Causal Adversarial Network for Learning Conditional and Interventional Distributions

TL;DR

This paper introduces a Causal Adversarial Network (CAN) that learns causal relations from data to generate conditional and interventional samples, eliminating the need for a predefined causal graph, demonstrated on face generation tasks.

Contribution

The paper presents a novel CAN framework that learns causal relations directly from data and can generate interventional and conditional samples without prior causal graph knowledge.

Findings

CAN effectively learns causal relations from data.

The model generates realistic interventional and conditional samples.

Performance is validated on CelebA face dataset.

Abstract

We propose a generative Causal Adversarial Network (CAN) for learning and sampling from conditional and interventional distributions. In contrast to the existing CausalGAN which requires the causal graph to be given, our proposed framework learns the causal relations from the data and generates samples accordingly. The proposed CAN comprises a two-fold process namely Label Generation Network (LGN) and Conditional Image Generation Network (CIGN). The LGN is a GAN-based architecture which learns and samples from the causal model over labels. The sampled labels are then fed to CIGN, a conditional GAN architecture, which learns the relationships amongst labels and pixels and pixels themselves and generates samples based on them. This framework is equipped with an intervention mechanism which enables. the model to generate samples from interventional distributions. We quantitatively and qualitatively assess the performance of CAN and empirically show that our model is able to generate both interventional and conditional samples without having access to the causal graph for the application of face generation on CelebA data.