mlsanityData to 7 Oct 2026

Distributionally Robust Optimization with Probabilistic Group

arXiv 2303.05809 ↗First posted 10 Mar 2023cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Modern machine learning models may be susceptible to learning spurious correlations that hold on average but not for the atypical group of samples. To address the problem, previous approaches minimize the empirical worst-group risk. Despite the promise, they often assume that each sample belongs to one and only one group, which does not allow expressing the uncertainty in group labeling. In this paper, we propose a novel framework PG-DRO, which explores the idea of probabilistic group membership for distributionally robust optimization. Key to our framework, we consider soft group membership instead of hard group annotations. The group probabilities can be flexibly generated using either supervised learning or zero-shot approaches. Our framework accommodates samples with group membership ambiguity, offering stronger flexibility and generality than the prior art. We comprehensively evaluate PG-DRO on both image classification and natural language processing benchmarks, establishing superior performance

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 31 of its 45 references that are in the map. First posted on arXiv 10 Mar 2023.

Builds on

31 of 45 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  7. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  8. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  9. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  10. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  11. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  12. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
19 more
  1. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  2. 2018Annotation Artifacts in Natural Language Inference Datacited by 656
  3. 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 522
  4. 2019Agnostic Federated Learningcited by 451
  5. 2019Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classificationcited by 396
  6. 2020An Investigation of Why Overparameterization Exacerbates Spurious Correlationscited by 310
  7. 2020Environment Inference for Invariant Learningcited by 306
  8. 2015Data-driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulationscited by 285
  9. 2018What is the Effect of Importance Weighting in Deep Learning?cited by 250
  10. 2019Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imagingcited by 215
  11. 2020No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problemscited by 208
  12. 2020Large-Scale Methods for Distributionally Robust Optimizationcited by 179
  13. 2022Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlationscited by 171
  14. 2016Variance-based regularization with convex objectivescited by 153
  15. 2020An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Modelscited by 133
  16. 2022Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimationcited by 88
  17. 2013Data-Driven Robust Optimizationcited by 84
  18. 2020Model Patching: Closing the Subgroup Performance Gap with Data Augmentationcited by 82
  19. 2020Coping with Label Shift via Distributionally Robust Optimisationcited by 69

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 5; 2026: 4.

14 papers.

Sort:

By area:

  1. 2024ARGS: Alignment as Reward-Guided Searchcited by 99
  2. 2024Process Reward Model with Q-Value Rankingscited by 78
  3. 2023Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detectioncited by 57
  4. 2024FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detectioncited by 14
  5. 2024On the Learnability of Out-of-distribution Detectioncited by 8
  6. 2025Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Setscited by 7
  7. 2025Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approachcited by 5
  8. 2025Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergiescited by 2
  9. 2025Group Distributionally Robust Machine Learning under Group Level Distributional Uncertaintycited by 2
  10. 2025Subgroups Matter for Robust Bias Mitigationcited by 1
  11. 2026Generalizable Multimodal Large Language Model Editing via Invariant Trajectory Learningcited by 1
  12. 2026Closing the loop in learning with missing datacited by 0
2 more
  1. 2026Learning the Robustness Mechanism with Bilevel Optimizationcited by 0
  2. 2026Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noisecited by 0