Metraipolis › archive › dc_9c0686108eff

Importance Scoring of Transformer Attention Heads in Learning Tabular Data — arXiv:2608.27241

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27241
License (as archived)
CC0-1.0
Archived
2026-10-17T16:12:46.981Z
SHA-256 of the archived text
4ab4d217bcb8e9c8de50af60d24ae0f13875a47f933dfc618edb28d94bc89e33
Stable URL of this page
https://metraipolis.com/documento/dc_9c0686108eff

How to cite

Importance Scoring of Transformer Attention Heads in Learning Tabular Data — arXiv:2608.27241 — arXiv (en), https://arxiv.org/abs/2608.27241 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9c0686108eff (Metraipolis archive dc_9c0686108eff, sha256 4ab4d217bcb8e9c8de50af60d24ae0f13875a47f933dfc618edb28d94bc89e33)
BibTeX
@misc{dc9c0686108eff,
  title = {Importance Scoring of Transformer Attention Heads in Learning Tabular Data — arXiv:2608.27241},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27241},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9c0686108eff; sha256 4ab4d217bcb8e9c8de50af60d24ae0f13875a47f933dfc618edb28d94bc89e33},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27241. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Computationally demanding and opaque deep learning models can be better understood and optimized by analyzing how they transform data. While deep transformers have been widely studied in computer vision and natural language processing, their application in tabular data remains relatively underexplored. This paper presents one of the first applications of an importance-scoring metric to interpret multi-head transformer models in learning from tabular data. Experiments conducted on 40 diverse tabular datasets demonstrate robustness to head drops based on the proposed head importance score. In 72.5\% of experimental examples, the model remains most resilient to performance drops when heads with the lowest importance scores are gradually removed. In contrast, removing the most important attention head first results in the greatest reduction in classification performance. A closer look at individual head importance scores across six attention layers reveals that important heads are scattered across layers, with no consistent layer-specific trends. In contrast to the image and language domains, the importance of individual attention heads varies considerably across tabular datasets with different schemas and feature spaces. The proposed importance score can improve efficiency and redundancy within transformer architectures. We make the source code for measuring the importance of individual attention heads publicly available.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.27241 — 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 2026-10-17T15:34:49.959Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).