Markov Equivalence Class

A Markov equivalence class (MEC) represents a set of directed acyclic graphs (DAGs) that encode the same conditional independence relationships, posing a challenge in causal inference as observational data alone cannot distinguish between them. Current research focuses on efficiently identifying and characterizing MECs, developing algorithms to enumerate or sample DAGs within a class, and incorporating expert knowledge or interventional data to refine the learned causal structure. This work is crucial for advancing causal discovery methods across various scientific domains, enabling more accurate causal effect estimation and improved decision-making under uncertainty.

Papers

October 31, 2024

Learning Mixtures of Unknown Causal Interventions
Abhinav Kumar, Kirankumar Shiragur, Caroline Uhler
Causal Graph Causal Direction Learning Mixture Markov Equivalence Class Interventional Data Node Intervention

October 24, 2024

Revisiting Differentiable Structure Learning: Inconsistency of $\ell_1$ Penalty and Beyond
Kaifeng Jin, Ignavier Ng, Kun Zhang, Biwei Huang
Structure Learning Hard to Easy Inconsistency Markov Equivalence Class Appropriate Penalty Term

October 22, 2024

MEC-IP: Efficient Discovery of Markov Equivalent Classes via Integer Programming
Abdelmonem Elrefaey, Rong Pan
Causal Discovery Bayesian Network Programming Assistance Integer Programming Integer Arithmetic Markov Equivalence Class Efficient Discovery

July 10, 2024

Towards Complete Causal Explanation with Expert Knowledge
Aparajithan Venkateswaran, Emilija Perković
Expert Knowledge Markov Equivalence Class Ancestral Graph

June 17, 2024

Stochastic Neural Network Symmetrisation in Markov Categories
Rob Cornish
Markov Equivalence Class Learning Probabilistic Symmetrization

March 9, 2024

Membership Testing in Markov Equivalence Classes via Independence Query Oracles
Jiaqi Zhang, Kirankumar Shiragur, Caroline Uhler
Causal Graph Causal Relationship Conditional Independence Markov Equivalence Class Set Membership

December 1, 2023

Bayesian causal discovery from unknown general interventions
Alessandro Mascaro, Federico Castelletti
Causal Discovery Bayesian Inference Directed Acyclic Graph Markov Equivalence Class Interventional Data Bayesian Causal Discovery Unknown Intervention

November 13, 2023

Towards Bounding Causal Effects under Markov Equivalence
Alexis Bellot
Causal Effect Markov Equivalence Class Causal Constraint

October 9, 2023

Causal structure learning with momentum: Sampling distributions over Markov Equivalence Classes of DAGs
Moritz Schauer, Marcel Wienöbst
Causal Structure Residual Momentum Fast Sampling Markov Equivalence Class Bayesian Network Structure Reversible Markov Chain High Reward DAG

October 6, 2023

A Fixed-Parameter Tractable Algorithm for Counting Markov Equivalence Classes with the same Skeleton
Vidya Sagar Sharma
Human Skeleton Markov Equivalence Class Causal DAG Fixed Parameter

September 1, 2023

Establishing Markov Equivalence in Cyclic Directed Graphs
Tom Claassen, Joris M. Mooij
Computational Complexity Markov Equivalence Class Strong Equivalence

July 5, 2023

Causal Discovery with Language Models as Imperfect Experts
Stephanie Long, Alexandre Piché, Valentina Zantedeschi, Tibor Schuster, Alexandre Drouin
Language Model Causal Discovery Causal Graph Causal Relationship Markov Equivalence Class Data Driven Identification Multi Expert

June 19, 2023

Front-door Adjustment Beyond Markov Equivalence with Limited Graph Knowledge
Abhin Shah, Karthikeyan Shanmugam, Murat Kocaoglu
Causal Graph Causal Effect Causal Effect Estimation Cause Effect Graph Knowledge Markov Equivalence Class Causal Fairness Front Door Adjustment

January 28, 2023

Efficient Enumeration of Markov Equivalent DAGs
Marcel Wienöbst, Malte Luttermann, Max Bannach, Maciej Liśkiewicz
Directed Acyclic Graph Markov Equivalence Class Excess Delay Efficient Enumeration

August 14, 2022

Novel Ordering-based Approaches for Causal Structure Learning in the Presence of Unobserved Variables
Ehsan Mokhtarian, Mohammadsadegh Khorasani, Jalal Etesami, Negar Kiyavash
Constructive Approach Speech Presence Long Form Novel Structure Learning Causal Structure Learning Unobserved Variable Markov Equivalence Class Causal Order Ancestral Graph

June 14, 2022

Counting Markov Equivalent Directed Acyclic Graphs Consistent with Background Knowledge
Vidya Sagar Sharma
Polynomial Time Automatic Counting Background Knowledge Markov Equivalence Class Fixed Parameter

June 2, 2022

Robustness Evaluation and Adversarial Training of an Instance Segmentation Model
Jacob Bond, Andrew Lingg
Adversarial Training Adversarial Learning Robustness Evaluation Better Robustness Markov Equivalence Class

May 5, 2022

Polynomial-Time Algorithms for Counting and Sampling Markov Equivalent DAGs with Applications
Marcel Wienöbst, Max Bannach, Maciej Liśkiewicz
Financial Application Causal Structure Polynomial Time Automatic Counting Causal Effect Identification Markov Equivalence Class Causal Graphical Model

April 11, 2022

Markov categories, causal theories, and the do-calculus
Yimu Yin, Jiji Zhang
Causal Model Markov Equivalence Class Causal Bayesian Network Causal Theory

March 1, 2022

A Transformational Characterization of Unconditionally Equivalent Bayesian Networks
Alex Markham, Danai Deligeorgaki, Pratik Misra, Liam Solus
Bayesian Network Markov Equivalence Class Equivalence Class Strong Equivalence