CITRIS

Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems
Causal representation learning is the task of identifying the underlying causal variables and their relations from high-dimensional …
Phillip Lippe, Sara Magliacane, Sindy Löwe, Yuki M Asano, Taco Cohen, Efstratios Gavves
PDF Cite Code Poster URL
CITRIS: Causal Identifiability from Temporal Intervened Sequences
In CITRIS we show under which conditions can one learn causal factors from sequences of high-dimensional data, e.g. images, in case one has access to the intervention targets.
Phillip Lippe, Sara Magliacane, Sindy Löwe, Yuki M Asano, Taco Cohen, Stratis Gavves
PDF Cite Code Dataset Poster Slides Source Document
CITRIS: Causal Identifiability from Temporal Intervened Sequences
Intervention Design for Causal Representation Learning
In this paper, we take a first step towards bringing two fields of causality closer together, intervention design and causal …
Phillip Lippe, Sara Magliacane, Sindy Löwe, Yuki M Asano, Taco Cohen, Efstratios Gavves
PDF Cite Code Poster Slides URL
Intervention Design for Causal Representation Learning