Semi-supervised Learning of Visual Causal Macrovariables
Open Access
- 8 May 2023
- journal article
- research article
- Published by University of Florida George A Smathers Libraries in The International FLAIRS Conference Proceedings
- Vol. 36
Abstract
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.Keywords
This publication has 1 reference indexed in Scilit:
- Explainable Models with Consistent InterpretationsProceedings of the AAAI Conference on Artificial Intelligence, 2021