三. 一种基于区块链的联邦学习框架(Blockchained On-Device Federated Learning) 据调研,[1] 提出一种基于区块链的联邦学习通用框架(Blockchained On-Device Federated Learning, BlockFL),其具体步骤如下: 1.参数初始化:创建创世块,其包含随机初始化的全局参数等信息。 2.本地模型更新:每一个终端设备从新区块下...
Motivation:随着联邦学习的流行,谷歌团队也提出了vanilla FL模型。但是该模型存在3个缺陷: 1)依赖唯一的中心服务器。该服务器一旦被攻击,将影响下属所有client客户端的模型训练进度; 2)没有奖励机制。如果没有及时的激励,一些拥有大批数据的机构或组织将没有足够的动力去分享数据去参与模型训练; 3)原始模型的训练完成...
By leveraging blockchain, this letter proposes a blockchained federated learning (BlockFL) architecture where local learning model updates are exchanged and verified. This enables on-device machine learning without any centralized training data or coordination by utilizing a consensus mechanism in blockcha...
Blockchained On-Device Federated Learningdoi:10.1109/LCOMM.2019.2921755Hyesung KimJihong ParkMehdi BennisSeong-Lyun KimIEEE
Federated Learning 联邦学习概述及最新工作 声明:以后会逐渐转移到某乎啦,有兴趣的伙伴可以关注:霁月 一、目前主流的联邦学习应用场景 Cross-silo FL Cross-device FL Setting Training a model on siloed data. Clients are from different organizations (e.g. medical or financial) o... ...
Towards On-Device Federated Learning: A Direct Acyclic Graph-based Blockchain Approach Due to the distributed characteristics of Federated Learning (FL), the vulnerability of global model and coordination of devices are the main obstacle. As ... M Cao,L Zhang,B Cao 被引量: 0发表: 2021年 Blo...