针对鲁棒反事实解释缺乏统一工具与基准的问题,本文提出开源 Python 库 RobustX,集成多种 CE 生成、评估方法和现有先进接口,并支持新方法快速扩展。
摘要:
机器学习(ML)模型越来越多地用于辅助高风险行业的决策,这要求具备可解释性以促进信任。反事实解释(CEs)非常适合这一目标,因为它们能够说明输入数据的变化如何可能导致不同结果,从而提供对 ML 模型预测的洞察。然而,要让 CEs 发挥其解释潜力,在被解释场景发生轻微变化时确保其鲁棒性仍然存在重大挑战。尽管 CEs 的鲁棒性已被广泛认为是一项基本要求,但标准化工具和基准的缺乏阻碍了对鲁棒 CE 生成方法进行全面、有效的比较。本文提出 RobustX,这是一个开源 Python 库,实现了一系列 CE 生成与评估方法,并重点关注鲁棒性属性。RobustX 为文献中的若干现有方法提供接口,使用户能够便捷访问最先进技术。该库还易于扩展,支持快速原型化新的鲁棒 CE 生成与评估方法。
英文摘要:
The increasing use of Machine Learning (ML) models to aid decision-making in high-stakes industries demands explainability to facilitate trust. Counterfactual Explanations (CEs) are ideally suited for this, as they can offer insights into the predictions of an ML model by illustrating how changes in its input data may lead to different outcomes. However, for CEs to realise their explanatory potential, significant challenges remain in ensuring their robustness under slight changes in the scenario being explained. Despite the widespread recognition of CEs' robustness as a fundamental requirement, a lack of standardised tools and benchmarks hinders a comprehensive and effective comparison of robust CE generation methods. In this paper, we introduce RobustX, an open-source Python library implementing a collection of CE generation and evaluation methods, with a focus on the robustness property. RobustX provides interfaces to several existing methods from the literature, enabling streamlined access to state-of-the-art techniques. The library is also easily extensible, allowing fast prototyping of novel robust CE generation and evaluation methods.
Unifying Image Counterfactuals and Feature Attributions with Latent-Space Adversarial Attacks
Department of Statistics, University of California, Berkeley(加州大学伯克利分校统计学系);Department of Statistics and Data Science, University of Pennsylvania(宾夕法尼亚大学统计学与数据科学系)
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)
Designing Counterfactual Generators using Deep Model Inversion
Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室);Arizona State University(亚利桑那州立大学);IBM Research AI(IBM研究院人工智能部门);Stanford University(斯坦福大学)
解释技术将小的、可解释的变化合成到给定的图像,同时在模型预测中产生所需的变化,这种解释技术已经成为内省黑盒模型的流行方法。通常被称为反事实,合成的解释需要包含可辨别的变化(为了易于解释),同时也是现实的(与数据流形的一致性)。在本文中,我们关注的情况是,我们只能访问经过训练的深度分类器,而不能访问实际的训练数据。虽然已经探索了从训练分布中反演深度模型以合成图像的问题,但我们的目标是开发一种深度反演方法来为给定的查询图像生成反事实解释。尽管它们在条件图像合成中是有效的,但我们表明现有的深度反演方法不足以产生有意义的反事实。我们提出了DISC(Deep Inversion for Synthesizing Counterfactuals),它通过利用(a)更强的图像先验,(b)结合新的流形一致性目标和(c)采用渐进式优化策略来改进深度反演。我们发现,除了产生视觉上有意义的解释外,来自DISC的反事实在学习分类器决策边界方面也很有效,并且对未知的测试时损坏具有鲁棒性。
Implicit Counterfactual Data Augmentation for Robust Learning
National Engineering Research Center for Software Engineering, Peking University, Beijing, 100871, China;Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, 310024, China;Department of Mathematics, Hong Kong Baptist University, Hong Kong, 999077, China
GLANCE: Global Actions in a Nutshell for Counterfactual Explainability
Institute for the Management of Information Systems, Athena Research Center(信息管理系统研究所,雅典研究中心);Department of Electrical and Computer Engineering, National Technical University of Athens(电气与计算机工程系,雅典技术大学);Max Planck Institute for Software Systems(软件系统马克斯·普朗克研究所);Université Libre de Bruxelles(布鲁塞尔自由大学);FARI Institute, Belgium(比利时FARI研究所);Department of Informatics, Athens University of Economics and Business(信息系,雅典经济与商业大学);Department of Informatics and Telecommunications, National and Kapodistrian University of Athens(信息与电信系,雅典国家与卡波迪斯蒂亚大学);Archimedes, Athena Research Center(阿基米德,雅典研究中心)