A Fast Differentially Private Distributed Algorithm Over Unbalanced Directed Networks
IEEE Transactions on Signal and Information Processing over Networks · 2026 · 12 · 771-784
DOI: 10.1109/tsipn.2026.3691978 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Signal and Information Processing over Networks, 2026. Verfasst von Mengxue Ran und 3 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Innovation Support Program for Chongqing Overseas Returnees, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
This paper develops a novel distributed optimization algorithm which combines the differentially private technique with the Barzilai-Borwein method (DPBB) for unbalanced directed networks. The algorithm protects the gradient data of agents by adding Gaussian noise to a gradient tracking process, achieving $(\varepsilon,\delta)$-differential privacy with an explicit expression. Then, it analyses the trade-off between convergence accuracy and privacy level. In order to accelerate convergence rate, it incorporates the Barzilai-Borwein method for dynamically adjusting the step size. DPBB is ultimately able to reach the neighborhood of optimal solution in a linearly convergent manner. Two distributed logistic regression examples demonstrate the algorithms’ effectiveness for fast convergence speed, low optimal mean square error and high model classification accuracy.
Förderung
- National Natural Science Foundation of China
- Innovation Support Program for Chongqing Overseas Returnees
- Fundamental Research Funds for the Central Universities
- Graduate Student Scientific Research and Innovation Project of Southwest University
Zitieren
APA
Ran, M., Wang, Z., Lei, Y., & Li, H. (2026). A Fast Differentially Private Distributed Algorithm Over Unbalanced Directed Networks. IEEE Transactions on Signal and Information Processing over Networks, 12, 771-784. https://doi.org/10.1109/tsipn.2026.3691978
Vancouver
Ran M, Wang Z, Lei Y, Li H. A Fast Differentially Private Distributed Algorithm Over Unbalanced Directed Networks. IEEE Transactions on Signal and Information Processing over Networks. 2026;12:771-784. doi:10.1109/tsipn.2026.3691978
BibTeX
@article{Ran2026,
author = {Ran, Mengxue and Wang, Zheng and Lei, Yan and Li, Hongyi},
title = {A Fast Differentially Private Distributed Algorithm Over Unbalanced Directed Networks},
journal = {IEEE Transactions on Signal and Information Processing over Networks},
year = {2026},
volume = {12},
pages = {771--784},
doi = {10.1109/tsipn.2026.3691978}
}
EUVIMED