mlsanityData to 7 Oct 2026

AdapTable: Test-Time Adaptation for Tabular Data via Shift-Aware Uncertainty Calibrator and Label Distribution Handler

arXiv 2407.10784 ↗First posted 15 Jul 2024cs.LG cs.AI stat.MLcited by 6

Not on the map. Why?

Abstract (arXiv)

In real-world scenarios, tabular data often suffer from distribution shifts that threaten the performance of machine learning models. Despite its prevalence and importance, handling distribution shifts in the tabular domain remains underexplored due to the inherent challenges within the tabular data itself. In this sense, test-time adaptation (TTA) offers a promising solution by adapting models to target data without accessing source data, crucial for privacy-sensitive tabular domains. However, existing TTA methods either 1) overlook the nature of tabular distribution shifts, often involving label distribution shifts, or 2) impose architectural constraints on the model, leading to a lack of applicability. To this end, we propose AdapTable, a novel TTA framework for tabular data. AdapTable operates in two stages: 1) calibrating model predictions using a shift-aware uncertainty calibrator, and 2) adjusting these predictions to match the target label distribution with a label distribution handler. We validate the effectiveness of AdapTable through theoretical analysis and extensive experiments on various distribution shift scenarios. Our results demonstrate AdapTable's ability to handle various real-world distribution shifts, achieving up to a 16% improvement on the HELOC dataset.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 49 of its 83 references that are in the map. First posted on arXiv 15 Jul 2024.

Builds on

49 of 83 references.

References · 49

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  7. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  8. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,404
  9. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  10. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 643
  11. 2019TabNet: Attentive Interpretable Tabular Learningcited by 640
  12. 2020Long-tail learning via logit adjustmentcited by 605
37 more
  1. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 467
  2. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 427
  3. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 409
  4. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 364
  5. 2019Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibrationcited by 359
  6. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  7. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  8. 2018AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networkscited by 319
  9. 2018CatBoost: gradient boosting with categorical features supportcited by 208
  10. 2022Test-Time Training with Masked Autoencoderscited by 208
  11. 2022Why do tree-based models still outperform deep learning on tabular data?cited by 198
  12. 2022Parameter-free Online Test-time Adaptationcited by 184
  13. 2017OpenML Benchmarking Suitescited by 169
  14. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  15. 2022NOTE: Robust Continual Test-time Adaptation Against Temporal Correlationcited by 150
  16. 2022LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Taskscited by 146
  17. 2020Domain Adaptation with Conditional Distribution Matching and Generalized Label Shiftcited by 124
  18. 2020Logical Neural Networkscited by 118
  19. 2022WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domaincited by 117
  20. 2023TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptationcited by 101
  21. 2021Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Taskscited by 100
  22. 2021Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibrationcited by 91
  23. 2022Back to the Source: Diffusion-Driven Test-Time Adaptationcited by 71
  24. 2023Benchmarking Distribution Shift in Tabular Data with TableShiftcited by 64
  25. 2023Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspectivecited by 54
  26. 2021Online Adaptation to Label Distribution Shiftcited by 44
  27. 2022What Makes Graph Neural Networks Miscalibrated?cited by 39
  28. 2020Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Trainingcited by 38
  29. 2024MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoningcited by 35
  30. 2017A Benchmark Environment Motivated by Industrial Control Problemscited by 31
  31. 2022MATE: Masked Autoencoders are Online 3D Test-Time Learnerscited by 23
  32. 2023Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shiftscited by 21
  33. 2019Unsupervised Domain Adaptation for Neural Machine Translation with Domain-Aware Feature Embeddingscited by 14
  34. 2018HELOC Applicant Risk Performance Evaluation by Topological Hierarchical Decompositioncited by 5
  35. 2022Unsupervised domain adaptation for speech recognition with unsupervised error correctioncited by 5
  36. 2023PC-Adapter: Topology-Aware Adapter for Efficient Domain Adaption on Point Clouds with Rectified Pseudo-labelcited by 5
  37. 2021Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learningcited by 3

Built on by

Cited by year (2026 to 7 Oct)

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

6 papers.

  1. 2025Representation Learning for Tabular Data: A Comprehensive Surveycited by 36
  2. 2024Fully Test-time Adaptation for Tabular Datacited by 8
  3. 2025Understanding the Limits of Deep Tabular Methods with Temporal Shiftcited by 4
  4. 2026Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustmentcited by 3
  5. 2025Feature-aware Modulation for Learning from Temporal Tabular Datacited by 0
  6. 2026Transfer Learning for Loan Recovery Prediction under Distribution Shifts with Heterogeneous Feature Spacescited by 0