Causal inference using deep neural networks
This work tackles the fundamental problem of causal inference from observational data for various scientific fields, offering an incremental improvement over existing methods.
This paper addresses causal inference from observational data by proposing a deep learning framework. It transforms input vectors into an image-like representation, constructs a Normalized Empirical Probability Density Distribution (NEPDF) matrix, and then trains a Convolutional Neural Network (CNN) on these NEPDFs to predict causality. The method is shown to be general, efficient for large datasets, and improves upon prior methods.
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.