EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Federated Multi-source Domain Adaptation via Contrastive Cross-domain Semantic Alignment with Adversarial Feature Augmentation

Wenjie Mao, Bin Yu, Chen Zhang, Yu Xie

ACM Transactions on Knowledge Discovery from Data · 31.05.2026 · 20 (4) · 1-32

DOI: 10.1145/3805032 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Knowledge Discovery from Data, online erschienen am 19.05.2026. Verfasst von Wenjie Mao und 3 weiteren Autor:innen. Die Arbeit nennt 87 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Research and Development Program of Shaanxi, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Generalized federated learning seeks to develop robust models across distributed source domains that generalize well to the unseen target domain. Mainstream methods make strict assumptions about the availability of target domain data, limiting the flexibility and adaptability of real-world applications. In this work, we tackle a real-world challenge that has never been addressed before: federated multi-source domain adaptation for an unseen target domain. We propose federated cross-domain semantic alignment with adversarial feature augmentation, a method that enhances model generalization across domains. Our method operates in the feature space to capture both diversity and invariance between source and target domains through a two-stage local training strategy. In the adversarial training phase, a domain identifier and feature discriminator constrain the generated features to extract target-relevant information. During the contrastive learning stage, a semantic representation alignment loss (SRA) is incorporated to align class prototype distributions between source and target domains, ensuring uniform classification standards. Federated aggregation consolidates model knowledge across clients, facilitating collaborative evolution and rapid adaptation to the unseen target domain. Extensive experimental results on four prevalent datasets demonstrate that our approach outperforms existing benchmarks across different backbones, showcasing its effectiveness in scenarios with data silos.

Förderung

  • Key Research and Development Program of Shaanxi
  • National Natural Science Foundation of China

Zitieren

APA

Mao, W., Yu, B., Zhang, C., & Xie, Y. (2026). Federated Multi-source Domain Adaptation via Contrastive Cross-domain Semantic Alignment with Adversarial Feature Augmentation. ACM Transactions on Knowledge Discovery from Data, 20(4), 1-32. https://doi.org/10.1145/3805032

Vancouver

Mao W, Yu B, Zhang C, Xie Y. Federated Multi-source Domain Adaptation via Contrastive Cross-domain Semantic Alignment with Adversarial Feature Augmentation. ACM Transactions on Knowledge Discovery from Data. 2026;20(4):1-32. doi:10.1145/3805032

BibTeX
@article{Mao2026,
  author = {Mao, Wenjie and Yu, Bin and Zhang, Chen and Xie, Yu},
  title = {Federated Multi-source Domain Adaptation via Contrastive Cross-domain Semantic Alignment with Adversarial Feature Augmentation},
  journal = {ACM Transactions on Knowledge Discovery from Data},
  year = {2026},
  volume = {20},
  number = {4},
  pages = {1--32},
  doi = {10.1145/3805032}
}
Kostenlos starten →