Metraipolis › archive › dc_dfdafb874040

Transfer Learning for Evolving Domains — arXiv:2609.13039

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.13039
License (as archived): CC0-1.0
Archived: 2026-10-16T03:15:54.852Z
SHA-256 of the archived text: 93a34ec53880068b89fb2a9b19505465c9ffcad6b7f399afd97fd4efe7e9725c
Stable URL of this page: https://metraipolis.com/documento/dc_dfdafb874040

How to cite

Transfer Learning for Evolving Domains — arXiv:2609.13039 — arXiv (en), https://arxiv.org/abs/2609.13039 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dfdafb874040 (Metraipolis archive dc_dfdafb874040, sha256 93a34ec53880068b89fb2a9b19505465c9ffcad6b7f399afd97fd4efe7e9725c)

BibTeX

@misc{dcdfdafb874040,
  title = {Transfer Learning for Evolving Domains — arXiv:2609.13039},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13039},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dfdafb874040; sha256 93a34ec53880068b89fb2a9b19505465c9ffcad6b7f399afd97fd4efe7e9725c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13039. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Transfer learning explores how to leverage knowledge from various tasks or domains (sources) to enhance predictive performance in related tasks or domains (targets). Typically, transfer learning research is segmented into several isolated sub-areas (such as domain generalisation, domain adaptation, or multi-domain learning), each making distinct assumptions about target data availability, namely how much data and how many labels are available at training time. However, in many real-world applications, data availability is not fixed but evolves over time, as instances and labels are progressively collected from a new domain. Each of the classical settings then describes only a snapshot of a trajectory that a deployed system must traverse in full. We formalise this trajectory as a transfer learning problem in its own right, Transfer Learning for Evolving Domains (TrED), specified by a data availability process fixed by the environment, a learning protocol that the method is free to choose, and an evaluation criterion that scores the whole trajectory of models rather than a single one. Within this formalism, the classical settings are recovered as regimes that a learner may pass through, rather than as separate problems that TrED concatenates. We then examine the transfer learning literature to identify mechanisms that are promising building blocks for a solution, and find that most methods are tailored to a single regime and that even the strongest existing candidates do not yet optimise the whole trajectory. We argue that TrED is a well-posed and unsolved problem, and an important direction for future research.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.13039 — 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 2026-10-16T03:05:44.080Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).