Metraipolis › archive › dc_5387f00edeb6

SOMTab: Set-Order Mamba for Efficient Tabular In-Context Learning — arXiv:2608.27882

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27882
License (as archived)
CC0-1.0
Archived
2026-10-17T10:47:58.899Z
SHA-256 of the archived text
6f27da9fb8813c633e99814739f1718babff400b481a7f77a1955bc1b420d474
Stable URL of this page
https://metraipolis.com/documento/dc_5387f00edeb6

How to cite

SOMTab: Set-Order Mamba for Efficient Tabular In-Context Learning — arXiv:2608.27882 — arXiv (en), https://arxiv.org/abs/2608.27882 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5387f00edeb6 (Metraipolis archive dc_5387f00edeb6, sha256 6f27da9fb8813c633e99814739f1718babff400b481a7f77a1955bc1b420d474)
BibTeX
@misc{dc5387f00edeb6,
  title = {SOMTab: Set-Order Mamba for Efficient Tabular In-Context Learning — arXiv:2608.27882},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27882},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5387f00edeb6; sha256 6f27da9fb8813c633e99814739f1718babff400b481a7f77a1955bc1b420d474},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27882. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tabular foundation models based on in-context learning have recently emerged as strong alternatives to task-specific model fitting. However, the current performance frontier remains dominated by attention-heavy architectures, where attention is used throughout the modeling pipeline. This raises a natural question: is attention necessary at every stage of tabular in-context learning? We introduce SOMTab, a Set-Order Mamba architecture for efficient tabular in-context learning. SOMTab separates representation construction from query-conditioned retrieval. For row and column representations, it maps unordered table tokens into stable latent slots and applies Mamba-based state-space mixing to construct compact representations. For final prediction, it retains attention-based in-context learning to preserve query-conditioned retrieval from labeled context examples. We further introduce DCH-TailMix, a synthetic prior that combines degree-corrected graph heterogeneity with mixed heavy-tailed regimes to diversify synthetic dependency structures. Across tabular benchmarks, SOMTab approaches the performance of strong Transformer-based tabular foundation models while achieving faster inference and lower GPU memory usage, yielding a favorable efficiency--accuracy trade-off.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.27882 — 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 2026-10-17T10:33:42.478Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).