提出可调精度的多项式算法，高效找出现实因果关系
Searching for actual causes: Approximate algorithms with adjustable precision
- 设计多项式复杂度算法，支持可调精度与完备性
- 适用于非布尔、黑箱、随机系统，覆盖现有方法无法处理的场景
- 适合需要可解释性但非专业的用户，如医疗或金融决策者
因果推理近年备受关注，有助于提升机器学习模型的性能、可靠性和可解释性。然而，当前可解释人工智能（XAI）与因果研究常被批评为仅关注哪些因素影响结果，而非真正导致结果的‘实际原因’。这一概念尚未形式化，且识别实际原因被证明是NP完全问题，缺乏实用近似方法。本文提出一组算法，在多项式时间内识别实际原因，并支持根据计算时间调整精度与完备性。实验表明，该方法可有效处理非布尔、黑箱及随机系统，而这些类型是现有方法无法覆盖的；同时，通过增加计算资源，可进一步提升识别的精确度和全面性。
原文摘要 · Abstract (English)
Causality has gained popularity in recent years. It has helped improve the performance, reliability, and interpretability of machine learning models. However, recent literature on explainable artificial intelligence (XAI) has faced criticism. The classical XAI and causality literature focuses on understanding which factors contribute to which consequences. While such knowledge is valuable for researchers and engineers, it is not what non-expert users expect as explanations. Instead, these users often await facts that cause the target consequences, i.e., actual causes. Formalizing this notion is still an open problem. Additionally, identifying actual causes is reportedly an NP-complete problem, and there are too few practical solutions to approximate formal definitions. We propose a set of algorithms to identify actual causes with a polynomial complexity and an adjustable level of precision and exhaustiveness. Our experiments indicate that the algorithms (1) identify causes for different categories of systems that are not handled by existing approaches (i.e., non-boolean, black-box, and stochastic systems), (2) can be adjusted to gain more precision and exhaustiveness with more computation time.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。