Skip to yearly menu bar Skip to main content


On Data Manifolds Entailed by Structural Causal Models

Ricardo Dominguez-Olmedo · Amir-Hossein Karimi · Georgios Arvanitidis · Bernhard Schölkopf

Exhibit Hall 1 #638


The geometric structure of data is an important inductive bias in machine learning. In this work, we characterize the data manifolds entailed by structural causal models. The strengths of the proposed framework are twofold: firstly, the geometric structure of the data manifolds is causally informed, and secondly, it enables causal reasoning about the data manifolds in an interventional and a counterfactual sense. We showcase the versatility of the proposed framework by applying it to the generation of causally-grounded counterfactual explanations for machine learning classifiers, measuring distances along the data manifold in a differential geometric-principled manner.

Chat is not available.