Causal Inference via Style Transfer for Out-of-distribution Generalisation

TL;DR

This paper introduces a novel causal inference method for out-of-distribution generalisation that leverages style transfer to implement front-door adjustment, effectively handling hidden confounders and improving model robustness across unseen domains.

Contribution

It proposes a new approach combining style transfer with front-door adjustment to address hidden confounders in causal inference for OOD generalisation, which was not previously explored.

Findings

Outperforms existing methods on benchmark datasets

Effectively handles hidden confounders in causal models

Improves OOD generalisation robustness

Abstract

Out-of-distribution (OOD) generalisation aims to build a model that can generalise well on an unseen target domain using knowledge from multiple source domains. To this end, the model should seek the causal dependence between inputs and labels, which may be determined by the semantics of inputs and remain invariant across domains. However, statistical or non-causal methods often cannot capture this dependence and perform poorly due to not considering spurious correlations learnt from model training via unobserved confounders. A well-known existing causal inference method like back-door adjustment cannot be applied to remove spurious correlations as it requires the observation of confounders. In this paper, we propose a novel method that effectively deals with hidden confounders by successfully implementing front-door adjustment (FA). FA requires the choice of a mediator, which we regard as the semantic information of images that helps access the causal mechanism without the need for observing confounders. Further, we propose to estimate the combination of the mediator with other observed images in the front-door formula via style transfer algorithms. Our use of style transfer to estimate FA is novel and sensible for OOD generalisation, which we justify by extensive experimental results on widely used benchmark datasets.