mlsanityData to 14 Oct 2026

Spurious Correlations and Where to Find Them

arXiv 2308.11043 ↗First posted 21 Aug 2023cs.LG stat.MLcited by 6

Not on the map. Why?

Abstract (arXiv)

Spurious correlations occur when a model learns unreliable features from the data and are a well-known drawback of data-driven learning. Although there are several algorithms proposed to mitigate it, we are yet to jointly derive the indicators of spurious correlations. As a result, the solutions built upon standalone hypotheses fail to beat simple ERM baselines. We collect some of the commonly studied hypotheses behind the occurrence of spurious correlations and investigate their influence on standard ERM baselines using synthetic datasets generated from causal graphs. Subsequently, we observe patterns connecting these hypotheses and model design choices.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 17 of its 24 references that are in the map. First posted on arXiv 21 Aug 2023.

Builds on

17 of 24 references.

References · 17

  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. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  5. 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 381
  6. 2020The Pitfalls of Simplicity Bias in Neural Networkscited by 351
  7. 2020An Investigation of Why Overparameterization Exacerbates Spurious Correlationscited by 310
  8. 2018Deep learning generalizes because the parameter-function map is biased towards simple functionscited by 183
  9. 2021Simple data balancing achieves competitive worst-group-accuracycited by 178
  10. 2020Understanding the Failure Modes of Out-of-Distribution Generalizationcited by 146
  11. 2022On Feature Learning in the Presence of Spurious Correlationscited by 145
  12. 2020What shapes feature representations? Exploring datasets, architectures, and trainingcited by 126
5 more
  1. 2021Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Modelscited by 76
  2. 2021Examining and Combating Spurious Features under Distribution Shiftcited by 65
  3. 2020Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionatelycited by 52
  4. 2013Challenges of Big Data Analysiscited by 47
  5. 2021CausalAdv: Adversarial Robustness through the Lens of Causalitycited by 37

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 1.

6 papers.

  1. 2024Mind the Graph When Balancing Data for Fairness or Robustnesscited by 9
  2. 2026Shortcut Learning in Binary Classifier Black Boxes: Applications to Voice Anti-Spoofing and Biometricscited by 6
  3. 2024Reassessing the Validity of Spurious Correlations Benchmarkscited by 4
  4. 2025Latent Space Factorization in LoRAcited by 2
  5. 2024The Pragmatic Frames of Spurious Correlations in Machine Learning: Interpreting How and Why They Mattercited by 0
  6. 2025Incorporating Interventional Independence Improves Robustness against Interventional Distribution Shiftcited by 0