Fully Test-time Adaptation for Tabular Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Zhi, Yu, Kun-Yang, Guo, Lan-Zhe, Li, Yu-Feng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929630315806720
author Zhou, Zhi
Yu, Kun-Yang
Guo, Lan-Zhe
Li, Yu-Feng
author_facet Zhou, Zhi
Yu, Kun-Yang
Guo, Lan-Zhe
Li, Yu-Feng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10871
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Fully Test-time Adaptation for Tabular Data
Zhou, Zhi
Yu, Kun-Yang
Guo, Lan-Zhe
Li, Yu-Feng
Machine Learning
Artificial Intelligence
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.
title Fully Test-time Adaptation for Tabular Data
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2412.10871