Metraipolis › archive › dc_39bbcbb58e45

Black-Box Knowledge Transfer across Distinct Feature Sets — arXiv:2608.12403

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.12403
License (as archived): CC0-1.0
Archived: 2026-10-19T04:27:45.214Z
SHA-256 of the archived text: 32087de9338d1a8367d2c1637bcc84b1328ac3bc1e4b11e3b4e0bd2caef1161a
Stable URL of this page: https://metraipolis.com/documento/dc_39bbcbb58e45

How to cite

Black-Box Knowledge Transfer across Distinct Feature Sets — arXiv:2608.12403 — arXiv (en), https://arxiv.org/abs/2608.12403 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_39bbcbb58e45 (Metraipolis archive dc_39bbcbb58e45, sha256 32087de9338d1a8367d2c1637bcc84b1328ac3bc1e4b11e3b4e0bd2caef1161a)

BibTeX

@misc{dc39bbcbb58e45,
  title = {Black-Box Knowledge Transfer across Distinct Feature Sets — arXiv:2608.12403},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12403},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_39bbcbb58e45; sha256 32087de9338d1a8367d2c1637bcc84b1328ac3bc1e4b11e3b4e0bd2caef1161a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12403. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pre-trained black-box predictive functions encode knowledge distilled from massive datasets and extensive computation. However, when the available input features differ from those the black box expects, direct use is infeasible. We introduce a method for transferring predictive knowledge from the black box to a new, heterogeneous input space. Our approach decomposes the target regression function into a transferable component, which the black box can inform, and a non-transferable component, which captures information unique to the new space. We propose a two-step neural network procedure, estimating the transferable component from abundant unlabeled feature pairs that bridge the two input spaces and the non-transferable component from limited labels. We derive prediction risk bounds that improve on those of a non-transfer alternative when the non-transferable component is small or smooth, and the procedure adapts to either case. Under additional conditions, the worst-case risk of our estimator is of strictly smaller polynomial order than the minimax risk of estimation from the labeled data alone. We extend the framework to multiple black boxes, each on its own input space, and show that aggregation can reduce prediction error relative to the best single black box. Simulated and real data demonstrate the practical value of the method.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2608.12403 — 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 2026-10-19T04:20:35.879Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).