الملخص
Tabular foundation models (TFMs) outperform established machine learning models on tabular benchmarks through in-context learning. Building on this success, interest is growing in applying them to data streams, where data arrive continuously and evolve over time. On a stream, a TFM adapts by updating its context rather than its parameters, so its accuracy and cost depend on which examples it keeps and how often it rebuilds its context. We therefore present a systematic study of TFMs on data streams, covering memory management, computational cost, and stream-specific challenges such as concept drift and delayed labels. We find that TFMs achieve the highest predictive performance and that simply retaining the most recent examples is as effective as existing memory management techniques. They also recover faster than streaming learners after drift and keep the highest accuracy under label delay. This accuracy, however, comes at a high serving cost, since a nearly unchanged context is re-encoded at every prediction. These results point to architectural efficiency as the way forward for in-context stream learning.
الكلمات المفتاحية
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Verma, N., Nowak-Assis, D., Lourenço, A., Bifet, A., Pfahringer, B., Bahri, M., & Lim, N. J. S. (2026). Rethinking Tabular Foundation Models On Data Streams. https://omanscience.com/ar/articles/rethinking-tabular-foundation-models-on-data-streams
MLA 9
Verma, Nilesh, et al. "Rethinking Tabular Foundation Models On Data Streams." https://omanscience.com/ar/articles/rethinking-tabular-foundation-models-on-data-streams.
شيكاغو (المؤلف–التاريخ)
Verma, Nilesh, Daniel Nowak-Assis, Afonso Lourenço, Albert Bifet, Bernhard Pfahringer, Maroua Bahri, and Nick Jin Sean Lim. 2026. "Rethinking Tabular Foundation Models On Data Streams." https://omanscience.com/ar/articles/rethinking-tabular-foundation-models-on-data-streams.
هارفارد
Verma, N., Nowak-Assis, D., Lourenço, A., Bifet, A., Pfahringer, B., Bahri, M. and Lim, N. J. S. (2026) 'Rethinking Tabular Foundation Models On Data Streams', Available at: https://omanscience.com/ar/articles/rethinking-tabular-foundation-models-on-data-streams.
فانكوفر
Verma N, Nowak-Assis D, Lourenço A, Bifet A, Pfahringer B, Bahri M, et al. Rethinking Tabular Foundation Models On Data Streams. https://omanscience.com/ar/articles/rethinking-tabular-foundation-models-on-data-streams
IEEE
N. Verma, D. Nowak-Assis, A. Lourenço, A. Bifet, B. Pfahringer, M. Bahri, and N. J. S. Lim, "Rethinking Tabular Foundation Models On Data Streams," https://omanscience.com/ar/articles/rethinking-tabular-foundation-models-on-data-streams.