EUVIMEDEUVIMED entdecken
Crossref

Domain Adaptation With Additional Features via Label-Aware and Graph-Based Fused Gromov-Wasserstein Optimal Transport

Toshimitsu Aritake, Hideitsu Hino

Neural Computation · 02.06.2026 · 38 (7) · 1203-1232

DOI: 10.1162/neco.a.1525 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neural Computation, online erschienen am 02.06.2026. Verfasst von Toshimitsu Aritake und 1 weiteren Autor:innen. Beteiligte Einrichtung: Hitotsubashi University, Kunitachi, Tokyo 186-0004, Japan toshimitsu.aritake@r.hit-u.ac.jp. Die Arbeit nennt 38 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In many domain adaptation tasks, the source and target domains share an identical feature space, so the domain gap arises only from the distributional shift. In practice; however, new-target-only features (e.g., sensors added after training) often become available at test time, violating the shared feature space assumption and invalidating most existing methods. We address this setting with Label-Aware and Graph-Based Fused Gromov-Wasserstein Optimal Transport (LAGB-FGW), focusing on a transductive domain adaptation scenario, in which the entire unlabeled target data set is available during training, and predictions are jointly inferred for all target samples. LAGB-FGW (1) embeds label discrepancy directly into the source metric, (2) constructs a K-NN graph on the full target feature space to capture structure introduced by the additional features, and (3) jointly solves standard Optimal Transport (OT) and Gromov-Wasserstein OT, thereby transferring labels using both the common and the additional features. We validate LAGB-FGW on four synthetic benchmarks and the HAR70+ human-activity data set, and LAGB-FGW consistently outperforms all baselines, highlighting the advantage of combining source label information with graph-based structural cues when additional target features are available only at test time.

Autor:innen und Institutionen

  • Hitotsubashi University, Kunitachi, Tokyo 186-0004, Japan toshimitsu.aritake@r.hit-u.ac.jp.
  • Institute of Statistical Mathematics, Tachikawa, Tokyo 190-8562, Japan.
  • Graduate University for Advanced Studies (SOKENDAI), Shonan Village, Hayama, Kanagawa 240-0193, Japan hino@ism.ac.jp.

Zitieren

APA

Aritake, T., & Hino, H. (2026). Domain Adaptation With Additional Features via Label-Aware and Graph-Based Fused Gromov-Wasserstein Optimal Transport. Neural Computation, 38(7), 1203-1232. https://doi.org/10.1162/neco.a.1525

Vancouver

Aritake T, Hino H. Domain Adaptation With Additional Features via Label-Aware and Graph-Based Fused Gromov-Wasserstein Optimal Transport. Neural Computation. 2026;38(7):1203-1232. doi:10.1162/neco.a.1525

BibTeX
@article{Aritake2026,
  author = {Aritake, Toshimitsu and Hino, Hideitsu},
  title = {Domain Adaptation With Additional Features via Label-Aware and Graph-Based Fused Gromov-Wasserstein Optimal Transport},
  journal = {Neural Computation},
  year = {2026},
  volume = {38},
  number = {7},
  pages = {1203--1232},
  doi = {10.1162/neco.a.1525}
}
Kostenlos starten →