max-ilse / deepcausality

A list of papers that combines causality and deep learning

DeepCausality

This is an attempt to stay on top of the ever increasing number of papers that combine flexible neural function approximators (aka neural networks) and causality research. I tried to organize the papers into a small number of categories. Some papers are part of multiple categories. If you happen to come across this list and want to add a paper please send me a pull request.

Approximating SCMs

Murat Kocaoglu, Christopher Snyder, Alexandros G. Dimakis, Sriram Vishwanath. 2017. CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training. https://arxiv.org/abs/1709.02023

Nick Pawlowski, Daniel C. Castro, Ben Glocker. 2020. Deep Structural Causal Models for Tractable Counterfactual Inference. https://arxiv.org/abs/2006.06485

Saloni Dash, Amit Sharma. 2020. Counterfactual Generation and Fairness Evaluation Using Adversarially Learned Inference. https://arxiv.org/abs/2009.08270

Ilyes Khemakhem, Ricardo Pio Monti, Robert Leech, Aapo Hyvärinen. 2020. Causal Autoregressive Flows. https://arxiv.org/abs/2011.02268

Raha Moraffah, Bahman Moraffah, Mansooreh Karami, Adrienne Raglin, Huan Liu. 2020. Causal Adversarial Network for Learning Conditional and Interventional Distributions. https://arxiv.org/abs/2008.11376

Estimating the treatment effect from observational data/unobserved confounding

Christos Louizos, Uri Shalit, Joris Mooij, David Sontag, Richard Zemel, Max Welling. 2017. Causal Effect Inference with Deep Latent-Variable Models. https://arxiv.org/abs/1705.08821

Yunzhe Li, Kun Kuang, Bo Li, Peng Cui, Jianrong Tao, Hongxia Yang, Fei Wu. 2020. Continuous Treatment Effect Estimation via Generative Adversarial De-confounding. http://proceedings.mlr.press/v127/li20a.html

Pengzhou Wu, Kenji Fukumizu. 2021. Identifying Treatment Effects under Unobserved Confounding by Causal Representation Learning. https://arxiv.org/abs/2101.06662

Meta Learning and causality

Sören R. Künzel, Jasjeet S. Sekhon, Peter J. Bickel, Bin Yu. 2017. Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learning. https://arxiv.org/abs/1706.03461

Yoshua Bengio, Tristan Deleu, Nasim Rahaman, Rosemary Ke, Sébastien Lachapelle, Olexa Bilaniuk, Anirudh Goyal, Christopher Pal. 2019. A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms. https://arxiv.org/abs/1901.10912

A causal interpretation of deep learning methods

Jovana Mitrovic, Brian McWilliams, Jacob Walker, Lars Buesing, Charles Blundell. 2020. Representation Learning via Invariant Causal Mechanisms. https://arxiv.org/abs/2010.07922

Maximilian Ilse, Jakub M. Tomczak, Patrick Forré. 2020. Selecting Data Augmentation for Simulating Interventions. https://arxiv.org/abs/2005.01856

Domain adaptation and generalisation