Exploring the Trade-off between Plausibility, Change Intensity and Adversarial Power in Counterfactual Explanations using Multi-objective Optimization
TECNALIA, Basque Research and Technology Alliance (BRTA)（TECNALIA，巴斯克研究与技术联盟）；University of the Basque Country (UPV/EHU)（巴斯克大学）；University of Granada（格拉纳达大学）；DaSCI Andalusian Institute of Data Science and Computational Intelligence（DaSCI安达卢西亚数据科学与计算智能研究所）；Medical University of Graz（格拉茨医科大学）；Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究所）；University of Alberta（阿尔伯塔大学）
Javier Del Ser, Alejandro Barredo-Arrieta, Natalia Díaz-Rodríguez, Francisco Herrera, Andreas Holzinger
There is a broad consensus on the importance of deep learning models in tasks involving complex data. Often, an adequate understanding of these models is required when focusing on the transparency of decisions in human-critical applications. Besides other explainability techniques, trustworthiness can be achieved by using counterfactuals, like the way a human becomes familiar with an unknown process: by understanding the hypothetical circumstances under which the output changes. In this work we argue that automated counterfactual generation should regard several aspects of the produced adversarial instances, not only their adversarial capability. To this end, we present a novel framework for the generation of counterfactual examples which formulates its goal as a multi-objective optimization problem balancing three different objectives: 1) plausibility, i.e., the likeliness of the counterfactual of being possible as per the distribution of the input data; 2) intensity of the changes to the original input; and 3) adversarial power, namely, the variability of the model's output induced by the counterfactual. The framework departs from a target model to be audited and uses a Generative Adversarial Network to model the distribution of input data, together with a multi-objective solver for the discovery of counterfactuals balancing among these objectives. The utility of the framework is showcased over six classification tasks comprising image and three-dimensional data. The experiments verify that the framework unveils counterfactuals that comply with intuition, increasing the trustworthiness of the user, and leading to further insights, such as the detection of bias and data misrepresentation.
Protein Counterfactuals via Diffusion-Guided Latent Optimization
Machine Learning Group, Technische Universität Berlin（技术大学柏林机器学习组）；Berlin Institute for the Foundations of Learning and Data (BIFOLD)（柏林学习与数据基础研究所（BIFOLD））；BASF Digital Solutions GmbH（巴斯夫数字解决方案有限公司）
Actionable and diverse counterfactual explanations incorporating domain knowledge and plausibility constraints
Faculty of Physics, Astronomy and Applied Computer Science, Institute of Applied Computer Science, Jagiellonian Human-Centered AI Lab（物理、天文与应用计算机科学学院，应用计算机科学研究所，雅盖隆人机中心AI实验室）
Keep Your Friends Close and Your Counterfactuals Closer: Improved Learning From Closest Rather Than Plausible Counterfactual Explanations in an Abstract Setting
Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Box
Human Technology Institute, University of Technology Sydney（悉尼科技大学人类技术研究所）；School of Information Systems, Queensland University of Technology（昆士兰科技大学信息系统学院）；INESC-ID Lisboa / Instituto Superior Técnico, ULisboa（INESC-ID里斯本/里斯本大学高等技术学院）
