Metraipolis › archive › dc_b74f2a65dd2f

Learning Through Game: Skewed Transfer of Tabular Knowledge to Strengthen Image Model — arXiv:2609.32272

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32272
License (as archived)
CC0-1.0
Archived
2026-10-07T22:36:24.757Z
SHA-256 of the archived text
c027e2cabe0914cadedbbeb4a30539ac2138c7581635ad4bab5442756adcd350
Stable URL of this page
https://metraipolis.com/documento/dc_b74f2a65dd2f

How to cite

Learning Through Game: Skewed Transfer of Tabular Knowledge to Strengthen Image Model — arXiv:2609.32272 — arXiv (en), https://arxiv.org/abs/2609.32272 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b74f2a65dd2f (Metraipolis archive dc_b74f2a65dd2f, sha256 c027e2cabe0914cadedbbeb4a30539ac2138c7581635ad4bab5442756adcd350)
BibTeX
@misc{dcb74f2a65dd2f,
  title = {Learning Through Game: Skewed Transfer of Tabular Knowledge to Strengthen Image Model — arXiv:2609.32272},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32272},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b74f2a65dd2f; sha256 c027e2cabe0914cadedbbeb4a30539ac2138c7581635ad4bab5442756adcd350},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32272. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal tabular-image learning is gaining growing attention, yet it faces challenges due to tabular data unavailable at test time. A practical solution involves transferring tabular knowledge to images during training to enhance the performance of image models at inference. However, the overlooked yet important challenges lie in the modality imbalance between images and tables, as well as their asymmetric modality relationship in cross-modal transfer, which limits the auxiliary role of tabular data. To address these issues, we propose Skewed Knowledge Transfer (SKT), which asymmetrically transfers tabular knowledge to improve the image model by adaptive integration of modality gradients in a shared parameter space. Specifically, we first introduce a multimodal shared head, which allows the model to benefit from cross-modal structure without adding additional parameters. We then design a two-step Nash Bargaining strategy to effectively leverage tabular gradients. In the first step, SKT seeks a point of modality balance and uses preference awareness in the second step to steer combined gradients toward image-beneficial directions. Furthermore, we theoretically analyze the Pareto improvement and convergence of SKT. To this end, tabular knowledge is explicitly transferred to enhance image models. Empirical experiments on widely used tabular-image datasets reveal that SKT consistently improves image unimodal performance by using tabular data as auxiliary information.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2609.32272 — 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 2026-10-07T22:14:27.634Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).