arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1412.3773cs.LGcs.AIstat.MLstat.OT
收藏

利用观测数据区分因果:方法和基准

Distinguishing cause from effect using observational data: methods and benchmarks

University of Amsterdam(阿姆斯特丹大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);ETH Zürich(苏黎世联邦理工学院)

Joris M. Mooij, Jonas Peters, Dominik Janzing, Jakob Zscheischler, Bernhard Schölkopf

摘要:

从纯粹的观测数据中发现因果关系是科学中的一个基本问题。这种因果发现问题的最基本形式是,在给定两个变量X、Y的联合观测值的情况下,决定是X导致Y,还是Y导致X。一个例子是决定是否海拔导致温度,反之亦然,只有联合测量两个变量。即使在没有混杂、没有反馈回路和没有选择偏差的简化假设下,这样的双变量因果发现问题也是具有挑战性的。然而,近年来提出了解决这些问题的若干办法。我们回顾了两个家庭这样的方法:加性噪声方法(ANM)和信息几何因果推理(IGCI)。我们提出了基准因果关系对,其中包括从来自各个领域的37个数据集中选择的100个不同因果关系对的数据(例如,气象学、生物学、医学、工程学、经济学等)并激励我们关于所有对的“地面真相”因果方向的决定。我们评估了几种二元因果发现方法在这些真实世界的基准数据和人工模拟数据上的性能。我们对真实世界数据的实证结果表明,某些方法确实能够仅使用纯粹的观察数据区分因果关系,尽管需要更多的基准数据才能获得统计上显著的结论。总体上表现最好的方法之一是最初由Hoyer等人(2009)提出的加性噪声方法,该方法在真实世界基准上获得了63 ± 10%的准确度和0.74 ± 0.05的AUC。作为这项工作的主要理论贡献,我们证明了该方法的一致性。

英文摘要:

The discovery of causal relationships from purely observational data is a fundamental problem in science. The most elementary form of such a causal discovery problem is to decide whether X causes Y or, alternatively, Y causes X, given joint observations of two variables X, Y. An example is to decide whether altitude causes temperature, or vice versa, given only joint measurements of both variables. Even under the simplifying assumptions of no confounding, no feedback loops, and no selection bias, such bivariate causal discovery problems are challenging. Nevertheless, several approaches for addressing those problems have been proposed in recent years. We review two families of such methods: Additive Noise Methods (ANM) and Information Geometric Causal Inference (IGCI). We present the benchmark CauseEffectPairs that consists of data for 100 different cause-effect pairs selected from 37 datasets from various domains (e.g., meteorology, biology, medicine, engineering, economy, etc.) and motivate our decisions regarding the "ground truth" causal directions of all pairs. We evaluate the performance of several bivariate causal discovery methods on these real-world benchmark data and in addition on artificially simulated data. Our empirical results on real-world data indicate that certain methods are indeed able to distinguish cause from effect using only purely observational data, although more benchmark data would be needed to obtain statistically significant conclusions. One of the best performing methods overall is the additive-noise method originally proposed by Hoyer et al. (2009), which obtains an accuracy of 63+-10 % and an AUC of 0.74+-0.05 on the real-world benchmark. As the main theoretical contribution of this work we prove the consistency of that method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