De-Biasing Generative Models using Counterfactual Methods

by   Sunay Bhat, et al.

Variational autoencoders (VAEs) and other generative methods have garnered growing interest not just for their generative properties but also for the ability to dis-entangle a low-dimensional latent variable space. However, few existing generative models take causality into account. We propose a new decoder based framework named the Causal Counterfactual Generative Model (CCGM), which includes a partially trainable causal layer in which a part of a causal model can be learned without significantly impacting reconstruction fidelity. By learning the causal relationships between image semantic labels or tabular variables, we can analyze biases, intervene on the generative model, and simulate new scenarios. Furthermore, by modifying the causal structure, we can generate samples outside the domain of the original training data and use such counterfactual models to de-bias datasets. Thus, datasets with known biases can still be used to train the causal generative model and learn the causal relationships, but we can produce de-biased datasets on the generative side. Our proposed method combines a causal latent space VAE model with specific modification to emphasize causal fidelity, enabling finer control over the causal layer and the ability to learn a robust intervention framework. We explore how better disentanglement of causal learning and encoding/decoding generates higher causal intervention quality. We also compare our model against similar research to demonstrate the need for explicit generative de-biasing beyond interventions. Our initial experiments show that our model can generate images and tabular data with high fidelity to the causal framework and accommodate explicit de-biasing to ignore undesired relationships in the causal data compared to the baseline.


page 1

page 7

page 9


CausalVAE: Structured Causal Disentanglement in Variational Autoencoder

Learning disentanglement aims at finding a low dimensional representatio...

Principled Knowledge Extrapolation with GANs

Human can extrapolate well, generalize daily knowledge into unseen scena...

Hypothesis Testing using Causal and Causal Variational Generative Models

Hypothesis testing and the usage of expert knowledge, or causal priors, ...

CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training

We propose an adversarial training procedure for learning a causal impli...

Spacetime Autoencoders Using Local Causal States

Local causal states are latent representations that capture organized pa...

Generative Interventions for Causal Learning

We introduce a framework for learning robust visual representations that...

Counterfactual Generative Networks

Neural networks are prone to learning shortcuts – they often model simpl...

Please sign up or login with your details

Forgot password? Click here to reset