EUVIMEDEUVIMED entdecken
Crossref

FedSDWC: Federated Synergistic Dual-Representation Weak Causal Learning for OOD

Zhenyuan Huang, Hui Zhang, Wenzhong Tang, Haijun Yang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (26) · 22092-22100

DOI: 10.1609/aaai.v40i26.39364 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhenyuan Huang und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Amid growing demands for data privacy and advances in computational infrastructure, federated learning (FL) has emerged as a prominent distributed learning paradigm. Nevertheless, differences in data distribution (such as covariate and semantic shifts) severely affect its reliability in real-world deployments. To address this issue, we propose FedSDWC, a causal inference method that integrates both invariant and variant features. FedSDWC infers causal semantic representations by modeling the weak causal influence between invariant and variant features, effectively overcoming the limitations of existing invariant learning methods in accurately capturing invariant features and directly constructing causal representations. This approach significantly enhances FL's ability to generalize and detect OOD data. Theoretically, we derive FedSDWC's generalization error bound under specific conditions and, for the first time, establish its relationship with client prior distributions. Moreover, extensive experiments conducted on multiple benchmark datasets validate the superior performance of FedSDWC in handling covariate and semantic shifts. For example, FedSDWC outperforms FedICON, the next best baseline, by an average of 3.04% on CIFAR-10 and 8.11% on CIFAR-100.

Zitieren

APA

Huang, Z., Zhang, H., Tang, W., & Yang, H. (2026). FedSDWC: Federated Synergistic Dual-Representation Weak Causal Learning for OOD. Proceedings of the AAAI Conference on Artificial Intelligence, 40(26), 22092-22100. https://doi.org/10.1609/aaai.v40i26.39364

Vancouver

Huang Z, Zhang H, Tang W, Yang H. FedSDWC: Federated Synergistic Dual-Representation Weak Causal Learning for OOD. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(26):22092-22100. doi:10.1609/aaai.v40i26.39364

BibTeX
@article{Huang2026,
  author = {Huang, Zhenyuan and Zhang, Hui and Tang, Wenzhong and Yang, Haijun},
  title = {FedSDWC: Federated Synergistic Dual-Representation Weak Causal Learning for OOD},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {26},
  pages = {22092--22100},
  doi = {10.1609/aaai.v40i26.39364}
}
Kostenlos starten →