LGAIMLDec 14, 2024

Fully Test-time Adaptation for Tabular Data

arXiv:2412.10871v111 citationsh-index: 15AAAI
Originality Incremental advance
AI Analysis

This addresses performance degradation in deep tabular models due to data distribution shifts, offering a solution for real-world applications, though it appears incremental as it builds on existing FTTA methods.

The paper tackles the problem of fully test-time adaptation for tabular data to handle distribution shifts, proposing FTAT, which outperforms state-of-the-art methods on six benchmark datasets.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes