Active Structure Learning of Causal DAGs via Directed Clique Tree

A growing body of work has begun to study intervention design for efficient structure learning of causal directed acyclic graphs (DAGs). A typical setting is a causally sufficient setting, i.e. a system with no latent confounders, selection bias, or feedback, when the essential graph of the observational equivalence class (EC) is given as an input and interventions are assumed to be noiseless. Most existing works focus on worst-case or average-case lower bounds for the number of interventions required to orient a DAG. These worst-case lower bounds only establish that the largest clique in the essential graph could make it difficult to learn the true DAG. In this work, we develop a universal lower bound for single-node interventions that establishes that the largest clique is always a fundamental impediment to structure learning. Specifically, we present a decomposition of a DAG into independently orientable components through directed clique trees and use it to prove that the number of single-node interventions necessary to orient any DAG in an EC is at least the sum of half the size of the largest cliques in each chain component of the essential graph. Moreover, we present a two-phase intervention design algorithm that, under certain conditions on the chordal skeleton, matches the optimal number of interventions up to a multiplicative logarithmic factor in the number of maximal cliques. We show via synthetic experiments that our algorithm can scale to much larger graphs than most of the related work and achieves better worst-case performance than other scalable approaches. A code base to recreate these results can be found at this https URL

[1]  Mathias Frisch,et al.  Causation and intervention , 2014 .

[2]  J. Pearl.  Causality: Models, Reasoning and Inference , 2000 .

[3]  Frederick Eberhardt,et al.  Experiment selection for causal discovery , 2013, J. Mach. Learn. Res..

[4]  Alexandros G. Dimakis,et al.  Cost-Optimal Learning of Causal Graphs , 2017, ICML.

[5]  Christopher Meek,et al.  Causal inference and causal explanation with background knowledge , 1995, UAI.

[6]  Michal Linial,et al.  Using Bayesian Networks to Analyze Expression Data , 2000, J. Comput. Biol..

[7]  Yangbo He,et al.  Active Learning of Causal Networks with Intervention Experiments and Optimal Designs , 2008 .

[8]  Michel Habib,et al.  Chordal Graphs and Their Clique Graphs , 1995, WG.

[9]  K. Sachs,et al.  Causal Protein-Signaling Networks Derived from Multiparameter Single-Cell Data , 2005, Science.

[10]  Peter Bühlmann,et al.  Two optimal strategies for active learning of causal models from interventional data , 2012, Int. J. Approx. Reason..

[11]  Alexandros G. Dimakis,et al.  Experimental Design for Cost-Aware Learning of Causal Graphs , 2018, NeurIPS.

[12]  P. Sreenivasa Kumar,et al.  Clique tree generalization and new subclasses of chordal graphs , 2002, Discret. Appl. Math..

[13]  Alexandros G. Dimakis,et al.  Learning Causal Graphs with Small Interventions , 2015, NIPS.

[14]  Tom Burr,et al.  Causation, Prediction, and Search , 2003, Technometrics.

[15]  Frederick Eberhardt,et al.  N-1 Experiments Suffice to Determine the Causal Relations Among N Variables , 2006 .

[16]  Martin S. Andersen,et al.  Chordal Graphs and Semidefinite Optimization , 2015, Found. Trends Optim..

[17]  Kun Zhang,et al.  Counting and Sampling from Markov Equivalent DAGs Using Clique Trees , 2018, AAAI.

[18]  Michael D. Perlman,et al.  Enumerating Markov Equivalence Classes of Acyclic Digraph Models , 2001, UAI.

[19]  Bernhard Schölkopf,et al.  Elements of Causal Inference: Foundations and Learning Algorithms , 2017 .

[20]  Yishay Mansour,et al.  Competitive ratio versus regret minimization: achieving the best of both worlds , 2019, ArXiv.

[21]  Kristjan H. Greenewald,et al.  Sample Efficient Active Learning of Causal Trees , 2019, NeurIPS.

[22]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[23]  Elias Bareinboim,et al.  Budgeted Experiment Design for Causal Structure Learning , 2017, ICML.

[24]  Allan Borodin,et al.  An optimal on-line algorithm for metrical task system , 1992, JACM.

[25]  AmirEmad Ghassami,et al.  Optimal Experiment Design for Causal Discovery from Fixed Number of Experiments , 2017, ArXiv.

[26]  Martin Wainwright,et al.  Handbook of Graphical Models , 2018 .