Backtracking Counterfactuals for Deep Structural Causal Models

Klaus-Rudolf Kladny, Julius von Kügelgen, Bernhard Schölkopf, Michael Muehlebach

Keywords: Counterfactual, Structural Causal Model, Deep Generative Model, XAI, Backtracking

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 employ constrained optimization to generate counterfactuals for high-dimensional data and conduct experiments on a modified version of MNIST.

Submission Number: 5