Results 21 to 30 of about 223 (114)
Edge computing privacy protection method based on blockchain and federated learning [PDF]
, 2021 Aiming at the needs of edge computing for data privacy, the correctness of calculation results and the auditability of data processing, a privacy protection method for edge computing based on blockchain and federated learning was proposed, which can ...
Chen FANG +6 more
core +1 more source
Efficient distributed model sharing strategy for data privacy protection in Internet of vehicles [PDF]
, 2022 Aiming at the efficiency problem of privacy data sharing in the Internet of vehicles (IoV), an efficient distributed model sharing strategy based on blockchain was proposed.In response to the data sharing requirements among multiple entities and roles in
Chen ZHAO +5 more
core +1 more source
Survey on model inversion attack and defense in federated learning [PDF]
, 2023 As a distributed machine learning technology, federated learning can solve the problem of data islands.However, because machine learning models will unconsciously remember training data, model parameters and global models uploaded by participants will ...
Dong WANG +7 more
core +1 more source
Communication-efficient federated learning method via redundant data elimination [PDF]
, 2023 To address the influence of limited network bandwidth of edge devices on the communication efficiency of federated learning, and efficiently transmit local model update to complete model aggregation, a communication-efficient federated learning method ...
Hao WANG, Kaiju LI, Qiang XU
core +1 more source
Client grouping and time-sharing scheduling for asynchronous federated learning in heterogeneous edge computing environment [PDF]
, 2023 To overcome the three key challenges of federated learning in heterogeneous edge computing, i.e., edge heterogeneity, data Non-IID, and communication resource constraints, a grouping asynchronous federated learning (FedGA) mechanism was proposed.Edge ...
Hongli XU +5 more
core +1 more source
Data augmentation scheme for federated learning with non-IID data [PDF]
, 2023 To solve the problem that the model accuracy remains low when the data are not independent and identically distributed (non-IID) across different clients in federated learning, a privacy-preserving data augmentation scheme was proposed.Firstly, a data ...
Di WANG, Lingtao TANG, Shengyun LIU
core +1 more source
TDMA-based user scheduling policies for federated learning [PDF]
, 2021 To improve the communication efficiency in FL (federated learning), for the scenario with heterogeneous edge user's computing capacity and channel state, a class of time division multiple access (TDMA) based user scheduling policies were proposed for FL ...
Dong WANG +3 more
core +1 more source
Review of Federated Learning and Its Security and Privacy Protection [PDF]
Federated Learning (FL) is a new distributed machine earning technology that only requires local maintenance of data and can train a common model through the cooperation of all parties, which mitigates issues pertaining to data collection and privacy ...
XIONG Shiqiang, HE Daojing, WANG Zhendong, DU Runmeng
core +1 more source
Byzantine-robust federated learning over Non-IID data [PDF]
, 2023 The malicious attacks of Byzantine nodes in federated learning was studied over the non-independent and identically distributed dataset , and a privacy protection robust gradient aggregation algorithm was proposed.A reference gradient was designed to ...
Jianfeng MA +6 more
core +1 more source
大数据联邦学习使用来自多个参与者提供的数据协同训练全局模型，近年来在促进企业间数据合作方面发挥着越来越重要的作用。另外，联邦学习训练范式常常面临数据不足的困境，因此为联邦学习参与者提供公平性保证以激励更多参与者贡献他们宝贵的资源是非常重要的。针对联邦学习的公平性问题，首先依据公平目标不同，从模型表现均衡、贡献评估公平、消除群体歧视出发进行了联邦学习公平性的3种分类；然后对现有的公平性促进方法进行了深入介绍与比较，旨在帮助研究者开发新的公平性促进方法；最后通过对联邦学习落地过程中的需求进行剖析 ...
朱智韬, 司世景, 王健宗, 程宁, 孔令炜, 黄章成, 肖京
doaj +1 more source