EUVIMEDEUVIMED entdecken
Crossref

Communication-Efficient Federated Learning by Exploiting Spatio-Temporal Correlations of Gradients

Shenlong Zheng, Zhen Zhang, Yuhui Deng, Geyong Min, Lin Cui

IEEE Transactions on Computers · 2026-04 · 75 (4) · 1433-1445

DOI: 10.1109/tc.2026.3654074 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Computers, 2026-04. Verfasst von Shenlong Zheng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 42 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Communication overhead is a critical challenge in federated learning, particularly in bandwidth-constrained networks. Although many methods have been proposed to reduce communication overhead, most focus solely on compressing individual gradients, overlooking the temporal correlations among them. Prior studies have shown that gradients exhibit spatial correlations, typically reflected in low-rank structures. Through empirical analysis, we further observe a strong temporal correlation between client gradients across adjacent rounds. Based on these observations, we propose GradESTC, a compression technique that exploits both spatial and temporal gradient correlations. GradESTC exploits spatial correlations to decompose each full gradient into a compact set of basis vectors and corresponding combination coefficients. By exploiting temporal correlations, only a small portion of the basis vectors need to be dynamically updated in each round. GradESTC significantly reduces communication overhead by transmitting lightweight combination coefficients and a limited number of updated basis vectors instead of the full gradients. Extensive experiments show that, upon reaching a target accuracy level near convergence, GradESTC reduces uplink communication by an average of 39.79% compared to the strongest baseline, while maintaining comparable convergence speed and final accuracy to uncompressed FedAvg. By effectively leveraging spatio-temporal gradient structures, GradESTC offers a practical and scalable solution for communication-efficient federated learning.

Zitieren

APA

Zheng, S., Zhang, Z., Deng, Y., Min, G., & Cui, L. (2026). Communication-Efficient Federated Learning by Exploiting Spatio-Temporal Correlations of Gradients. IEEE Transactions on Computers, 75(4), 1433-1445. https://doi.org/10.1109/tc.2026.3654074

Vancouver

Zheng S, Zhang Z, Deng Y, Min G, Cui L. Communication-Efficient Federated Learning by Exploiting Spatio-Temporal Correlations of Gradients. IEEE Transactions on Computers. 2026;75(4):1433-1445. doi:10.1109/tc.2026.3654074

BibTeX
@article{Zheng2026,
  author = {Zheng, Shenlong and Zhang, Zhen and Deng, Yuhui and Min, Geyong and Cui, Lin},
  title = {Communication-Efficient Federated Learning by Exploiting Spatio-Temporal Correlations of Gradients},
  journal = {IEEE Transactions on Computers},
  year = {2026},
  volume = {75},
  number = {4},
  pages = {1433--1445},
  doi = {10.1109/tc.2026.3654074}
}
Kostenlos starten →