EUVIMEDEUVIMED entdecken
Studienprotokoll

Generalized Distribution Aggregation Protocol for Federated Statistical Heterogeneity

Mingwei Xu, Xiaofeng Cao, Ivor W Tsang, James T Kwok, Heng Tao Shen

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-07 · 48 (7) · 7820-7834

DOI: 10.1109/tpami.2026.3663744 ↗

Kurz gefasst

Studienprotokoll in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-07. Verfasst von Mingwei Xu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jilin Province and Jilin Province Budgetary Capital Construction Fund Plan, Research Grants Council of the Hong Kong Special Administrative Region.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated heterogeneity refers to the disparities in data distributions, model architectures, and communication capabilities across various devices or institutional entities. In real-world scenarios, statistical heterogeneity can often lead to ineffective aggregation, severely impacting generalization performance and resulting in biased or unstable model weights. Theoretically, distributional robustness analysis indicates that the generalization performance of a learning model can be bounded with respect to any heterogeneity distribution. This insight motivates us to reconsider the aggregation strategy in federated statistical heterogeneity scenarios, and we thus propose a new weighting aggregation protocol that considers the generalization bound disagreement of each local model. Specifically, we estimate the upper and lower bounds of the second-order origin moment of the shifted distribution for the current local model, and using these bound disagreements as the aggregation proportions for weights in each communication round. Our experiments demonstrate that this proposed aggregation protocol significantly improves the performance of several representative Federated Learning algorithms on benchmark datasets.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Jilin Province and Jilin Province Budgetary Capital Construction Fund Plan
  • Research Grants Council of the Hong Kong Special Administrative Region
  • New Cornerstone Science Foundation

Zitieren

APA

Xu, M., Cao, X., Tsang, I. W., Kwok, J. T., & Shen, H. T. (2026). Generalized Distribution Aggregation Protocol for Federated Statistical Heterogeneity. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(7), 7820-7834. https://doi.org/10.1109/tpami.2026.3663744

Vancouver

Xu M, Cao X, Tsang IW, Kwok JT, Shen HT. Generalized Distribution Aggregation Protocol for Federated Statistical Heterogeneity. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(7):7820-7834. doi:10.1109/tpami.2026.3663744

BibTeX
@article{Xu2026,
  author = {Xu, Mingwei and Cao, Xiaofeng and Tsang, Ivor W and Kwok, James T and Shen, Heng Tao},
  title = {Generalized Distribution Aggregation Protocol for Federated Statistical Heterogeneity},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {7},
  pages = {7820--7834},
  doi = {10.1109/tpami.2026.3663744}
}
Kostenlos starten →