CN114667523A - 模型训练方法、装置、服务器、终端和存储介质 - Google Patents
模型训练方法、装置、服务器、终端和存储介质 Download PDFInfo
- Publication number
- CN114667523A CN114667523A CN202080002976.6A CN202080002976A CN114667523A CN 114667523 A CN114667523 A CN 114667523A CN 202080002976 A CN202080002976 A CN 202080002976A CN 114667523 A CN114667523 A CN 114667523A
- Authority
- CN
- China
- Prior art keywords
- model
- training
- model parameters
- terminals
- parameters
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Mobile Radio Communication Systems (AREA)
- Information Transfer Between Computers (AREA)
Abstract
本公开是关于一种模型训练方法、装置、服务器、终端和存储介质,属于通信技术领域。所述方法包括:接收多个终端的数据分布信息,所述数据分布信息包括数据的类别以及各个类别包含的样本数;选取符合所述多个终端的数据分布信息的训练数据集;基于所述训练数据集进行模型训练,得到模型参数;将所述模型参数发送给所述多个终端中的至少部分终端;接收所述至少部分终端对所述模型参数进行训练得到的训练结果;基于所述至少部分终端的训练结果,对所述模型参数进行更新,得到全局模型参数。
Description
PCT国内申请,说明书已公开。
Claims (41)
- PCT国内申请,权利要求书已公开。
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2020/123292 WO2022082742A1 (zh) | 2020-10-23 | 2020-10-23 | 模型训练方法、装置、服务器、终端和存储介质 |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114667523A true CN114667523A (zh) | 2022-06-24 |
Family
ID=81291178
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202080002976.6A Pending CN114667523A (zh) | 2020-10-23 | 2020-10-23 | 模型训练方法、装置、服务器、终端和存储介质 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN114667523A (zh) |
WO (1) | WO2022082742A1 (zh) |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109716346A (zh) * | 2016-07-18 | 2019-05-03 | 河谷生物组学有限责任公司 | 分布式机器学习***、装置和方法 |
US20190042956A1 (en) * | 2018-02-09 | 2019-02-07 | Intel Corporation | Automatic configurable sequence similarity inference system |
CN110956202B (zh) * | 2019-11-13 | 2023-08-01 | 重庆大学 | 基于分布式学习的图像训练方法、***、介质及智能设备 |
CN111444848A (zh) * | 2020-03-27 | 2020-07-24 | 广州英码信息科技有限公司 | 一种基于联邦学习的特定场景模型升级方法和*** |
CN111611610B (zh) * | 2020-04-12 | 2023-05-30 | 西安电子科技大学 | 联邦学习信息处理方法、***、存储介质、程序、终端 |
-
2020
- 2020-10-23 WO PCT/CN2020/123292 patent/WO2022082742A1/zh active Application Filing
- 2020-10-23 CN CN202080002976.6A patent/CN114667523A/zh active Pending
Also Published As
Publication number | Publication date |
---|---|
WO2022082742A1 (zh) | 2022-04-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109600262B (zh) | Urllc传输网络切片中资源自配置和自优化方法及装置 | |
CN114142907B (zh) | 一种通信终端设备的信道筛选优化方法及*** | |
US20230409962A1 (en) | Sampling user equipments for federated learning model collection | |
EP4050812A1 (en) | Method and device for transmitting channel state information | |
CN102158962B (zh) | 基站协作中的分簇方法、资源分配方法及相关设备 | |
CN106507489B (zh) | 一种资源分配方法,及接入设备 | |
CN112333235A (zh) | 一种多运营商多网聚合的文件传输方法、***及智能终端 | |
CN108777857B (zh) | 一种URLLC和mMTC共存场景下的接入控制方法及*** | |
Ganjalizadeh et al. | Saving energy and spectrum in enabling URLLC services: A scalable RL solution | |
Avranas et al. | Deep reinforcement learning for resource constrained multiclass scheduling in wireless networks | |
US11864158B2 (en) | Distributed method for allocating transmission resources to D2D terminals in a cellular access network | |
CN114667523A (zh) | 模型训练方法、装置、服务器、终端和存储介质 | |
JP7425197B2 (ja) | スケジューリング方法及び装置 | |
CN117632463A (zh) | 一种计算任务的分割方法及相关装置 | |
CN111065166A (zh) | 直接通信链路的资源调度方法、终端及网络侧设备 | |
CN107666718B (zh) | 一种传输资源确认方法、用户终端、基站和*** | |
CN109495224A (zh) | 一种信息处理方法、装置、设备及计算机可读存储介质 | |
US11277715B2 (en) | Transmit multicast frame | |
CN116016095A (zh) | 一种合约管理方法、装置及*** | |
CN114666812A (zh) | 信息处理的方法和装置 | |
CN113382475B (zh) | 一种基于mumimo的资源调度方法及装置 | |
US20230354296A1 (en) | Node scheduling method and apparatus | |
US20240089742A1 (en) | Data transmission method and related apparatus | |
CN110868728B (zh) | 网络配置评判方法、装置及存储介质 | |
WO2023088017A1 (zh) | 确定网络切片可用资源的方法、电子设备和存储介质 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |