Causal Machine Learning: A Survey and Open Problems
Foundations and Trends® in Optimization · 2025-06-15 · 9 (1-2) · 1-247
DOI: 10.1561/2400000052 ↗At a glance
Journal article in Foundations and Trends® in Optimization, published online on 2025-06-15. Written by Jean Kaddour and 4 co-authors. Cited 27 times so far (Crossref); 521 references.
Abstract (original language)
Causal Machine Learning (CausalML) is an umbrella term for machine learning methods that formalize the data- generation process as a causal model. This perspective enables one to reason about the effects of changes to this process (interventions) and what would have happened in hindsight (counterfactuals). We categorize work in CausalML into five groups according to the problems they address: (1) causal supervised learning, (2) causal generative modeling, (3) causal explanations, (4) causal fairness, and (5) causal reinforcement learning. We systematically compare approaches in each category and point out open problems. Further, we review field-specific applications in computer vision, natural language processing, and graph representation learning. Finally, we provide an overview of causal benchmarks and a discussion of the state of this nascent field, including recommendations for future work.
Cite
APA
Kaddour, J., Lynch, A., Liu, Q., Kusner, M. J., & Ricardo, S. (2025). Causal Machine Learning: A Survey and Open Problems. Foundations and Trends® in Optimization, 9(1-2), 1-247. https://doi.org/10.1561/2400000052
Vancouver
Kaddour J, Lynch A, Liu Q, Kusner MJ, Ricardo S. Causal Machine Learning: A Survey and Open Problems. Foundations and Trends® in Optimization. 2025;9(1-2):1-247. doi:10.1561/2400000052
BibTeX
@article{Kaddour2025,
author = {Kaddour, Jean and Lynch, Aengus and Liu, Qi and Kusner, Matt J. and Ricardo, Silva},
title = {Causal Machine Learning: A Survey and Open Problems},
journal = {Foundations and Trends® in Optimization},
year = {2025},
volume = {9},
number = {1-2},
pages = {1--247},
doi = {10.1561/2400000052}
}
EUVIMED