Exploring Energy Landscapes for Minimal Counterfactual Explanations: Applications in Cybersecurity and Beyond
Netcompany-Intrasoft S.A.（Netcompany-Intrasoft公司）；Hellenic Mediterranean University（希腊地中海大学）；Harokopio University of Athens（雅典哈罗科皮奥大学）；University of Western Macedonia（西马其顿大学）
IMFACT: Counterfactual Explanations for Time Series via Intrinsic Mode Function Substitution
LMU Munich（慕尼黑大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；TU Graz（格拉茨工业大学）；BOKU University Vienna（维也纳农业大学）；TECNALIA（泰克纳利亚）；University of the Basque Country (EHU)（巴斯克大学）
AVCG: A Generalized Variational Framework for Counterfactual Generation under Hypothesis Distributions
School of Computing and Digital Technologies, Sheffield Hallam University（谢菲尔德哈勒姆大学计算与数字技术学院）；Centre of Excellence in AI and Robotics (CEAIR), Sheffield Hallam University（谢菲尔德哈勒姆大学人工智能与机器人卓越中心）；Laboratoire d’analyse cognitive de l’information (LANCI), Université du Québec à Montréal（魁北克大学蒙特利尔分校信息认知分析实验室）；Institut Santé et société (ISS), Université du Québec à Montréal（魁北克大学蒙特利尔分校健康与社会研究所）；Institut de recherches et d’études féministes (IREF), Université du Québec à Montréal（魁北克大学蒙特利尔分校女权主义研究与教育研究所）
CounterFlowNet: From Minimal Changes to Meaningful Counterfactual Explanations
Wrocław University of Science and Technology（沃拉布大学科学与技术大学）；Faculty of Mathematics and Computer Science（数学与计算机科学系）；Jagiellonian University（雅盖隆大学）；Doctoral School of Exact and Natural Sciences（精确与自然科学博士学校）
Counterfactual Explanation-Based Badminton Motion Guidance Generation Using Wearable Sensors
School of Integrated Technology, Gwangjun Institute of Science and Technology（光州科学技术学院综合技术学院）；Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology（麻省理工学院计算机科学与人工智能实验室）
MASCOTS: Model-Agnostic Symbolic COunterfactual explanations for Time Series
Warsaw University of Technology（华沙理工大学）；University of Warsaw（华沙大学）；University of Pisa（比萨大学）；ISTI-CNR（意大利国家研究委员会信息科学与技术研究所）；KP Labs（KP实验室）；European Space Operations Centre（欧洲空间操作中心）；ETH Zürich（苏黎世联邦理工学院）
CountARFactuals -- Generating plausible model-agnostic counterfactual explanations with adversarial random forests
Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；LMU Munich（慕尼黑大学）；Leibniz Institute for Prevention Research & Epidemiology – BIPS（莱布尼茨预防研究与流行病学研究所）；University of Bremen（不来梅大学）；University of Tübingen（蒂宾根大学）；University of Copenhagen（哥本哈根大学）
Uncertainty Estimation and Out-of-Distribution Detection for Counterfactual Explanations: Pitfalls and Solutions
University College Dublin（都柏林大学学院）；Insight Centre for Data Analytics（洞察数据分析中心）；VistaMilk SFI Research Centre（VistaMilk SFI研究中心）
虽然最近已经提出了丰富的技术来生成不透明的黑盒系统的预测的反事实的解释，显着较少的注意力已经支付到探索这些生成的解释的不确定性。这在高风险场景中成为一个关键问题，在这种场景中，不确定和误导性的解释可能会产生可怕的后果（例如，医疗诊断和治疗计划）。此外，通常难以确定所生成的解释是否在训练数据中有良好的基础并且对分布偏移敏感。本文提出了几种实用的解决方案，可以通过与其他研究作品在可解释性方面建立新的联系来解决这些问题（例如，信任分数）和不确定性估计（例如，Monte Carlo Dropout）。两个实验证明了我们提出的解决方案的实用性。
Physics-Guided Counterfactual Explanations for Large-Scale Multivariate Time Series: Application in Scalable and Interpretable SEP Event Prediction
Dept. of Computer Science Georgia State University Atlanta, GA, USA（计算机科学系 佐治亚州立大学）；Dept. of Computer Science California State University Fullerton, CA, USA（计算机科学系 加州州立大学Fullerton分校）
Beyond One-Size-Fits-All: Adapting Counterfactual Explanations to User Objectives
National Technical University of Athens（雅典国立技术大学）；School of Electrical and Computer Engineering（电气与计算机工程学院）；Artificial Intelligence and Learning Systems Laboratory（人工智能与学习系统实验室）
