提出新方法，找出模型预测的直接原因，提升可解释性。
Modeling and Discovering Direct Causes for Predictive Models
- 构建因果框架，分析模型输入输出关系
- 在假设下实现直接因果特征的完整发现
- 新独立性规则加速发现过程，适合可解释性研究者
我们提出一种因果建模框架，用于捕捉预测模型（如机器学习模型）的输入-输出行为。该框架使我们能够识别出直接导致预测结果的特征，对数据收集和模型评估具有广泛意义。在此基础上，我们在若干假设下提出了完备且正确的算法，用于从数据中发现直接因果关系。此外，我们提出一种新颖的独立性准则，可与算法结合以加速发现过程，理论与实证均证明其有效性。
原文摘要 · Abstract (English)
We introduce a causal modeling framework that captures the input-output behavior of predictive models (e.g., machine learning models). The framework enables us to identify features that directly cause the predictions, which has broad implications for data collection and model evaluation. We then present sound and complete algorithms for discovering direct causes (from data) under some assumptions. Furthermore, we propose a novel independence rule that can be integrated with the algorithms to accelerate the discovery process, as we demonstrate both theoretically and empirically.
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。