Výsledky vyhledávání

Report

Online Auction-Based Incentive Mechanism Design for Horizontal Federated Learning with Budget Constraint

Autor: Zhang, Jingwen, Wu, Yuezhou, Pan, Rong

Federated learning makes it possible for all parties with data isolation to train the model collaboratively and efficiently while satisfying privacy protection. To obtain a high-quality model, an incentive mechanism is necessary to motivate more high

Externí odkaz: http://arxiv.org/abs/2201.09047

Zobrazit plný text záznamu

Report

Auction-Based Ex-Post-Payment Incentive Mechanism Design for Horizontal Federated Learning with Reputation and Contribution Measurement

Autor: Zhang, Jingwen, Wu, Yuezhou, Pan, Rong

Federated learning trains models across devices with distributed data, while protecting the privacy and obtaining a model similar to that of centralized ML. A large number of workers with data and computing power are the foundation of federal learnin

Externí odkaz: http://arxiv.org/abs/2201.02410

Zobrazit plný text záznamu

Report

Privacy-preserving Federated Adversarial Domain Adaption over Feature Groups for Interpretability

Autor: Kang, Yan, Liu, Yang, Wu, Yuezhou, Ma, Guoqiang, Yang, Qiang

We present a novel privacy-preserving federated adversarial domain adaptation approach ($\textbf{PrADA}$) to address an under-studied but practical cross-silo federated domain adaptation problem, in which the party of the target domain is insufficien

Externí odkaz: http://arxiv.org/abs/2111.10934

Zobrazit plný text záznamu

Report

FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learning

Autor: Wu, Yuezhou, Kang, Yan, Luo, Jiahuan, He, Yuanqin, Yang, Qiang

Publikováno v: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022

Federated learning (FL) aims to protect data privacy by enabling clients to build machine learning models collaboratively without sharing their private data. Recent works demonstrate that information exchanged during FL is subject to gradient-based p

Externí odkaz: http://arxiv.org/abs/2111.08211

Zobrazit plný text záznamu