Movatterモバイル変換


[0]ホーム

URL:


CN115280338A - A model training method, electronic device and storage medium based on federated learning - Google Patents

A model training method, electronic device and storage medium based on federated learning
Download PDF

Info

Publication number
CN115280338A
CN115280338ACN202080098459.3ACN202080098459ACN115280338ACN 115280338 ACN115280338 ACN 115280338ACN 202080098459 ACN202080098459 ACN 202080098459ACN 115280338 ACN115280338 ACN 115280338A
Authority
CN
China
Prior art keywords
model
training method
federated learning
storage medium
electronic device
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202080098459.3A
Other languages
Chinese (zh)
Inventor
田文强
沈嘉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Oppo Mobile Telecommunications Corp Ltd
Original Assignee
Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangdong Oppo Mobile Telecommunications Corp LtdfiledCriticalGuangdong Oppo Mobile Telecommunications Corp Ltd
Publication of CN115280338ApublicationCriticalpatent/CN115280338A/en
Pendinglegal-statusCriticalCurrent

Links

Images

Classifications

Landscapes

Abstract

Translated fromChinese

一种基于联邦学习的模型训练方法,包括:子节点设备发送局部模型的模型参数和所述局部模型对应的权重信息(S201);所述模型参数和所述权重信息用于主节点设备训练全局模型。还公开了另一种基于联邦学习的模型训练方法、电子设备及存储介质。

Figure 202080098459

A model training method based on federated learning, comprising: a child node device sends model parameters of a local model and weight information corresponding to the local model (S201); the model parameters and the weight information are used for the master node device to train a global model Model. Also disclosed are another model training method, electronic device and storage medium based on federated learning.

Figure 202080098459

Description

Translated fromChinese

PCT国内申请,说明书已公开。PCT domestic application, specification has been published.

Claims (60)

Translated fromChinese
PCT国内申请,权利要求书已公开。PCT domestic application, the claims have been published.
CN202080098459.3A2020-03-112020-03-11 A model training method, electronic device and storage medium based on federated learningPendingCN115280338A (en)

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
PCT/CN2020/078721WO2021179196A1 (en)2020-03-112020-03-11Federated learning-based model training method, electronic device, and storage medium

Publications (1)

Publication NumberPublication Date
CN115280338Atrue CN115280338A (en)2022-11-01

Family

ID=77670362

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN202080098459.3APendingCN115280338A (en)2020-03-112020-03-11 A model training method, electronic device and storage medium based on federated learning

Country Status (2)

CountryLink
CN (1)CN115280338A (en)
WO (1)WO2021179196A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN116170781A (en)*2022-12-072023-05-26杭州援宇科技有限公司D2D mutual learning system pairing method based on unlicensed frequency band transmission
CN116347646A (en)*2022-12-132023-06-27国网湖北省电力有限公司信息通信公司 An NR-U-based efficient access method for federated learning of electric power Internet

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN113935469B (en)*2021-10-262022-06-24城云科技(中国)有限公司Model training method based on decentralized federal learning
CN113708982B (en)*2021-10-282022-01-18华中科技大学Service function chain deployment method and system based on group learning
CN113869528B (en)2021-12-022022-03-18中国科学院自动化研究所De-entanglement individualized federated learning method for consensus characterization extraction and diversity propagation
CN114118447A (en)*2021-12-152022-03-01湖南红普创新科技发展有限公司Novel federal learning system, method and device, computer equipment and storage medium
CN114254761B (en)*2021-12-222025-05-27安徽兰科智能科技有限公司 A universal federated learning implementation method for heterogeneous networks
CN114266406B (en)*2021-12-242024-07-12北京航空航天大学Large-range road network traffic flow state prediction method based on federal learning
CN116669085A (en)*2022-02-182023-08-29展讯通信(上海)有限公司 Communication method, device, equipment and storage medium
CN114662706B (en)*2022-03-242024-07-12支付宝(杭州)信息技术有限公司Model training method, device and equipment
WO2024026583A1 (en)*2022-07-302024-02-08华为技术有限公司Communication method and communication apparatus
CN117676594A (en)*2022-08-102024-03-08索尼集团公司Electronic device and method for spectrum management apparatus, and storage medium
WO2024036526A1 (en)*2022-08-172024-02-22华为技术有限公司Model scheduling method and apparatus
CN116346863B (en)*2023-05-292023-08-01湘江实验室 Data processing method, device, equipment and medium for in-vehicle network based on federated learning

