Early Stopping Tabular In-Context Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Küken, Jaris, Purucker, Lennart, Hutter, Frank
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909664348733440
author Küken, Jaris
Purucker, Lennart
Hutter, Frank
author_facet Küken, Jaris
Purucker, Lennart
Hutter, Frank
contents Tabular foundation models have shown strong performance across various tabular learning tasks via in-context learning, offering robust generalization without any downstream finetuning. However, their inference-time costs remain high, particularly for larger datasets. To address this, we propose early-stopping the in-context learning process. We achieve this by dynamically evaluating whether to stop in-context learning after each Transformer encoder layer. Once stopped, we decode the embedding using a pre-trained layer-wise decoder. Experiments across 34 small classification tasks size show that early stopping in-context learning accelerates inference by up to x1.3 with negligible degradation in predictive performance. To assess scalability, we further evaluate our method on five larger classification tasks, achieving speedups of up to x2.2. Our results demonstrate the potential of early exiting as an effective and practical strategy for improving the efficiency of tabular in-context learning.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21387
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Early Stopping Tabular In-Context Learning
Küken, Jaris
Purucker, Lennart
Hutter, Frank
Machine Learning
Tabular foundation models have shown strong performance across various tabular learning tasks via in-context learning, offering robust generalization without any downstream finetuning. However, their inference-time costs remain high, particularly for larger datasets. To address this, we propose early-stopping the in-context learning process. We achieve this by dynamically evaluating whether to stop in-context learning after each Transformer encoder layer. Once stopped, we decode the embedding using a pre-trained layer-wise decoder. Experiments across 34 small classification tasks size show that early stopping in-context learning accelerates inference by up to x1.3 with negligible degradation in predictive performance. To assess scalability, we further evaluate our method on five larger classification tasks, achieving speedups of up to x2.2. Our results demonstrate the potential of early exiting as an effective and practical strategy for improving the efficiency of tabular in-context learning.
title Early Stopping Tabular In-Context Learning
topic Machine Learning
url https://arxiv.org/abs/2506.21387