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

Changhun Kim, Taewon Kim, Seungyeon Woo, June Yong Yang, Eunho Yang

Primary Area: transfer learning, meta learning, and lifelong learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: tabular data, distribution shift robustness, test-time adaptation

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: we propose a novel tabular test-time adaptation method for the first time.

Abstract:

In real-world applications, tabular data often suffer from distribution shifts due to their widespread and abundant nature, leading to a significant impact on the performance of machine learning models during testing. However, addressing these shifts in the tabular domain has been relatively underexplored due to unique challenges such as varying attributes and dataset sizes, as well as limitations representation learning capabilities of deep learning models for tabular data. Particularly, with the recent promising paradigm of test-time adaptation (TTA), where we adapt the off-the-shelf model to the unlabeled target domain during the inference phase without accessing the source domain, we observe that directly adopting commonly used TTA methods from other domains often leads to model collapse. We systematically explore challenges in tabular data test-time adaptation, including skewed entropy, complex latent space decision boundaries, confidence calibration issues with both overconfident and under-confident, and model bias towards source label distributions along with class imbalances. Based on these insights, we introduce AdapTable, a novel tabular test-time adaptation method that directly modifies output probabilities by estimating target label distributions and adjusting initial probabilities based on calibrated uncertainty.
Extensive experiments on both real-world distribution shifts and synthetic corruptions demonstrate the adaptation efficacy of the proposed method using unlabeled test data alone.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 7383