mlsanityData to 14 Oct 2026

Learning Invariant Representations with Missing Data

arXiv 2112.00881 ↗First posted 1 Dec 2021cs.LG stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

Spurious correlations allow flexible models to predict well during training but poorly on related test distributions. Recent work has shown that models that satisfy particular independencies involving correlation-inducing textitnuisance variables have guarantees on their test performance. Enforcing such independencies requires nuisances to be observed during training. However, nuisances, such as demographics or image background labels, are often missing. Enforcing independence on just the observed data does not imply independence on the entire population. Here we derive acrshortmmd estimators used for invariance objectives under missing nuisances. On simulations and clinical data, optimizing through these estimates achieves test performance similar to using estimators that make use of the full data.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 18 of its 44 references that are in the map. First posted on arXiv 1 Dec 2021.

Builds on

18 of 44 references.

References · 18

  1. 2020Shortcut Learning in Deep Neural Networkscited by 1,969
  2. 2019Invariant Risk Minimizationcited by 1,854
  3. 2020In Search of Lost Domain Generalizationcited by 1,054
  4. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 742
  5. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 536
  6. 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 523
  7. 2020An Investigation of Why Overparameterization Exacerbates Spurious Correlationscited by 310
  8. 2020Environment Inference for Invariant Learningcited by 306
  9. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  10. 2018Why Is My Classifier Discriminatory?cited by 143
  11. 2020Robust Optimization for Fairness with Noisy Protected Groupscited by 78
  12. 2021Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Testscited by 77
6 more
  1. 2021Causally motivated Shortcut Removal Using Auxiliary Labelscited by 55
  2. 2017Characteristic and Universal Tensor Product Kernelscited by 41
  3. 2021Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlationscited by 41
  4. 2020Representation via Representations: Domain Generalization via Adversarially Learned Invariant Representationscited by 26
  5. 2021Deconfounding Scores: Feature Representations for Causal Effect Estimation with Weak Overlapcited by 9
  6. 2013Pylearn2: a machine learning research librarycited by 2

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 2.

4 papers.

  1. 2021BARACK: Partially Supervised Group Robustness With Guaranteescited by 25
  2. 2023Robustness to Spurious Correlations Improves Semantic Out-of-Distribution Detectioncited by 4
  3. 2022A Survey on Preserving Fairness Guarantees in Changing Environmentscited by 2
  4. 2023Partial identification of kernel based two sample tests with mismeasured datacited by 0