Navigating causal deep learning
Not on the map. Why?
Abstract (arXiv)
Causal deep learning (CDL) is a new and important research area in the larger field of machine learning. With CDL, researchers aim to structure and encode causal knowledge in the extremely flexible representation space of deep learning models. Doing so will lead to more informed, robust, and general predictions and inference -- which is important! However, CDL is still in its infancy. For example, it is not clear how we ought to compare different methods as they are so different in their output, the way they encode causal knowledge, or even how they represent this knowledge. This is a living paper that categorises methods in causal deep learning beyond Pearl's ladder of causation. We refine the rungs in Pearl's ladder, while also adding a separate dimension that categorises the parametric assumptions of both input and representation, arriving at the map of causal deep learning. Our map covers machine learning disciplines such as supervised learning, reinforcement learning, generative modelling and beyond. Our paradigm is a tool which helps researchers to: find benchmarks, compare methods, and most importantly: identify research gaps. With this work we aim to structure the avalanche of papers being published on causal deep learning. While papers on the topic are being published daily, our map remains fixed. We open-source our map for others to use as they see fit: perhaps to offer guidance in a related works section, or to better highlight the contribution of their paper.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 26 of its 81 references that are in the map. First posted on arXiv 1 Dec 2022.
Builds on
26 of 81 references.
References · 26
- 2017Attention Is All You Needcited by 59,932
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 643
- 2017Nonparametric regression using deep neural networks with ReLU activation functioncited by 431
- 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 212
- 2019Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterizationcited by 187
- 2018Invariance, Causality and Robustnesscited by 123
- 2019Synthetic Data for Deep Learningcited by 113
- 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
- 2021SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networkscited by 108
- 2020Causal Interpretability for Machine Learning -- Problems, Methods and Evaluationcited by 82
14 more
- 2021MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanismscited by 50
- 2015How much data is needed to train a medical image deep learning system to achieve necessary high accuracy?cited by 45
- 2013Strong Completeness and Faithfulness in Bayesian Networkscited by 44
- 2020CASTLE: Regularization via Auxiliary Causal Graph Discoverycited by 41
- 2020Causality Learning: A New Perspective for Interpretable Machine Learningcited by 28
- 2013On the Logic of Causal Modelscited by 19
- 2013The Recovery of Causal Poly-Trees from Statistical Datacited by 19
- 2019Beyond Human-Level Accuracy: Computational Challenges in Deep Learningcited by 19
- 2020Learning Robust Models Using The Principle of Independent Causal Mechanismscited by 18
- 2019Learning Interpretable Models with Causal Guaranteescited by 11
- 2021Incorporating Causal Graphical Prior Knowledge into Predictive Modeling via Simple Data Augmentationcited by 10
- 2021Matching Learned Causal Effects of Neural Networks with Domain Priorscited by 10
- 2021Disentangled Counterfactual Recurrent Networks for Treatment Effect Inference over Timecited by 9
- 2019Improving Model Robustness Using Causal Knowledgecited by 7
Built on by
Citing papers per year: 2025: 1.
1 paper.