Counterfactual Generation Under Confounding

by   Abbavaram Gowtham Reddy, et al.

A machine learning model, under the influence of observed or unobserved confounders in the training data, can learn spurious correlations and fail to generalize when deployed. For image classifiers, augmenting a training dataset using counterfactual examples has been empirically shown to break spurious correlations. However, the counterfactual generation task itself becomes more difficult as the level of confounding increases. Existing methods for counterfactual generation under confounding consider a fixed set of interventions (e.g., texture, rotation) and are not flexible enough to capture diverse data-generating processes. Given a causal generative process, we formally characterize the adverse effects of confounding on any downstream tasks and show that the correlation between generative factors (attributes) can be used to quantitatively measure confounding between generative factors. To minimize such correlation, we propose a counterfactual generation method that learns to modify the value of any attribute in an image and generate new images given a set of observed attributes, even when the dataset is highly confounded. These counterfactual images are then used to regularize the downstream classifier such that the learned representations are the same across various generative factors conditioned on the class label. Our method is computationally efficient, simple to implement, and works well for any number of generative factors and confounding variables. Our experimental results on both synthetic (MNIST variants) and real-world (CelebA) datasets show the usefulness of our approach.


page 8

page 13


Rethinking Counterfactual Data Augmentation Under Confounding

Counterfactual data augmentation has recently emerged as a method to mit...

Debiasing Counterfactuals In the Presence of Spurious Correlations

Deep learning models can perform well in complex medical imaging classif...

Deep Generative Model with Beta Bernoulli Process for Modeling and Learning Confounding Factors

While deep representation learning has become increasingly capable of se...

Causal World Models by Unsupervised Deconfounding of Physical Dynamics

The capability of imagining internally with a mental model of the world ...

On Explaining Confounding Bias

When analyzing large datasets, analysts are often interested in the expl...

Understanding confounding effects in linguistic coordination: an information-theoretic approach

We suggest an information-theoretic approach for measuring stylistic coo...

Please sign up or login with your details

Forgot password? Click here to reset