Citations (3)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN109871702A (en)*2019-02-182019-06-11深圳前海微众银行股份有限公司 Federated model training method, system, device, and computer-readable storage medium
CN110490335A (en)*2019-08-072019-11-22深圳前海微众银行股份有限公司A kind of method and device calculating participant's contribution rate
CN110782042A (en)*2019-10-292020-02-11深圳前海微众银行股份有限公司 Horizontal and vertical federation methods, devices, equipment and media

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US11475350B2 (en)*2018-01-222022-10-18Google LlcTraining user-level differentially private machine-learned models
CN110442457A (en)*2019-08-122019-11-12北京大学深圳研究生院Model training method, device and server based on federation's study
CN110610242B (en)*2019-09-022023-11-14深圳前海微众银行股份有限公司Method and device for setting weights of participants in federal learning
CN110795477A (en)*2019-09-202020-02-14平安科技(深圳)有限公司Data training method, device and system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN109871702A (en)*2019-02-182019-06-11深圳前海微众银行股份有限公司 Federated model training method, system, device, and computer-readable storage medium
CN110490335A (en)*2019-08-072019-11-22深圳前海微众银行股份有限公司A kind of method and device calculating participant's contribution rate
CN110782042A (en)*2019-10-292020-02-11深圳前海微众银行股份有限公司 Horizontal and vertical federation methods, devices, equipment and media

Cited By (2)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN116170781A (en)*2022-12-072023-05-26杭州援宇科技有限公司D2D mutual learning system pairing method based on unlicensed frequency band transmission
CN116347646A (en)*2022-12-132023-06-27国网湖北省电力有限公司信息通信公司 An NR-U-based efficient access method for federated learning of electric power Internet

Also Published As

Publication numberPublication date
WO2021179196A1 (en)2021-09-16

Similar Documents

PublicationPublication DateTitle
CN115280338A (en) A model training method, electronic device and storage medium based on federated learning
CN114402369A (en) Human body gesture recognition method, device, storage medium and electronic device
CN110710190A (en)Method and terminal for generating user portrait
CN114450682A (en) Control method, device and computer-readable storage medium for integrated energy system
CN113807097A8 (en) Named entity recognition model establishment method and named entity recognition method
CN111527501A (en)Chip adaptation determining method and related product
CN113015996A (en)Advertisement pushing method and related equipment
CN114945817A (en)Task processing method, device and equipment based on defect detection and storage medium
CN114846762A (en) Communication link initialization method and device
CN112640550A (en)Transmission device and method of feedback information
CN115427969A (en)Model updating method and device and communication equipment
CN115885272A (en) Method, device, electronic device, storage medium and program for updating knowledge map
JP2020126510A5 (en)
CN114945892A (en)Method, device, system, equipment and storage medium for playing audio
Yang et al.Global stability of two SIS epidemic mean-field models on complex networks: Lyapunov functional approach
CN112889061A (en)Method, device and equipment for evaluating quality of face image and storage medium
CN115023929A (en) Data synchronization method, device, system, electronic device and storage medium
CN115735233A (en) Object detection model training method, object detection method and device
CN118489133A (en) Model building method and device, storage medium, and electronic device
CN110786043A (en)Method for determining data transmission mode, network device and computer storage medium
CN115244912A (en) File distribution method, apparatus, electronic device, and computer-readable storage medium
JP2019078857A5 (en)
CN115486111A (en)Network selection method, electronic device and storage medium
CN115004671A (en)Resource publishing method, device, gateway, cloud platform and computer storage medium
CN110178427A (en)Terminal pattern acquisition methods, device and equipment

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination

[8]ページ先頭

©2009-2025 Movatter.jp