Causal inference using deep neural networks

2020/11/25 by Ye Yuan, Yuan, Ye, Xueying Ding +4
Computer Science · Mathematics · #Bayesian Modeling and Causal Inference #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Geochemistry and Geologic Mapping #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.2011.12508

arxiv created 2020/11/25 · openalex publication_date 2020/11/25 · arxiv updated 2020/11/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Causal inference from observation data is a core problem in many scientific fields. Here we present a general supervised deep learning framework that infers causal interactions by transforming the input vectors to an image-like representation for every pair of inputs. Given a training dataset we first construct a normalized empirical probability density distribution (NEPDF) matrix. We then train a convolutional neural network (CNN) on NEPDFs for causality predictions. We tested the method on several different simulated and real world data and compared it to prior methods for causal inference. As we show, the method is general, can efficiently handle very large datasets and improves upon prior methods.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• On the Identifiability of the Post-Nonlinear Causal Model
• Investigating Causal Relations by Econometric Models and Cross-spectral Methods

Related

• A Primer on Deep Learning for Causal Inference
• A Survey of Methods, Challenges and Perspectives in Causality
• A Primer on Deep Learning for Causal Inference
• Deep Learning of Causal Structures in High Dimensions
• Deep Causal Learning: Representation, Discovery and Inference