Deep Backtracking Counterfactuals for Causally Compliant Explanations

Published: 31 Jul 2024, Last Modified: 17 Sept 2024Accepted by TMLREveryoneRevisionsBibTeXCC BY 4.0
Abstract: Counterfactuals answer questions of what would have been observed under altered circumstances and can therefore offer valuable insights. Whereas the classical interventional interpretation of counterfactuals has been studied extensively, backtracking constitutes a less studied alternative where all causal laws are kept intact. In the present work, we introduce a practical method called deep backtracking counterfactuals (DeepBC) for computing backtracking counterfactuals in structural causal models that consist of deep generative components. We propose two distinct versions of our method—one utilizing Langevin Monte Carlo sampling and the other employing constrained optimization—to generate counterfactuals for high-dimensional data. As a special case, our formulation reduces to methods in the field of counterfactual explanations. Compared to these, our approach represents a causally compliant, versatile and modular alternative. We demonstrate these properties experimentally on a modified version of MNIST and CelebA.
Submission Length: Long submission (more than 12 pages of main content)
Code: https://github.com/rudolfwilliam/DeepBC
Assigned Action Editor: ~Pascal_Poupart2
Submission Number: 2164
Loading