[论文解读] The role of causality in explainable artificial intelligence

Gianluca Carloni, Andrea Berti+1 more|arXiv (Cornell University)|Sep 18, 2023

Explainable Artificial Intelligence (XAI)被引用 9

一句话总结

对因果关系与可解释性AI之间关系的综合性综述，识别出三个主要视角（对XAI的批评者、用于因果性的XAI、为XAI服务的因果性），并勾勒出两领域之间在方法论与实践上的桥梁。

ABSTRACT

Causality and eXplainable Artificial Intelligence (XAI) have developed as separate fields in computer science, even though the underlying concepts of causation and explanation share common ancient roots. This is further enforced by the lack of review works jointly covering these two fields. In this paper, we investigate the literature to try to understand how and to what extent causality and XAI are intertwined. More precisely, we seek to uncover what kinds of relationships exist between the two concepts and how one can benefit from them, for instance, in building trust in AI systems. As a result, three main perspectives are identified. In the first one, the lack of causality is seen as one of the major limitations of current AI and XAI approaches, and the "optimal" form of explanations is investigated. The second is a pragmatic perspective and considers XAI as a tool to foster scientific exploration for causal inquiry, via the identification of pursue-worthy experimental manipulations. Finally, the third perspective supports the idea that causality is propaedeutic to XAI in three possible manners: exploiting concepts borrowed from causality to support or improve XAI, utilizing counterfactuals for explainability, and considering accessing a causal model as explaining itself. To complement our analysis, we also provide relevant software solutions used to automate causal tasks. We believe our work provides a unified view of the two fields of causality and XAI by highlighting potential domain bridges and uncovering possible limitations.

研究动机与目标

• 系统综述跨学科文献，了解因果性与XAI的关系。
• 明确因果性–XAI关系的主要视角。
• 提供统一视角，突出因果性与XAI之间的领域桥梁与局限性。

提出的方法

• 在Scopus、IEEE Xplore、Web of Science和ACM数据库中进行结构化文献综述。
• 使用VOSviewer进行关键词共现分析，以绘制概念之间的关系。
• 主题聚类将论文组织为连贯的视角：在因果视角下的对XAI的批评者、用于因果性的XAI、以及为XAI的因果性。
• 汇编并分析已被引用用于自动化因果任务的软件解决方案。

实验结果

研究问题

• RQ1 当前文献中因果性与XAI之间的关系是什么？
• RQ2 有哪些框架或形式化方法能够连接因果性与XAI，它们的局限性是什么？
• RQ3 哪个视角（对XAI的批评者、用于因果性的XAI，还是为XAI的因果性）最能支持将因果性融入XAI？
• RQ4 如何将因果工具和度量用于提升XAI解释的质量？

主要发现

• 出现了三大主要视角：在因果视角下的对XAI的批评者、用于因果性的XAI、以及为XAI的因果性。
• 当前的AI/XAI缺乏因果性被视为一大局限，存在对鲁棒性与解释可信度的担忧。
• XAI可以通过提示可追踪的、值得 Pursue 的实验操作来辅助因果探索，但解释可能并非对因果推断的完美指南。
• 因果性概念（SCMs、do-算子、因果Shapley值）可以增强XAI方法，并提供更具机理性的解释。
• 在关键场景中，获取因果模型或因果推理能力本身就能对AI决策提供解释。
• 综述映射出用于自动化因果任务的软件解决方案及其属性。