mlsanityData to 7 Oct 2026

Learning Counterfactually Invariant Predictors

arXiv 2207.09768 ↗First posted 20 Jul 2022cs.LG stat.MLcited by 10

Not on the map. Why?

Abstract (arXiv)

Notions of counterfactual invariance (CI) have proven essential for predictors that are fair, robust, and generalizable in the real world. We propose graphical criteria that yield a sufficient condition for a predictor to be counterfactually invariant in terms of a conditional independence in the observational distribution. In order to learn such predictors, we propose a model-agnostic framework, called Counterfactually Invariant Prediction (CIP), building on the Hilbert-Schmidt Conditional Independence Criterion (HSCIC), a kernel-based conditional dependence measure. Our experimental results demonstrate the effectiveness of CIP in enforcing counterfactual invariance across various simulated and real-world datasets including scalar and multi-variate settings.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 33 of its 85 references that are in the map. First posted on arXiv 20 Jul 2022.

Builds on

33 of 85 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  4. 2019Invariant Risk Minimizationcited by 1,832
  5. 2017Deep Setscited by 1,394
  6. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  7. 2016Group Equivariant Convolutional Networkscited by 1,154
  8. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  9. 2017Counterfactual Fairnesscited by 802
  10. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 533
  11. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 443
  12. 2016Kernel Mean Embedding of Distributions: A Review and Beyondcited by 360
21 more
  1. 2017Avoiding Discrimination through Causal Reasoningcited by 191
  2. 2018Path-Specific Counterfactual Fairnesscited by 179
  3. 2017Fair Inference On Outcomescited by 143
  4. 2017Invariant Causal Prediction for Nonlinear Modelscited by 140
  5. 2018Invariance, Causality and Robustnesscited by 123
  6. 2020A Measure-Theoretic Approach to Kernel Conditional Mean Embeddingscited by 86
  7. 2018Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guaranteescited by 71
  8. 2021Causally motivated Shortcut Removal Using Auxiliary Labelscited by 55
  9. 2018Causal Reasoning for Algorithmic Fairnesscited by 51
  10. 2017Characteristic and Universal Tensor Product Kernelscited by 41
  11. 2016Kernel Distribution Embeddings: Universal Kernels, Characteristic Kernels and Kernel Metrics on Distributionscited by 39
  12. 2020Metrizing Weak Convergence with Maximum Mean Discrepanciescited by 35
  13. 2020Causal Feature Selection for Algorithmic Fairnesscited by 25
  14. 2016Achieving non-discrimination in data releasecited by 23
  15. 2019A Unifying Causal Framework for Analyzing Dataset Shift-stable Learning Algorithmscited by 17
  16. 2022Selection, Ignorability and Challenges With Causal Fairnesscited by 16
  17. 2020Fairness Under Feature Exemptions: Counterfactual and Observational Measurescited by 15
  18. 2020Algorithmic Decision Making with Conditional Fairnesscited by 14
  19. 2021Fairness with Continuous Optimal Transportcited by 9
  20. 2022Breaking Correlation Shift via Conditional Invariant Regularizercited by 7
  21. 2019Capuchin: Causal Database Repair for Algorithmic Fairnesscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 1; 2025: 4; 2026: 1.

10 papers.

  1. 2025Beyond Reward Hacking: Causal Rewards for Large Language Model Alignmentcited by 42
  2. 2022Efficient Conditionally Invariant Representation Learningcited by 19
  3. 2025When Shift Happens - Confounding Is to Blamecited by 5
  4. 2023Results on Counterfactual Invariancecited by 4
  5. 2023Prediction without Preclusion: Recourse Verification with Reachable Setscited by 4
  6. 2023Causal Information Splitting: Engineering Proxy Features for Robustness to Distribution Shiftscited by 2
  7. 2024Learning Conditional Invariances through Non-Commutativitycited by 1
  8. 2025AI Alignment in Medical Imaging: Unveiling Hidden Biases Through Counterfactual Analysiscited by 1
  9. 2025DISCO: Mitigating Bias in Deep Learning with Conditional Distance Correlationcited by 0
  10. 2026A pipeline for enabling path-specific causal fairness in observational health datacited by 0