Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Lee, Seunghan
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Soft Contrastive Learning for Time Series
par: Lee, Seunghan, et autres
Publié: (2023)

Learning to Embed Time Series Patches Independently
par: Lee, Seunghan, et autres
Publié: (2023)

AdapTable: Test-Time Adaptation for Tabular Data via Shift-Aware Uncertainty Calibrator and Label Distribution Handler
par: Kim, Changhun, et autres
Publié: (2024)

Channel Normalization for Time Series Channel Identification
par: Lee, Seunghan, et autres
Publié: (2025)

Dataset-Driven Channel Masks in Transformers for Multivariate Time Series
par: Lee, Seunghan, et autres
Publié: (2024)

ANT: Adaptive Noise Schedule for Time Series Diffusion Models
par: Lee, Seunghan, et autres
Publié: (2024)

Sequential Order-Robust Mamba for Time Series Forecasting
par: Lee, Seunghan, et autres
Publié: (2024)

When Normality Shifts: Risk-Aware Test-Time Adaptation for Unsupervised Tabular Anomaly Detection
par: Huang, Wei, et autres
Publié: (2026)

Improving LLM Group Fairness on Tabular Data via In-Context Learning
par: Cherepanova, Valeriia, et autres
Publié: (2024)

Addressing Label Shift in Distributed Learning via Entropy Regularization
par: Wu, Zhiyuan, et autres
Publié: (2025)

Posterior Label Smoothing for Node Classification
par: Heo, Jaeseung, et autres
Publié: (2024)

Towards Understanding Layer Contributions in Tabular In-Context Learning Models
par: Balef, Amir Rezaei, et autres
Publié: (2025)

Orion-Bix: Bi-Axial Attention for Tabular In-Context Learning
par: Bouadi, Mohamed, et autres
Publié: (2025)

LLM Embeddings Improve Test-time Adaptation to Tabular $Y|X$-Shifts
par: Zeng, Yibo, et autres
Publié: (2024)

Mitigating Domain Shift in Federated Learning via Intra- and Inter-Domain Prototypes
par: Le, Huy Q., et autres
Publié: (2025)

CATS: Mitigating Correlation Shift for Multivariate Time Series Classification
par: Lin, Xiao, et autres
Publié: (2025)

FinTexTS: Financial Text-Paired Time-Series Dataset via Semantic-Based and Multi-Level Pairing
par: Lee, Jaehoon, et autres
Publié: (2026)

Amortized In-Context Bayesian Posterior Estimation
par: Mittal, Sarthak, et autres
Publié: (2025)

Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning
par: Bouadi, Mohamed, et autres
Publié: (2025)

Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation
par: Jang, Minguk, et autres
Publié: (2024)

CANDI: Curated Test-Time Adaptation for Multivariate Time-Series Anomaly Detection Under Distribution Shift
par: Kim, HyunGi, et autres
Publié: (2026)

TabularMath: Evaluating Computational Extrapolation in Tabular Learning via Program-Verified Synthesis
par: Cheng, Zerui, et autres
Publié: (2026)

TabICL: A Tabular Foundation Model for In-Context Learning on Large Data
par: Qu, Jingang, et autres
Publié: (2025)

ReTabAD: A Benchmark for Restoring Semantic Context in Tabular Anomaly Detection
par: Yoon, Sanghyu, et autres
Publié: (2025)

Probabilistic Test-Time Generalization by Variational Neighbor-Labeling
par: Ambekar, Sameer, et autres
Publié: (2023)

Rethinking Distribution Shifts: Empirical Analysis and Inductive Modeling for Tabular Data
par: Wang, Tianyu, et autres
Publié: (2023)

FinSTaR: Towards Financial Reasoning with Time Series Reasoning Models
par: Lee, Seunghan, et autres
Publié: (2026)

Measuring and Mitigating Bias for Tabular Datasets with Multiple Protected Attributes
par: Duong, Manh Khoi, et autres
Publié: (2024)

Fully Test-time Adaptation for Tabular Data
par: Zhou, Zhi, et autres
Publié: (2024)

Rethinking Multimodal Fusion for Time Series: Auxiliary Modalities Need Constrained Fusion
par: Lee, Seunghan, et autres
Publié: (2026)

FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning
par: Ji, Xinyuan, et autres
Publié: (2024)

Training on Fake Labels: Mitigating Label Leakage in Split Learning via Secure Dimension Transformation
par: Jiang, Yukun, et autres
Publié: (2024)

Noise Immunity in In-Context Tabular Learning: An Empirical Robustness Analysis of TabPFN's Attention Mechanisms
par: Hu, James, et autres
Publié: (2026)

Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift
par: Chen, Mouxiang, et autres
Publié: (2023)

LUCoS: Latent Unsupervised Context Selection for Tabular Foundation Models
par: Ipas, Oroel, et autres
Publié: (2026)

Detecting and Mitigating the Correct-Answer Extinction Window in Test-Time Reinforcement Learning with Majority Voting
par: Lin, Hongxiang, et autres
Publié: (2026)

Class-based Subset Selection for Transfer Learning under Extreme Label Shift
par: Goyal, Akul, et autres
Publié: (2024)

Less is More: Pseudo-Label Filtering for Continual Test-Time Adaptation
par: Tan, Jiayao, et autres
Publié: (2024)

AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation
par: Lee, Taeckyung, et autres
Publié: (2024)

Hybrid Autoencoders for Tabular Data: Leveraging Model-Based Augmentation in Low-Label Settings
par: Naor, Erel, et autres
Publié: (2025)