Causal Discovery from Nonstationary/Heterogeneous Data: Skeleton Estimation and Orientation Determination

By Kun Zhang, Biwei Huang, Jiji Zhang, Clark Glymour, Bernhard Schölkopf. 2017

160 citations recorded by the source corpus.

It is commonplace to encounter nonstationary or heterogeneous data, of which the underlying generating process changes over time or across data sets (the data sets may have different experimental conditions or data collection conditions). Such a distribution shift feature presents both challenges and opportunities for causal discovery. In this paper we develop a principled framework for causal discovery from such data, called Constraint-based causal Discovery from Nonstationary/heterogeneous Data (CD-NOD), which addresses two important questions. First, we propose an enhanced constraint-based procedure to detect variables whose local mechanisms change and recover the skeleton of the causal structure over observed variables. Second, we present a way to determine causal orientations by making use of independence changes in the data distribution implied by the underlying causal model, benefiting from information carried by changing distributions. Experimental results on various synthetic and real-world data sets are presented to demonstrate the efficacy of our methods.

Subfields: Causal Inference & Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Causal Inference & Discovery

Citations in the corpus

Weakly-Supervised Disentanglement Without Compromises (2020, background): “A parallel thread of work has studied distribution shifts by identifying changes in causal generative factors (Zhang et al., 2015; 2017; Huang et al., 2017), which is linked to a causal view of disentanglement (Suter et al., 2019; Schölkopf, 2019).”
Causal Regularization (2019, background): “Despite all concerns against our oversimplified assumptions, I want to stimulate a general discussion about recommending stronger regularization than criteria of statistical predictability suggest – whenever one is actually interested in causal models, which are more and more believed to be required”
Causal Discovery from Heterogeneous/Nonstationary Data (2019, methodology): “We compared with the window-based method (Zhang et al., 2017), the IB method, and the MC method for direction determination.”
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms (2019, background): “, 2017) and how non-stationarity makes causal discovery easier (Zhang et al., 2017).”
Behind Distribution Shift: Mining Driving Forces of Changes and Causal Arrows (2017, positive): “The procedure for causal discovery from nonstationary data proposed in [11] is briefly described in Algorithm 1.”
Specific and Shared Causal Relation Modeling and Mechanism-Based Clustering (2019, methodology): “On the other hand, if we ignore the differences and concatenate the data to estimate a causal graph, spurious edge or incorrect causal directions may be introduced [39].”
Causal Generative Domain Adaptation Networks (2018, methodology): “If there are multiple source domains, we modify the CD-NOD method [26], which extends the original PC to the case with distribution shifts.”
Review of Causal Discovery Methods Based on Graphical Models (2019, unknown): “This, in particular, inspires a framework for causal mechanism change detection, causal skeleton estimation, causal direction identiﬁcation, and nonstationary driving force estimation (Huang et al., 2017; Zhang et al., 2017b).”
Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models (2019, methodology): “For CD-NOD, the kernel width was set empirically (Zhang et al., 2017), and the signiﬁcance level was 0.05.”
Causal Discovery from Soft Interventions with Unknown Targets: Characterization and Learning (2020, background): “The works in [4, 23, 38, 30, 15] assume Markovianity (the absence of latent confounders).”
Causal Discovery with General Non-Linear Relationships using Non-Linear ICA (2019, methodology): “As a result, a wide range of methods have been proposed (Shimizu et al., 2006; Pearl, 2009; Hoyer et al., 2009; Zhang and Hyv ¨ arinen, 2009; Peters et al., 2016; Zhang et al., 2017).”
Joint Causal Inference from Multiple Contexts (2016, methodology): “, 2015; Forré and Mooij, 2018), (b) methods that pool all data and construct a single context-independent causal graph directly from the pooled data (Cooper, 1997; Cooper and Yoo, 1999; Tian and Pearl, 2001; Sachs et al., 2005; Eaton and Murphy, 2007; Chen et al., 2007; Hauser and Bühlmann, 2012; Mo”
Generalized Score Functions for Causal Discovery (2018, background): “As a consequence, they can be easily extended to handle more complex situations, such as the case with nonstationary time series or multiple, heterogeneous data sets [16, 32].”