an instance in order to alter its prediction from an undesired to a desired label. As such, they are highly useful for providing trustworthy interpretations of decision-making in domains where complex and opaque machine learning algorithms are utilized. To guarantee their quality and promote user trust, they need to satisfy the <i>faithfulness</i> desideratum, when supported by the data distribution. We hereby propose a counterfactual generation algorithm for mixed-feature spaces that prioritizes faithfulness through <i>k-justification</i>, a novel counterfactual property introduced in this paper. The proposed algorithm employs a graph representation of the search space and provides counterfactuals by solving an integer program. In addition, the algorithm is classifier-agnostic and is not dependent on the order in which the feature space is explored. In our empirical evaluation, we demonstrate that it guarantees k-justification while showing comparable performance to state-of-the-art methods in <i>feasibility</i>, <i>sparsity</i>, and <i>proximity</i>.</p>","PeriodicalId":49900,"journal":{"name":"Machine Learning","volume":null,"pages":null},"PeriodicalIF":4.3000,"publicationDate":"2024-03-26","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/s10994-024-06530-1","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
Abstract
Counterfactual explanations modify the feature values of an instance in order to alter its prediction from an undesired to a desired label. As such, they are highly useful for providing trustworthy interpretations of decision-making in domains where complex and opaque machine learning algorithms are utilized. To guarantee their quality and promote user trust, they need to satisfy the faithfulness desideratum, when supported by the data distribution. We hereby propose a counterfactual generation algorithm for mixed-feature spaces that prioritizes faithfulness through k-justification, a novel counterfactual property introduced in this paper. The proposed algorithm employs a graph representation of the search space and provides counterfactuals by solving an integer program. In addition, the algorithm is classifier-agnostic and is not dependent on the order in which the feature space is explored. In our empirical evaluation, we demonstrate that it guarantees k-justification while showing comparable performance to state-of-the-art methods in feasibility, sparsity, and proximity.
反事实解释可以修改实例的特征值,从而将其预测从不佳标签变为理想标签。因此,在使用复杂而不透明的机器学习算法的领域中,反事实解释对于提供可信的决策解释非常有用。为了保证其质量并提高用户信任度,它们需要在数据分布的支持下满足忠实性要求。在此,我们提出了一种混合特征空间的反事实生成算法,该算法通过 k-justification 优先考虑忠实性,这是本文引入的一种新颖的反事实属性。本文提出的算法采用搜索空间的图表示法,通过求解整数程序来提供反事实。此外,该算法与分类器无关,也不依赖于探索特征空间的顺序。在实证评估中,我们证明了该算法在可行性、稀疏性和接近性方面与最先进的方法性能相当,同时还保证了 k 的合理性。
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.