CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training

by   Murat Kocaoglu, et al.

We propose an adversarial training procedure for learning a causal implicit generative model for a given causal graph. We show that adversarial training can be used to learn a generative model with true observational and interventional distributions if the generator architecture is consistent with the given causal graph. We consider the application of generating faces based on given binary labels where the dependency structure between the labels is preserved with a causal graph. This problem can be seen as learning a causal implicit generative model for the image and labels. We devise a two-stage procedure for this problem. First we train a causal implicit generative model over binary labels using a neural network consistent with a causal graph as the generator. We empirically show that WassersteinGAN can be used to output discrete labels. Later, we propose two new conditional GAN architectures, which we call CausalGAN and CausalBEGAN. We show that the optimal generator of the CausalGAN, given the labels, samples from the image distributions conditioned on these labels. The conditional GAN combined with a trained causal implicit generative model for the labels is then a causal implicit generative model over the labels and the generated image. We show that the proposed architectures can be used to sample from observational and interventional image distributions, even for interventions which do not naturally occur in the dataset.


page 18

page 19

page 32

page 33

page 34

page 35

page 36

page 37


Semi-Implicit Generative Model

To combine explicit and implicit generative models, we introduce semi-im...

Network Model with Application to Allergy Diseases

We propose a new graphical model to describe the comorbidity of allergic...

De-Biasing Generative Models using Counterfactual Methods

Variational autoencoders (VAEs) and other generative methods have garner...

A Stochastic Model for Block Segmentation of Images Based on the Quadtree and the Bayes Code for It

In information theory, lossless compression of general data is based on ...

Image Decomposition and Classification through a Generative Model

We demonstrate in this paper that a generative model can be designed to ...

A Universal Marginalizer for Amortized Inference in Generative Models

We consider the problem of inference in a causal generative model where ...

Moment-Matching Graph-Networks for Causal Inference

In this note we explore a fully unsupervised deep-learning framework for...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset