CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training

Abstract

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.

Cited by in corpus (29)

• Deep Generative Design: Integration of Topology Optimization and Generative Models
• How Generative Adversarial Networks and Their Variants Work: An Overview
• Guided Image Generation with Conditional Invertible Neural Networks
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Explaining Classifiers with Causal Concept Effect (CaCE)
• Deep Structural Causal Models for Tractable Counterfactual Inference
• Causal Induction from Visual Observations for Goal Directed Tasks
• Neural Network Attributions: A Causal Perspective
• Domain Adaptation as a Problem of Inference on Graphical Models
• DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks
• iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering
• Multiple Causal Inference with Latent Confounding
• Some models are useful, but how do we know which ones? Towards a unified Bayesian model taxonomy
• Competitive Training of Mixtures of Independent Deep Generative Models
• Generating User-friendly Explanations for Loan Denials using GANs
• Unbiased Auxiliary Classifier GANs with MINE
• The Medical Deconfounder: Assessing Treatment Effects with Electronic Health Records
• Causal-TGAN: Generating Tabular Data Using Causal Generative Adversarial Networks
• Causal Adversarial Network for Learning Conditional and Interventional Distributions
• Intact-VAE: Estimating Treatment Effects under Unobserved Confounding
• Causal Attention for Vision-Language Tasks
• iReason: Multimodal Commonsense Reasoning using Videos and Natural Language with Interpretability
• Defining and Quantifying the Emergence of Sparse Concepts in DNNs
• Learning Generative Models of Tissue Organization with Supervised GANs
• Additive Adversarial Learning for Unbiased Authentication
• Learning latent causal graphs via mixture oracles
• Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanisms
• Matched sample selection with GANs for mitigating attribute confounding
• Dual Projection Generative Adversarial Networks for Conditional Image Generation