paper-with-me

홈 › Papers

Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment

2026-05-06 · Seunghan Lee arxiv

TabPFN has recently gained attention as a foundation model for tabular datasets, achieving strong performance by leveraging in-context learning on synthetic data. However, we find that TabPFN is vulnerable to label shift, often overfitting to the majority class in the training dataset. To address this limitation, we propose DistPFN, the first test-time posterior adjustment method designed for tabular foundation models. DistPFN rescales predicted class probabilities by downweighting the influence of the training prior (i.e., the class distribution of the context) and emphasizing the contribution of the model's predicted posterior, without architectural modification or additional training. We further introduce DistPFN-T, which incorporates temperature scaling to adaptively control the adjustment strength based on the discrepancy between prior and posterior. We evaluate our methods on over 250 OpenML datasets, demonstrating substantial improvements for various TabPFN-based models in classification tasks under label shift, while maintaining strong performance in standard settings without label shift. Code is available at this repository: https://github.com/seunghan96/DistPFN.

📄 PDF Abstract BibTeX arXiv:2605.04363

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

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

2024-07-15 · Changhun Kim, Taewon Kim, Seungyeon Woo, June Yong Yang 외

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 dom…

Representation LearningTest-time Adaptation

Fully Test-time Adaptation for Tabular Data

2024-12-14 · Zhi Zhou, Kun-Yang Yu, Lan-Zhe Guo, Yu-Feng Li

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,…

Data AugmentationTest-time Adaptation

LLM Embeddings Improve Test-time Adaptation to Tabular $Y|X$-Shifts

2024-10-09 · Yibo Zeng, Jiashuo Liu, Henry Lam, Hongseok Namkoong

For tabular datasets, the change in the relationship between the label and covariates ($Y|X$-shifts) is common due to missing variables (a.k.a. confounders). Since it is impossible to generalize to a completely new and u…

Test-time AdaptationWorld Knowledge

TabFSBench: Tabular Benchmark for Feature Shifts in Open Environment

2025-01-31 · Zi-Jian Cheng, Zi-Yi Jia, Zhi Zhou, Lan-Zhe Guo 외

Tabular data is widely utilized in various machine learning tasks. Current tabular learning research predominantly focuses on closed environments, while in real-world applications, open environments are often encountered…

Logit-Origin Centering for Singleton Test-Time Adaptation

2026-08-02 · Mayank Sharma, Rohit Kumar Mourya, Pratik Mazumder arxiv

Tabular data is used extensively in many real-world use cases. Deep learning models have been developed to deal with tabular data, but generally perform poorly when the test data distribution differs from that of the tra…

Test-time Adaptation