ICML Spotlight: CITRIS - Causal Identifiability from Temporal Intervened Sequences

CITRIS

Abstract

In this spotlight talk, I introduce CITRIS - our new causal representation learning framework. CITRIS identifies causal variables and their graph from temporal observations like videos, in which interventions have been performed. For more details, check out our paper.

Date
Jul 20, 2022 15:00 — 16:00
Event
International Conference on Machine Learning (ICML 2022)
Location
Baltimore, USA