Semi-supervised Learning of Visual Causal Macrovariables
Keywords:Causal Representation Learning, Explainable Artificial Intelligence, Semi-supervised Learning
Discovery of causally related concepts is one of the key challenges in extracting knowledge from observational data. Lower-dimensional “causal macrovariables” represent concepts which preserve all relevant causal information in high-dimensional systems. Existing causal macrovariable discovery algorithms are limited by assumptions about known and controllable interventions. We propose a variational autoencoder-inspired architecture with regularization terms for semi-supervised causal macrovariable discovery. These terms impose domain knowledge regarding visual causal concepts to differentiate between correlation and causation. Experiments on both synthetic and real-world datasets with known causal dynamics show that our method can discover more concise and precise causal macrovariables than unsupervised methods.
How to Cite
Copyright (c) 2023 Aruna Jammalamadaka, Lingyi Zhang, Joseph Comer, Sasha Strelnikoff, Ryan Mustari, Tsai-Ching Lu, Rajan Bhattacharyya
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.