CN116018601A - 一种联邦学习方法、装置及系统 - Google Patents

一种联邦学习方法、装置及系统 Download PDF

Info

Publication number
CN116018601A
CN116018601A CN202080103515.8A CN202080103515A CN116018601A CN 116018601 A CN116018601 A CN 116018601A CN 202080103515 A CN202080103515 A CN 202080103515A CN 116018601 A CN116018601 A CN 116018601A
Authority
CN
China
Prior art keywords
data
target
model
node
module
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
CN202080103515.8A
Other languages
English (en)
Inventor
王楚捷
秦东润
于益俊
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.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co 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 Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Publication of CN116018601A publication Critical patent/CN116018601A/zh
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • 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
    • G06N3/098—Distributed learning, e.g. federated learning
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种联邦学习方法、装置及系统，涉及人工智能领域，该方法包括：第一节点根据训练任务所需的目标数据特征，获取多个第二节点的数据分布信息，任一个第二节点的数据分布信息用于指示第二节点本地存储的符合目标数据特征的业务数据所属的数据类别；第一节点根据训练任务所需的目标数据类别以及多个第二节点的数据分布信息，在多个第二节点中选择至少两个目标第二节点，任一个目标第二节点本地存储有符合目标数据特征且属于目标数据类别的目标业务数据；第一节点指示至少两个目标第二节点进行联邦学习，以获得训练任务中与目标数据类别对应的联邦学习模型。在参与方具有多种数据分布的情况下，该方法可避免所训练的模型受到数据毒化的影响。

Description

PCT国内申请，说明书已公开。

Claims (47)

  1. PCT国内申请，权利要求书已公开。
CN202080103515.8A 2020-11-30 2020-11-30 一种联邦学习方法、装置及系统 Pending CN116018601A (zh)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/132991 WO2022110248A1 (zh) 2020-11-30 2020-11-30 一种联邦学习方法、装置及系统

Publications (1)

Publication Number Publication Date
CN116018601A true CN116018601A (zh) 2023-04-25

Family

ID=81753917

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202080103515.8A Pending CN116018601A (zh) 2020-11-30 2020-11-30 一种联邦学习方法、装置及系统

Country Status (4)

Country Link
US (1) US20230274192A1 (zh)
EP (1) EP4231209A4 (zh)
CN (1) CN116018601A (zh)
WO (1) WO2022110248A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024092661A1 (zh) * 2022-11-03 2024-05-10 北京小米移动软件有限公司 模型的标识方法及装置
CN116757286B (zh) * 2023-08-16 2024-01-19 杭州金智塔科技有限公司 基于联邦学习的多方联合因果树模型构建系统以及方法

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200202243A1 (en) * 2019-03-05 2020-06-25 Allegro Artificial Intelligence Ltd Balanced federated learning
US11836643B2 (en) * 2019-03-08 2023-12-05 Nec Corporation System for secure federated learning
WO2020229684A1 (en) * 2019-05-16 2020-11-19 Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. Concepts for federated learning, client classification and training data similarity measurement
CN110442457A (zh) * 2019-08-12 2019-11-12 北京大学深圳研究生院 基于联邦学习的模型训练方法、装置及服务器
CN110598870B (zh) * 2019-09-02 2024-04-30 深圳前海微众银行股份有限公司 一种联邦学习方法及装置
CN111008709A (zh) * 2020-03-10 2020-04-14 支付宝(杭州)信息技术有限公司 联邦学习、资料风险评估方法、装置和系统
CN111860581A (zh) * 2020-06-11 2020-10-30 南京邮电大学 一种基于模型离散度的联邦学习训练方法

Also Published As

Publication number Publication date
EP4231209A4 (en) 2023-12-20
EP4231209A1 (en) 2023-08-23
WO2022110248A1 (zh) 2022-06-02
US20230274192A1 (en) 2023-08-31

Similar Documents

Publication Publication Date Title
US11451622B1 (en) Multi-tier resource and load orchestration
CN106936890B (zh) 汇聚车辆相关的大数据
CN108418862A (zh) 基于人工智能服务云平台的微服务管理方法和系统
CN116018601A (zh) 一种联邦学习方法、装置及系统
GB2574904A (en) Ranking data sources in a data processing system
CN109151042B (zh) 物联感知数据智能规划方法
CN104468711A (zh) 物联网通用的数据管理编码方法及系统
CN109409980A (zh) 单车推荐方法、装置、设备及计算机可读存储介质
CN111163482B (zh) 数据的处理方法、设备及存储介质
WO2023131303A1 (zh) 数字孪生网络的编排方法、数字孪生网络、介质和程序
CN113722568A (zh) 元数据处理、工业标识注册、数据查询方法、装置及介质
CN114091610A (zh) 智能决策方法及装置
CN103916891A (zh) 一种异构web服务网关实现方法及装置
CN102158551A (zh) 物联网信息源统一描述和访问方法
CN111309946B (zh) 一种已建立档案优化方法及装置
CN109741108A (zh) 基于情境感知的流式应用推荐方法、装置和电子设备
CN109257422A (zh) 感知网络信息重构方法
CN109218131B (zh) 网络监控方法、装置、计算机设备和存储介质
KR20130126444A (ko) 사용자 식별 정보를 이용한 컨테이너 자원의 구성 방법, 기록 매체 및 그 장치
WO2022028170A1 (zh) 一种数据传输方法、相关网络节点和存储介质
CN114528297A (zh) 一种数据收集方法、装置、电子设备及存储介质
US20150172157A1 (en) Method and apparatus for determining data flow rate on service access port
CN108206894B (zh) 一种业务处理系统、方法及装置
CN112468965A (zh) 一种外勤拜访真实性校验方法、装置及计算机设备
US8484182B1 (en) Wireless device content searching

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