iCITRIS: Causal Representation Learning for Instantaneous Temporal Effects

Phillip Lippe, Sara Magliacane, Sindy Löwe, Yuki M Asano, Taco Cohen, Efstratios Gavves

Keywords: Instantaneous Effects, Causal Representation Learning, Identifiability, Causal Discovery, Causal Structure Learning

TL;DR: We present a causal representation learning method that can identify causal variables with instantaneous effects and their graph from temporal sequences with interventions.

Abstract: Causal representation learning is the task of identifying the underlying causal variables and their relations from high-dimensional observations, such as images. Recent work has shown that one can reconstruct the causal variables from temporal sequences of observations under the assumption that there are no instantaneous causal relations between them. In practical applications, however, our measurement or frame rate might be slower than many of the causal effects. This effectively creates ``instantaneous'' effects and invalidates previous identifiability results. To address this issue, we propose iCITRIS, a causal representation learning method that can handle instantaneous effects in temporal sequences when given perfect interventions with known intervention targets. iCITRIS identifies the intervention-dependent part of the causal factors from temporal observations, while simultaneously using a differentiable causal discovery method to learn their causal graph. We demonstrate this in experiments on two video datasets.