Saved in:
Bibliographic Details
Main Authors: Zhu, Zehan, Zhao, Heng, Huang, Yan, Zhou, Joey Tianyi, Ji, Shouling, Xu, Jinming
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.13583
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914201967001600
author Zhu, Zehan
Zhao, Heng
Huang, Yan
Zhou, Joey Tianyi
Ji, Shouling
Xu, Jinming
author_facet Zhu, Zehan
Zhao, Heng
Huang, Yan
Zhou, Joey Tianyi
Ji, Shouling
Xu, Jinming
contents In this paper, we propose a Differentially Private Stochastic Gradient Push with Compressed communication (termed DP-CSGP) for decentralized learning over directed graphs. Different from existing works, the proposed algorithm is designed to maintain high model utility while ensuring both rigorous differential privacy (DP) guarantees and efficient communication. For general non-convex and smooth objective functions, we show that the proposed algorithm achieves a tight utility bound of $\mathcal{O}\left( \sqrt{d\log \left( \frac{1}δ \right)}/(\sqrt{n}Jε) \right)$ ($J$ and $d$ are the number of local samples and the dimension of decision variables, respectively) with $\left(ε, δ\right)$-DP guarantee for each node, matching that of decentralized counterparts with exact communication. Extensive experiments on benchmark tasks show that, under the same privacy budget, DP-CSGP achieves comparable model accuracy with significantly lower communication cost than existing decentralized counterparts with exact communication.
format Preprint
id arxiv_https___arxiv_org_abs_2512_13583
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DP-CSGP: Differentially Private Stochastic Gradient Push with Compressed Communication
Zhu, Zehan
Zhao, Heng
Huang, Yan
Zhou, Joey Tianyi
Ji, Shouling
Xu, Jinming
Machine Learning
Artificial Intelligence
In this paper, we propose a Differentially Private Stochastic Gradient Push with Compressed communication (termed DP-CSGP) for decentralized learning over directed graphs. Different from existing works, the proposed algorithm is designed to maintain high model utility while ensuring both rigorous differential privacy (DP) guarantees and efficient communication. For general non-convex and smooth objective functions, we show that the proposed algorithm achieves a tight utility bound of $\mathcal{O}\left( \sqrt{d\log \left( \frac{1}δ \right)}/(\sqrt{n}Jε) \right)$ ($J$ and $d$ are the number of local samples and the dimension of decision variables, respectively) with $\left(ε, δ\right)$-DP guarantee for each node, matching that of decentralized counterparts with exact communication. Extensive experiments on benchmark tasks show that, under the same privacy budget, DP-CSGP achieves comparable model accuracy with significantly lower communication cost than existing decentralized counterparts with exact communication.
title DP-CSGP: Differentially Private Stochastic Gradient Push with Compressed Communication
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2512.13583