Gradient-based Causal Structure Learning with Normalizing Flow

2020/10/07 by Xiongren Chen, Chen, Xiongren
Computer Science · #Bayesian Modeling and Causal Inference #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification #cs.LG

paper · pdf · doi:10.48550/arxiv.2010.03095

arxiv created 2020/10/07 · openalex publication_date 2020/10/07 · arxiv updated 2020/10/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper, we propose a score-based normalizing flow method called DAG-NF to learn dependencies of input observation data. Inspired by Grad-CAM in computer vision, we use jacobian matrix of output on input as causal relationships and this method can be generalized to any neural networks especially for flow-based generative neural networks such as Masked Autoregressive Flow(MAF) and Continuous Normalizing Flow(CNF) which compute the log likelihood loss and divergence of distribution of input data and target distribution. This method extends NOTEARS which enforces a important acylicity constraint on continuous adjacency matrix of graph nodes and significantly reduce the computational complexity of search space of graph.

Citations

• Identifiability of Gaussian structural equation models with equal error variances
• On the Identifiability of the Post-Nonlinear Causal Model

Related

• Masked Gradient-Based Causal Structure Learning
• A Graph Autoencoder Approach to Causal Structure Learning
• Causal normalizing flows: from theory to practice
• Gradient-Based Neural DAG Learning
• CASTLE: Regularization via Auxiliary Causal Graph Discovery