mlsanityData to 7 Oct 2026

DeconDTN-Toolkit: A Library for Evaluation and Enhancement of Robustness to Provenance Shift

arXiv 2605.11237 ↗First posted 11 May 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Despite the burgeoning body of work on distribution shifts, provenance shift-where the relationship between data source and label changes at deployment-remains poorly understood and under-addressed. In this paper, we establish a formal connection between provenance shift, counterfactual invariance, and invariant learning to derive a learning objective for robustness. We then introduce textscDeconDTN-Toolkit, a specialized evaluation and remediation suite designed to simulate provenance shifts of varying degrees while maintaining the training protocol and the infrastructure of existing benchmarks. We reveal the vulnerability of Empirical Risk Minimization under provenance shift, introduce a robust out-of-distribution performance indicator, and conduct a comprehensive evaluation on existing algorithms. Our work provides both the theoretical grounding and the practical tools necessary to characterize the problem of confounding by provenance, and implementations of methods to mitigate it.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 49 of its 77 references that are in the map. First posted on arXiv 11 May 2026.

Builds on

49 of 77 references.

References · 49

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  6. 2019Invariant Risk Minimizationcited by 1,832
  7. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  8. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  9. 2020In Search of Lost Domain Generalizationcited by 1,042
  10. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  11. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  12. 2021Domain Generalization: A Surveycited by 760
37 more
  1. 2022Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learningcited by 553
  2. 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 522
  3. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 442
  4. 2019Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classificationcited by 396
  5. 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 379
  6. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 364
  7. 2020An Investigation of Why Overparameterization Exacerbates Spurious Correlationscited by 310
  8. 2020Pretrained Transformers Improve Out-of-Distribution Robustnesscited by 293
  9. 2021Gradient Matching for Domain Generalizationcited by 258
  10. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
  11. 2020Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detectioncited by 217
  12. 2022Improving Out-of-Distribution Robustness via Selective Augmentationcited by 202
  13. 2018Hate Speech Dataset from a White Supremacy Forumcited by 196
  14. 2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
  15. 2020Improve Unsupervised Domain Adaptation with Mixup Trainingcited by 185
  16. 2017Domain Generalization by Marginal Transfer Learningcited by 180
  17. 2021Simple data balancing achieves competitive worst-group-accuracycited by 177
  18. 2023Change is Hard: A Closer Look at Subpopulation Shiftcited by 119
  19. 2024Causal Representation Learning from Multiple Distributions: A General Settingcited by 67
  20. 2022Probable Domain Generalization via Quantile Risk Minimizationcited by 66
  21. 2021Examining and Combating Spurious Features under Distribution Shiftcited by 64
  22. 2021Optimal Representations for Covariate Shiftcited by 51
  23. 2024A Decade's Battle on Dataset Bias: Are We There Yet?cited by 46
  24. 2022Probing Classifiers are Unreliable for Concept Removal and Detectioncited by 40
  25. 2020Annotating Social Determinants of Health Using Active Learning, and Characterizing Determinants Using Neural Event Extractioncited by 32
  26. 2022Why does Throwing Away Data Improve Worst-Group Error?cited by 22
  27. 2022Explicit Tradeoffs between Adversarial and Natural Distributional Robustnesscited by 20
  28. 2023When More is Less: Incorporating Additional Datasets Can Hurt Performance By Introducing Spurious Correlationscited by 18
  29. 2024The Data Addition Dilemmacited by 15
  30. 2024Mind the Graph When Balancing Data for Fairness or Robustnesscited by 9
  31. 2023Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixupcited by 8
  32. 2024Ask Your Distribution Shift if Pre-Training is Right for Youcited by 7
  33. 2023Backdoor Adjustment of Confounding by Provenance for Robust Text Classification of Multi-institutional Clinical Notescited by 5
  34. 2024Towards Understanding Variants of Invariant Risk Minimization through the Lens of Calibrationcited by 3
  35. 2025Mitigating Confounding in Speech-Based Dementia Detection through Weight Maskingcited by 3
  36. 2025Mitigating Shortcut Learning with InterpoLated Learningcited by 2
  37. 2023Enhancing Robustness of Foundation Model Representations under Provenance-related Distribution Shiftscited by 1

Built on by

Not cited yet.