arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.02728cs.LGcs.AIstat.ML
收藏

发现可靠的因果规则

Discovering Reliable Causal Rules

Amazon Research Tübingen(亚马逊图宾根研究院);Monash University(莫纳什大学);CISPA Helmholtz Center for Information Security(CISPA亥姆霍兹信息安全中心)

Kailash Budhathoki, Mario Boley, Jilles Vreeken

摘要:

我们研究的问题,派生的政策,或规则,当制定一个复杂的系统,导致预期的结果。由于缺乏进行受控实验的能力,这些规则必须从过去对系统行为的观察中推断出来。这是一个具有挑战性的问题,原因有两个:第一,观察效应往往不能代表潜在的因果效应,因为它们被混杂因素的存在所扭曲。其次,对规则效果的经验估计具有很高的方差,因此,它们的最大化可能导致随机结果。为了解决这些问题,我们首先从观察数据中测量规则的因果效应-调整潜在混杂因素的影响。重要的是,我们提供了一个图形化的标准下,因果规则发现是可能的。此外,从样本中发现可靠的因果规则,我们提出了一个保守的和一致的因果效应估计,并推导出一个有效的和精确的算法,最大化的估计。在合成数据上,所提出的估计量比朴素估计量更快地收敛到地面真值,并且即使在小样本量下也能恢复相关的因果规则。在真实数据集上的大量实验表明,该算法是有效的,并发现有意义的规则。

英文摘要:

We study the problem of deriving policies, or rules, that when enacted on a complex system, cause a desired outcome. Absent the ability to perform controlled experiments, such rules have to be inferred from past observations of the system's behaviour. This is a challenging problem for two reasons: First, observational effects are often unrepresentative of the underlying causal effect because they are skewed by the presence of confounding factors. Second, naive empirical estimations of a rule's effect have a high variance, and, hence, their maximisation can lead to random results. To address these issues, first we measure the causal effect of a rule from observational data---adjusting for the effect of potential confounders. Importantly, we provide a graphical criteria under which causal rule discovery is possible. Moreover, to discover reliable causal rules from a sample, we propose a conservative and consistent estimator of the causal effect, and derive an efficient and exact algorithm that maximises the estimator. On synthetic data, the proposed estimator converges faster to the ground truth than the naive estimator and recovers relevant causal rules even at small sample sizes. Extensive experiments on a variety of real-world datasets show that the proposed algorithm is efficient and discovers meaningful rules.

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。

↑