Multi-Scope Representation Learning for Causal Relation Discovery with new Challenging Datasets


Jiageng Zhu (University of Southern California), Hanchen Xie (Bosch), Jianhua Wu (University of Southern California), Mohamed E. Hussein (USC/ISI), Mahyar Khayatkhoei (USC/ISI), Jiazhi Li (Futurewei Technologies Inc.), Wael AbdAlmageed (Clemson University)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Discovering semantic meaningful latent factors and the causal relations among them is an emergent topic in representation learning with notable impacts on real-world applications. However, many existing Causal Representation Learning (CRL) methods are hindered by strong assumptions, such as full data annotation, the need for counterfactual data, and/or prior knowledge of the causal structure. To address these limitations, we introduce Causal-Macro, a weakly supervised architecture that effectively discovers semantic causal factors and learns their causal relations. We theoretically show that Causal-Macro is identifiable in the sense that the marginalized posterior distribution of learned factors can be identified up to coordinate-wise reparameterization of ground-truth factors. In addition, we show that existing CRL datasets are limited to simple causal graphs with a small number of generative factors. Thus, we propose two new datasets with a larger number of diverse generative factors and more sophisticated causal graphs. Our comprehensive evaluations demonstrate the superior performance of Causal-Macro over existing methods, supported by detailed studies highlighting the impact of each design element in Causal-Macro.

Citation

@inproceedings{Zhu_2024_BMVC,
author    = {Jiageng Zhu and Hanchen Xie and Jianhua Wu and Mohamed E. Hussein and Mahyar Khayatkhoei and Jiazhi Li and Wael AbdAlmageed},
title     = {Multi-Scope Representation Learning for Causal Relation Discovery with new Challenging Datasets},
booktitle = {35th British Machine Vision Conference 2024, {BMVC} 2024, Glasgow, UK, November 25-28, 2024},
publisher = {BMVA},
year      = {2024},
url       = {https://papers.bmvc2024.org/0572.pdf}
}


Copyright © 2024 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection