mlsanityData to 7 Oct 2026

Incorporating Causal Graphical Prior Knowledge into Predictive Modeling via Simple Data Augmentation

arXiv 2103.00136 ↗First posted 27 Feb 2021cs.LG stat.MLcited by 10

Not on the map. Why?

Abstract (arXiv)

Causal graphs (CGs) are compact representations of the knowledge of the data generating processes behind the data distributions. When a CG is available, e.g., from the domain knowledge, we can infer the conditional independence (CI) relations that should hold in the data distribution. However, it is not straightforward how to incorporate this knowledge into predictive modeling. In this work, we propose a model-agnostic data augmentation method that allows us to exploit the prior knowledge of the CI encoded in a CG for supervised machine learning. We theoretically justify the proposed method by providing an excess risk bound indicating that the proposed method suppresses overfitting by reducing the apparent complexity of the predictor hypothesis class. Using real-world data with CGs provided by domain experts, we experimentally show that the proposed method is effective in improving the prediction accuracy, especially in the small-data regime.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 19 of its 72 references that are in the map. First posted on arXiv 27 Feb 2021.

Builds on

19 of 72 references.

References · 19

  1. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  2. 2013Causal Discovery with Continuous Additive Noise Modelscited by 252
  3. 2013Causal Inference in the Presence of Latent Variables and Selection Biascited by 165
  4. 2017Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributionscited by 125
  5. 2020Counterfactual Data Augmentation using Locally Factored Dynamicscited by 93
  6. 2019Causal Discovery with General Non-Linear Relationships Using Non-Linear ICAcited by 58
  7. 2020Few-shot Domain Adaptation by Causal Mechanism Transfercited by 47
  8. 2020CASTLE: Regularization via Auxiliary Causal Graph Discoverycited by 41
  9. 2017Nested Markov Properties for Acyclic Directed Mixed Graphscited by 38
  10. 2017Learning Causal Structures Using Regression Invariancecited by 32
  11. 2020Semiparametric Inference For Causal Effects In Graphical Models With Hidden Variablescited by 23
  12. 2013Cyclic Causal Discovery from Continuous Equilibrium Datacited by 21
7 more
  1. 2020Efficient adjustment sets in causal graphical models with hidden variablescited by 13
  2. 2019Causal bootstrappingcited by 11
  3. 2019Causality-based Feature Selection: Methods and Evaluationscited by 11
  4. 2013Markovian acyclic directed mixed graphs for discrete datacited by 10
  5. 2019Improving Model Robustness Using Causal Knowledgecited by 7
  6. 2015Removing systematic errors for exoplanet search via latent causescited by 4
  7. 2016PAG2ADMG: An Algorithm for the Complete Causal Enumeration of a Markov Equivalence Classcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 5; 2024: 0; 2025: 1; 2026: 1.

10 papers.

  1. 2023Causal Order: The Key to Leveraging Imperfect Experts in Causal Inferencecited by 46
  2. 2022Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalizationcited by 20
  3. 2023Causal Deep Learningcited by 20
  4. 2023Toward Falsifying Causal Graphs Using a Permutation-Based Testcited by 11
  5. 2022Knowledge-augmented Deep Learning and Its Applications: A Surveycited by 10
  6. 2023A Guide for Practical Use of ADMG Causal Data Augmentationcited by 2
  7. 2022Navigating causal deep learningcited by 1
  8. 2023Enhancing the Performance of Neural Networks Through Causal Discovery and Integration of Domain Knowledgecited by 1
  9. 2025Disconnect to Connect: A Data Augmentation Method for Improving Topology Accuracy in Image Segmentationcited by 1
  10. 2026Data Augmentation via Causal-Residual Bootstrappingcited by 0