# Fully Test-time Adaptation for Tabular Data

arXiv: https://arxiv.org/abs/2412.10871 · HTML: https://mlsanity.com/paper/2412.10871/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 48 references that are in the map.
- First posted on arXiv 14 Dec 2024.

## Builds on (most cited first, 20 of 20)

- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Self-Normalizing Neural Networks](https://mlsanity.com/paper/1706.02515/) (2017)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [TabTransformer: Tabular Data Modeling Using Contextual Embeddings](https://mlsanity.com/paper/2012.06678/) (2020)
- [Rethinking ImageNet Pre-training](https://mlsanity.com/paper/1811.08883/) (2018)
- [Geometric Dataset Distances via Optimal Transport](https://mlsanity.com/paper/2002.02923/) (2020)
- [NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation](https://mlsanity.com/paper/2208.05117/) (2022)
- [Test-Time Adaptation via Conjugate Pseudo-labels](https://mlsanity.com/paper/2207.09640/) (2022)
- [Deep Learning for Financial Applications : A Survey](https://mlsanity.com/paper/2002.05786/) (2020)
- [TabR: Tabular Deep Learning Meets Nearest Neighbors in 2023](https://mlsanity.com/paper/2307.14338/) (2023)
- [Benchmarking Distribution Shift in Tabular Data with TableShift](https://mlsanity.com/paper/2312.07577/) (2023)
- [Gradient Boosting Neural Networks: GrowNet](https://mlsanity.com/paper/2002.07971/) (2020)
- [Online Adaptation to Label Distribution Shift](https://mlsanity.com/paper/2107.04520/) (2021)
- [A Benchmark Environment Motivated by Industrial Control Problems](https://mlsanity.com/paper/1709.09480/) (2017)
- [Adapting to Online Label Shift with Provable Guarantees](https://mlsanity.com/paper/2207.02121/) (2022)
- [Predict the Future from the Past? On the Temporal Data Distribution Shift in Financial Sentiment Classifications](https://mlsanity.com/paper/2310.12620/) (2023)
- [Wild-Tab: A Benchmark For Out-Of-Distribution Generalization In Tabular Regression](https://mlsanity.com/paper/2312.01792/) (2023)
- [AdapTable: Test-Time Adaptation for Tabular Data via Shift-Aware Uncertainty Calibrator and Label Distribution Handler](https://mlsanity.com/paper/2407.10784/) (2024)

## Built on by (most cited first, 8 of 8)

- [Realistic Evaluation of TabPFN v2 in Open Environments](https://mlsanity.com/paper/2505.16226/) (2025)
- [On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective](https://mlsanity.com/paper/2605.28057/) (2026)
- [CGI: Identifying Conditional Generative Models with Example Images](https://mlsanity.com/paper/2501.13991/) (2025)
- [Data Curation Matters: Model Collapse and Spurious Shift Performance Prediction from Training on Uncurated Text Embeddings](https://mlsanity.com/paper/2506.17989/) (2025)
- [Transfer Learning for Loan Recovery Prediction under Distribution Shifts with Heterogeneous Feature Spaces](https://mlsanity.com/paper/2604.02832/) (2026)
- [Logit-Origin Centering for Singleton Test-Time Adaptation](https://mlsanity.com/paper/2608.01074/) (2026)
- [Reliable Neural Collapse Approximation for Open-World Test-Time Adaptation](https://mlsanity.com/paper/2608.19890/) (2026)
- [Transfer Learning for Evolving Domains](https://mlsanity.com/paper/2609.13039/) (2026)

## Abstract (arXiv)

Tabular data plays a vital role in various real-world scenarios and finds extensive applications. Although recent deep tabular models have shown remarkable success, they still struggle to handle data distribution shifts, leading to performance degradation when testing distributions change. To remedy this, a robust tabular model must adapt to generalize to unknown distributions during testing. In this paper, we investigate the problem of fully test-time adaptation (FTTA) for tabular data, where the model is adapted using only the testing data. We identify three key challenges: the existence of label and covariate distribution shifts, the lack of effective data augmentation, and the sensitivity of adaptation, which render existing FTTA methods ineffective for tabular data. To this end, we propose the Fully Test-time Adaptation for Tabular data, namely FTAT, which enables FTTA methods to robustly optimize the label distribution of predictions, adapt to shifted covariate distributions, and suit a variety of tasks and models effectively. We conduct comprehensive experiments on six benchmark datasets, which are evaluated using three metrics. The experimental results demonstrate that FTAT outperforms state-of-the-art methods by a margin.