Saved in:
Bibliographic Details
Main Authors: Wang, Lina, Yuan, Yunsheng, Wang, Chunxiao, Li, Feng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.23726
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916687215853568
author Wang, Lina
Yuan, Yunsheng
Wang, Chunxiao
Li, Feng
author_facet Wang, Lina
Yuan, Yunsheng
Wang, Chunxiao
Li, Feng
contents In the paradigm of decentralized learning, a group of agents collaborates to learn a global model using distributed datasets without a central server. However, due to the heterogeneity of the local data across the different agents, learning a robust global model is rather challenging. Moreover, the collaboration of the agents relies on their gradient information exchange, which poses a risk of privacy leakage. In this paper, to address these issues, we propose PDSL, a novel privacy-preserved decentralized stochastic learning algorithm with heterogeneous data distribution. On one hand, we innovate in utilizing the notion of Shapley values such that each agent can precisely measure the contributions of its heterogeneous neighbors to the global learning goal; on the other hand, we leverage the notion of differential privacy to prevent each agent from suffering privacy leakage when it contributes gradient information to its neighbors. We conduct both solid theoretical analysis and extensive experiments to demonstrate the efficacy of our PDSL algorithm in terms of privacy preservation and convergence.
format Preprint
id arxiv_https___arxiv_org_abs_2503_23726
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PDSL: Privacy-Preserved Decentralized Stochastic Learning with Heterogeneous Data Distribution
Wang, Lina
Yuan, Yunsheng
Wang, Chunxiao
Li, Feng
Machine Learning
In the paradigm of decentralized learning, a group of agents collaborates to learn a global model using distributed datasets without a central server. However, due to the heterogeneity of the local data across the different agents, learning a robust global model is rather challenging. Moreover, the collaboration of the agents relies on their gradient information exchange, which poses a risk of privacy leakage. In this paper, to address these issues, we propose PDSL, a novel privacy-preserved decentralized stochastic learning algorithm with heterogeneous data distribution. On one hand, we innovate in utilizing the notion of Shapley values such that each agent can precisely measure the contributions of its heterogeneous neighbors to the global learning goal; on the other hand, we leverage the notion of differential privacy to prevent each agent from suffering privacy leakage when it contributes gradient information to its neighbors. We conduct both solid theoretical analysis and extensive experiments to demonstrate the efficacy of our PDSL algorithm in terms of privacy preservation and convergence.
title PDSL: Privacy-Preserved Decentralized Stochastic Learning with Heterogeneous Data Distribution
topic Machine Learning
url https://arxiv.org/abs/2503.23726