As Machine Learning (ML) is now widely applied in many domains, in both research and industry, an understanding of what is happening inside the black box is becoming a growing demand, especially by non-experts of these models. Several approaches had thus been developed to provide clear insights of a model prediction for a particular observation but at the cost of long computation time or restrictive hypothesis that does not fully take into account interaction between attributes. This paper provides methods based on the detection of relevant groups of attributes -- named coalitions -- influencing a prediction and compares them with the literature. Our results show that these coalitional methods are more efficient than existing ones such as SHapley Additive exPlanation (SHAP). Computation time is shortened while preserving an acceptable accuracy of individual prediction explanations. Therefore, this enables wider practical use of explanation methods to increase trust between developed ML models, end-users, and whoever impacted by any decision where these models played a role.
The Shapley Value of coalition of variables provides better explanations
虽然Shapley值（SV）是解释机器学习模型的黄金标准之一，但我们发现它们仍然知之甚少，特别是在存在分类变量或低重要性变量的情况下。例如，我们表明，流行的做法，包括在虚拟变量的SV求和是错误的，因为它提供了错误的估计模型中的所有SV，并意味着虚假的解释。基于零和积极联盟的识别，以及SV的联盟版本，我们提供了一个正确的计算和推断的重要变量。此外，一个Python库（所有的实验和模拟都可以用公共可用的库Active Coalition of Variables复制，https：//www.github.com/salimamoukou/acv00），该库为基于树的模型计算可靠的条件期望和SV，并与玩具模型和真实数据集上的最先进算法进行比较。
A unified framework for evaluating the robustness of machine-learning interpretability for prospect risking
Center for Energy and Geo Processing (CeGP)（能源与地球处理中心）；Omni Lab for Intelligent Visual Engineering and Science (OLIVES)（智能视觉工程与科学实验室）；School of Electrical and Computer Engineering（电气与计算机工程学院）；Georgia Institute of Technology（佐治亚理工学院）
Exploring Data Augmentation and Resampling Strategies for Transformer-Based Models to Address Class Imbalance in AI Scoring of Scientific Explanations in NGSS Classroom
Michigan State University（密歇根州立大学）；CREATE for STEM（STEM创新计划）；University of Houston（休斯顿大学）
Towards a more efficient computation of individual attribute and policy contribution for post-hoc explanation of cooperative multi-agent systems using Myerson values
Artificial and Natural Intelligence Toulouse Institute (ANITI)（图卢兹人工与自然智能研究所）；University of Toulouse（图卢兹大学）；ISAE-Supaero（法国高等航空航天学院）；Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI)（安达卢西亚数据科学与计算智能研究所）；Research Center for Information and Communications Technologies of the University of Granada (CITIC-UGR)（格拉纳达大学信息与通信技术研究中心）；University of Granada（格拉纳达大学）
Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy
Technische Universität Berlin（柏林工业大学）；BIFOLD – Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）；Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；Korea University（高丽大学）；Max Planck Institut für Informatik（马克斯·普朗克信息学研究所）
Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks
Technische Universität Berlin（柏林工业大学）；Berlin Institute for the Foundations of Learning and Data – BIFOLD（柏林学习与数据基础研究所（BIFOLD））；Korea University（高丽大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Google DeepMind（谷歌DeepMind）；Freie Universität Berlin（柏林自由大学）
The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies
