Learning Latent Causal Structures with a Redundant Input Neural Network

Abstract

Most causal discovery algorithms find causal structure among a set of observed variables. Learning the causal structure among latent variables remains an important open problem, particularly when using high-dimensional data. In this paper, we address a problem for which it is known that inputs cause outputs, and these causal relationships are encoded by a causal network among a set of an unknown number of latent variables. We developed a deep learning model, which we call a redundant input neural network (RINN), with a modified architecture and a regularized objective function to find causal relationships between input, hidden, and output variables. More specifically, our model allows input variables to directly interact with all latent variables in a neural network to influence what information the latent variables should encode in order to generate the output variables accurately. In this setting, the direct connections between input and latent variables makes the latent variables partially interpretable; furthermore, the connectivity among the latent variables in the neural network serves to model their potential causal relationships to each other and to the output variables. A series of simulation experiments provide support that the RINN method can successfully recover latent causal structure between input and output variables.

Proceedings of the 2020 KDD Workshop on Causal Discovery, in Proceedings of Machine Learning Research

References in corpus (8)

• Training Very Deep Networks
• Causal Effect Inference with Deep Latent-Variable Models
• Causal Inference in the Presence of Latent Variables and Selection Bias
• Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex
• Causal Learning and Explanation of Deep Neural Networks via Autoencoded Activations
• Learning Neural Causal Models from Unknown Interventions
• Structural Agnostic Modeling: Adversarial Learning of Causal Graphs
• A Comparison of Public Causal Search Packages on Linear, Gaussian Data with No Latent Variables