一种计算可行的因果概率解释框架

中文摘要 AI 辅助

解释特定结果为何发生、哪些输入应承担责任或获得功劳，是哲学、科学与政策分析的核心。现有工具分为两类：实际因果性（AC）理论能给出原则性判定，但仅适用于小型模型，因计算需枚举反事实场景；可扩展归因方法如SHAP（或因果SHAP）至少部分忽略生成数据的因果结构，可能给出与严谨因果分析冲突的结果。我们提出概率因果影响（PCI）以弥合该差距。PCI基于实际因果性与Pearl的必要性和充分性概率概念，将可解释性问题重构为概率因果模型上的估计问题，可通过蒙特卡洛轻松近似。通过指定“候选解释”分布、反事实值分布及评分函数，PCI提供可处理的、基于因果的分级解释，将AC与Pearl的因果概率作为退化情况推广。我们在合成与真实案例中评估PCI，涵盖与AC的一致性检查、可扩展性实验、复杂连续值动力系统，以及基于数百万数据点训练的真实部署因果机器学习模型。

英文摘要

Explaining why a specific outcome occurred, and which inputs deserve the blame or credit, is central to philosophical, scientific, and policy analysis. Existing tools split into two camps. The theory of actual causality (AC) gives principled verdicts, but only for toy-sized models, because computing them requires enumerating counterfactual scenarios. Scalable attribution methods like SHAP (or even causal SHAP) at least partially ignore the causal structure that generated the data, and can give answers that conflict with a careful causal analysis. We close this gap with Probabilistic Causal Impact (PCI). PCI builds on actual causality and on Pearl's notions of probability of necessity and sufficiency, but recasts the question of explainability as an estimation problem on a probabilistic causal model that is easily approximated via Monte Carlo. By specifying a distribution over "candidate explanations," a distribution over counterfactual values, and a scoring function, PCI provides tractable, causally grounded, graded explanations, generalizing AC and Pearl's probability of causation as degenerate cases. We evaluate PCI in synthetic and real-world examples, spanning consistency checks with AC, scaling experiments, complex continuous-valued dynamical systems, and a real-world deployed causal machine learning model trained on millions of datapoints.

发表机构

• Basis Research Institute（贝西斯研究所）
• Sorbus AI（索巴斯人工智能公司）
• Massachusetts Institute of Technology（麻省理工学院）
• University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
• University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
• HouseIQ（豪斯IQ公司）

机构由 AI 辅助整理，请以论文原文为准。