发表机构
Purdue University; Johns Hopkins University; Intuit AI Research; Microsoft（普渡大学; 约翰霍普金斯大学; Intuit AI 研究院; 微软）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有根因分析依赖强假设的局限，提出基于深度因果模型的RCA-DCM方法，利用分布约束和部分图知识，在模拟与真实微服务数据上显著提升根因识别准确率。
AI 中文摘要
根因分析（RCA）是许多现实场景中的关键问题。通过将异常观测与相应的参考（即正常）观测进行比较，RCA能够识别系统中故障或失效的机制。然而，现有方法要么依赖启发式方法，要么依赖具有强无混杂假设的条件独立性检验，因此在存在潜在变量的情况下无法利用其他复杂的分布约束。为放宽这些假设，我们将底层系统建模为因果模型，并将异常系统建模为同一因果模型结构函数的变化。具体而言，为处理未观测的混杂因素，我们在分布约束检验与根因分析之间建立了隐式联系。为使我们的方法适应任意因果模型生成的数据，我们采用深度因果模型（DCM）框架，在该框架中使用神经网络设计因果模型。最后，我们展示了我们的方法RCA-DCM如何利用不同级别的部分图知识来执行RCA。我们在模拟数据集、基于物理的因果腔室和两个微服务应用上将RCA-DCM与最先进的基线方法进行了评估。在Sock Shop（0.880对0.752）和Online Boutique（0.776对0.712）上，RCA-DCM相较于最强基线提高了top-1准确率；当因果腔室中的真实根因未被观测并作为潜在混杂因素时，它比任何竞争方法更频繁地恢复出精确的根因集合（完美恢复率（PRR）0.846对0.731）。
英文摘要
Root cause analysis (RCA) is a critical problem in many real-world scenarios. RCA enables the identification of faulty or failing mechanisms in a system by comparing anomalous observations with corresponding reference (i.e., regular) observations. However, existing approaches rely either on heuristic methods or on conditional independence tests with a strong unconfoundedness assumption, and thus fail to exploit other complicated distributional constraints in the presence of latent variables. To relax these assumptions, we model the underlying system as a causal model and the anomalous system as a change in the structural functions of the same causal model. Specifically, to handle unobserved confounders, we establish an implicit connection between distributional constraint testing and root cause analysis. To adapt our approach to data generated from arbitrary causal models, we employ the deep causal model (DCM) framework, in which we design the causal model using neural networks. Finally, we illustrate how our method, RCA-DCM, can utilize different levels of partial graphical knowledge to perform RCA. We evaluate RCA-DCM against state-of-the-art baselines on simulated datasets, a physics-based causal chamber and two micro-service applications. RCA-DCM improves top-1 accuracy over the strongest baseline on both Sock Shop (0.880 vs. 0.752) and Online Boutique (0.776 vs. 0.712), and when the true root cause in the causal chamber is unobserved and acts as a latent confounder, it recovers the exact root-cause set more often than any competing method (perfect recovery rate (PRR) 0.846 vs. 0.731).
