Metraipolis › archive › dc_09b841da3441

ElTab: Elastically Looped Tabular Transformers — arXiv:2610.41819

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41819
License (as archived)
CC0-1.0
Archived
2026-11-02T04:52:28.191Z
SHA-256 of the archived text
c3abecc9f7d03ab32994920161fe2b5517da23619b80fae4ed3f8987c3fb4e60
Stable URL of this page
https://metraipolis.com/documento/dc_09b841da3441

How to cite

ElTab: Elastically Looped Tabular Transformers — arXiv:2610.41819 — arXiv (en), https://arxiv.org/abs/2610.41819 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09b841da3441 (Metraipolis archive dc_09b841da3441, sha256 c3abecc9f7d03ab32994920161fe2b5517da23619b80fae4ed3f8987c3fb4e60)
BibTeX
@misc{dc09b841da3441,
  title = {ElTab: Elastically Looped Tabular Transformers — arXiv:2610.41819},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41819},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09b841da3441; sha256 c3abecc9f7d03ab32994920161fe2b5517da23619b80fae4ed3f8987c3fb4e60},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41819. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tabular transformer models such as TabPFN achieve strong predictive performance but incur substantial inference costs, making them difficult to deploy in resource-constrained settings. While looped transformers reduce parameter count through weight sharing, they can lose significant predictive power when stopped early. To address this challenge, we introduce the Elastically Looped Tabular Transformer (ElTab), a single model trained to operate across different computational budgets through supervision at randomly sampled early exits. Across 30 OpenML classification datasets, a single ElTab model matches six depth-specific looped models while cutting training cost by more than half, and matches a 12-layer TabPFN-style baseline with 25% fewer inference FLOPs. These results show that elastic-depth training yields a single model that adapts to the deployment budget at hand, offering a favorable trade-off among predictive performance, storage, and computational cost.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.41819 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-02T04:45:12.913Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).