Recent work demonstrated the existence of Boolean functions for which Shapley values provide misleading information about the relative importance of features in rule-based explanations. Such misleading information was broadly categorized into a number of possible issues. Each of those issues relates with features being relevant or irrelevant for a prediction, and all are significant regarding the inadequacy of Shapley values for rule-based explainability. This earlier work devised a brute-force approach to identify Boolean functions, defined on small numbers of features, and also associated instances, which displayed such inadequacy-revealing issues, and so served as evidence to the inadequacy of Shapley values for rule-based explainability. However, an outstanding question is how frequently such inadequacy-revealing issues can occur for Boolean functions with arbitrary large numbers of features. It is plain that a brute-force approach would be unlikely to provide insights on how to tackle this question. This paper answers the above question by proving that, for any number of features, there exist Boolean functions that exhibit one or more inadequacy-revealing issues, thereby contributing decisive arguments against the use of Shapley values as the theoretical underpinning of feature-attribution methods in explainability.
ShaTS: A Shapley-based Explainability Method for Time Series Artificial Intelligence Models applied to Anomaly Detection in Industrial Internet of Things
Departamento de Ingeniería y Tecnología de Computadores, University of Murcia(计算机工程与技术部门,穆尔西亚大学)
Shapley-Value-Based Graph Sparsification for GNN Inference
Department of Intelligent Systems Engineering Indiana University Bloomington Bloomington Indiana USA;Department of Computer Science \& Engineering Texas A\&M University College Station Texas USA;Indiana University Bloomington;Texas A\&M University
Explaining Reinforcement Learning: A Counterfactual Shapley Values Approach
School of Engineering Mathematics and Technology, University of Bristol(布里斯托大学工程数学与技术学院);School of Electronic and Information Engineering, Tongji University(同济大学电子与信息工程学院)
Beyond Shapley: Efficient Computation of Asymmetric Shapley Values
Departamento de Computación, Facultad de Ciencias Exactas y Naturales, UBA(布宜诺斯艾利斯大学自然科学与精确科学学院计算机科学系);Instituto de Ciencias de la Computación (ICC), CONICET(国家科学与技术研究理事会计算机科学研究所)
AstraZeneca(阿斯利康);The University of Edinburgh(爱丁堡大学);Toulouse School of Economics(图卢兹经济学院);Institute for Advanced Study in Toulouse(图卢兹高等研究院);Central European University(中欧大学)
FlowX: Towards Explainable Graph Neural Networks via Message Flows
Texas A&M University(德克萨斯A&M大学);University of Science and Technology of China(中国科学技术大学);Beijing University of Posts and Telecommunications(北京邮电大学);West China Hospital(四川大学华西医院)
Amortized Linear-time Exact Shapley Value for Product-Kernel Methods
Rational Intelligence Lab, CISPA Helmholtz Center for Information Security(理性智能实验室,信息安全中心(CISPA));Department of Computer Science, Vrije Universiteit Amsterdam(阿姆斯特丹自由大学计算机科学系);Epistemic Intelligence & Computation Lab, College of Computing & Data Science, Nanyang Technological University(认知智能与计算实验室,南洋理工大学计算机与数据科学学院)
An exploration of the influence of path choice in game-theoretic attribution algorithms
Zest AI
我们比较机器学习可解释性方法的基础上的理论,原子(Shapley,1953年)和无穷小(Aumann和Shapley,1974年)的游戏,在理论和实验研究的模型和集成路径的选择如何影响所产生的功能属性。为了深入了解干预性Shapley值导致的归因差异(Sundararajan和Najmi,2019; Janzing等人,2019年; Chen等人,2019)和广义综合指数(GIG)(Merrill et al.,2019)我们注意到介入Shapley等效于沿$n!$路径的多路径积分,其中$n$是模型输入特征的数量。应用斯托克定理,我们表明,这两种方法的路径对称性的结果在相同的属性时,模型是由一个单独的功能和两个功能产品的总和可分离的功能。然后,我们进行了一系列的实验,不同程度的数据缺失,以证明如何干预沙普利的多路径方法可以产生不太一致的属性比单一的直线路径的奥曼-沙普利。我们认为这是因为介入Shapley所采用的多条路径远离训练数据流形,因此更有可能通过模型几乎没有支持的区域。在没有更有意义的路径选择的情况下,我们因此提倡直线路径,因为它几乎总是更接近数据流形。在直线路径属性算法中,GIG是唯一鲁棒的,因为它仍然会产生由决策树建模的原子游戏的Shapley值。
Unveiling Hidden Factors: Explainable AI for Feature Boosting in Speech Emotion Recognition
University of Québec (TÉLUQ)(魁北克大学(TÉLUQ));Concordia University(康考迪亚大学);Concordia Institute for Information Systems Engineering(康考迪亚信息系统工程学院);University of Québec at Montréal(蒙特利尔魁北克大学);Centre for Research and Intervention on Suicide, Ethical Issues and End-of-Life Practices(自杀、伦理问题与临终实践研究与干预中心)