mlsanityData to 7 Oct 2026

Domain Generalisation via Imprecise Learning

arXiv 2404.04669 ↗First posted 6 Apr 2024cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) generalisation is challenging because it involves not only learning from empirical data, but also deciding among various notions of generalisation, e.g., optimising the average-case risk, worst-case risk, or interpolations thereof. While this choice should in principle be made by the model operator like medical doctors, this information might not always be available at training time. The institutional separation between machine learners and model operators leads to arbitrary commitments to specific generalisation strategies by machine learners due to these deployment uncertainties. We introduce the Imprecise Domain Generalisation framework to mitigate this, featuring an imprecise risk optimisation that allows learners to stay imprecise by optimising against a continuous spectrum of generalisation strategies during training, and a model framework that allows operators to specify their generalisation preference at deployment. Supported by both theoretical and empirical evidence, our work showcases the benefits of integrating imprecision into domain generalisation.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 52 of its 92 references that are in the map. First posted on arXiv 6 Apr 2024.

Builds on

52 of 92 references.

References · 52

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  5. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  6. 2016Group Equivariant Convolutional Networkscited by 1,154
  7. 2016HyperNetworkscited by 1,003
  8. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 809
  9. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  10. 2021Domain Generalization: A Surveycited by 760
  11. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  12. 2018Recognition in Terra Incognitacited by 655
38 more
  1. 2013Domain Generalization via Invariant Feature Representationcited by 622
  2. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 533
  3. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  4. 2019AutoML: A Survey of the State-of-the-Artcited by 388
  5. 2018A Survey of Unsupervised Deep Domain Adaptationcited by 361
  6. 2020Performative Predictioncited by 318
  7. 2020The Risks of Invariant Risk Minimizationcited by 262
  8. 2020Gradient Starvation: A Learning Proclivity in Neural Networkscited by 262
  9. 2015Strategic Classificationcited by 256
  10. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  11. 2019Pareto Multi-Task Learningcited by 224
  12. 2020Domain Generalization using Causal Matchingcited by 224
  13. 2020Adaptive Risk Minimization: Learning to Adapt to Domain Shiftcited by 183
  14. 2017Domain Generalization by Marginal Transfer Learningcited by 180
  15. 2017Invariant Causal Prediction for Nonlinear Modelscited by 140
  16. 2023Change is Hard: A Closer Look at Subpopulation Shiftcited by 119
  17. 2018Anchor regression: heterogeneous data meets causalitycited by 116
  18. 2021Does Invariant Risk Minimization Capture Invariance?cited by 116
  19. 2020A Review of Single-Source Deep Unsupervised Visual Domain Adaptationcited by 96
  20. 2021Heterogeneous Risk Minimizationcited by 90
  21. 2020The iWildCam 2020 Competition Datasetcited by 86
  22. 2019Fairness risk measurescited by 85
  23. 2022Probable Domain Generalization via Quantile Risk Minimizationcited by 66
  24. 2021Out of Distribution Generalization in Machine Learningcited by 59
  25. 2020Efficient Continuous Pareto Exploration in Multi-Task Learningcited by 57
  26. 2023Improved Test-Time Adaptation for Domain Generalizationcited by 45
  27. 2021On Tilted Losses in Machine Learning: Theory and Applicationscited by 42
  28. 2022Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalizationcited by 38
  29. 2022Probabilistically Robust Learning: Balancing Average- and Worst-case Performancecited by 36
  30. 2022WOODS: Benchmarks for Out-of-Distribution Generalization in Time Seriescited by 29
  31. 2021Deconditional Downscaling with Gaussian Processescited by 24
  32. 2021BayesIMP: Uncertainty Quantification for Causal Data Fusioncited by 21
  33. 2023Spuriosity Didn't Kill the Classifier: Using Invariant Predictions to Harness Spurious Featurescited by 21
  34. 2020Learning Inconsistent Preferences with Gaussian Processescited by 11
  35. 2024Do causal predictors generalize better to new domains?cited by 11
  36. 2023Causal Strategic Learning with Competitive Selectioncited by 9
  37. 2020Spectral Ranking with Covariatescited by 8
  38. 2021An Imprecise SHAP as a Tool for Explaining the Class Probability Distributions under Limited Training Datacited by 6

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 8; 2026: 5.

14 papers.

Sort:

  1. 2025Integral Imprecise Probability Metricscited by 11
  2. 2024Scoring Rules and Calibration for Imprecise Probabilitiescited by 10
  3. 2025Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'cited by 8
  4. 2025Truthful Elicitation of Imprecise Forecastscited by 6
  5. 2026Learning Credal Ensembles via Distributionally Robust Optimizationcited by 6
  6. 2025Generalization Bounds and Stopping Rules for Learning with Self-Selected Datacited by 5
  7. 2025When Shift Happens - Confounding Is to Blamecited by 5
  8. 2026Quantifying Epistemic Predictive Uncertainty in Conformal Predictioncited by 4
  9. 2025Learning where to learn: Training data distribution optimization for scientific machine learningcited by 1
  10. 2025Epistemic Errors of Imperfect Multitask Learners When Distributions Shiftcited by 1
  11. 2025When Do Credal Sets Stabilize? Fixed-Point Theorems for Credal Set Updatescited by 1
  12. 2026Incentive Aware AI Regulations: A Credal Characterisationcited by 0
2 more
  1. 2026Upper Entropy for 2-Monotone Lower Probabilitiescited by 0
  2. 2026Unification and Optimization of Robust Supervised Learningcited by 0