CN115496204B - 一种跨域异质场景下的面向联邦学习的评测方法及装置 - Google Patents
一种跨域异质场景下的面向联邦学习的评测方法及装置 Download PDFInfo
- Publication number
- CN115496204B CN115496204B CN202211228750.5A CN202211228750A CN115496204B CN 115496204 B CN115496204 B CN 115496204B CN 202211228750 A CN202211228750 A CN 202211228750A CN 115496204 B CN115496204 B CN 115496204B
- Authority
- CN
- China
- Prior art keywords
- time
- federal learning
- gradient
- client
- layer
- 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.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 38
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000012360 testing method Methods 0.000 claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 15
- 230000008569 process Effects 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims description 21
- 238000004891 communication Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 8
- 230000002776 aggregation Effects 0.000 claims description 5
- 238000004220 aggregation Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000006116 polymerization reaction Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 abstract 1
- 238000013139 quantization Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
Description
Claims (4)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211228750.5A CN115496204B (zh) | 2022-10-09 | 2022-10-09 | 一种跨域异质场景下的面向联邦学习的评测方法及装置 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211228750.5A CN115496204B (zh) | 2022-10-09 | 2022-10-09 | 一种跨域异质场景下的面向联邦学习的评测方法及装置 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115496204A CN115496204A (zh) | 2022-12-20 |
CN115496204B true CN115496204B (zh) | 2024-02-02 |
Family
ID=84474789
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211228750.5A Active CN115496204B (zh) | 2022-10-09 | 2022-10-09 | 一种跨域异质场景下的面向联邦学习的评测方法及装置 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115496204B (zh) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117350373B (zh) * | 2023-11-30 | 2024-03-01 | 艾迪恩(山东)科技有限公司 | 一种基于局部自注意力机制的个性化联邦聚合算法 |
CN117649672B (zh) * | 2024-01-30 | 2024-04-26 | 湖南大学 | 基于主动学习与迁移学习的字体类别视觉检测方法和系统 |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112232528A (zh) * | 2020-12-15 | 2021-01-15 | 之江实验室 | 一种联邦学习模型训练方法、装置及联邦学习系统 |
WO2021115480A1 (zh) * | 2020-06-30 | 2021-06-17 | 平安科技(深圳)有限公司 | 联邦学习方法、装置、设备和存储介质 |
CN113391897A (zh) * | 2021-06-15 | 2021-09-14 | 电子科技大学 | 一种面向异构场景的联邦学习训练加速方法 |
CN114169412A (zh) * | 2021-11-23 | 2022-03-11 | 北京邮电大学 | 面向大规模产业链隐私计算的联邦学习模型训练方法 |
CN114219097A (zh) * | 2021-11-30 | 2022-03-22 | 华南理工大学 | 一种基于异构资源之上的联邦学习训练和预测方法及系统 |
CN114492833A (zh) * | 2021-12-29 | 2022-05-13 | 上海智能网联汽车技术中心有限公司 | 基于梯度记忆的车联网联邦学习分层知识安全迁移方法 |
CN114580663A (zh) * | 2022-03-01 | 2022-06-03 | 浙江大学 | 面向数据非独立同分布场景的联邦学习方法及系统 |
WO2022141841A1 (zh) * | 2020-12-29 | 2022-07-07 | 平安科技(深圳)有限公司 | 联邦学习的过程中模型参数的处理方法、装置及相关设备 |
CN114912705A (zh) * | 2022-06-01 | 2022-08-16 | 南京理工大学 | 一种联邦学习中异质模型融合的优化方法 |
CN114943345A (zh) * | 2022-06-10 | 2022-08-26 | 西安电子科技大学 | 基于主动学习和模型压缩的联邦学习全局模型训练方法 |
CN115062710A (zh) * | 2022-06-22 | 2022-09-16 | 西安电子科技大学 | 基于深度确定性策略梯度的联邦学习分类模型训练方法 |
-
2022
- 2022-10-09 CN CN202211228750.5A patent/CN115496204B/zh active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021115480A1 (zh) * | 2020-06-30 | 2021-06-17 | 平安科技(深圳)有限公司 | 联邦学习方法、装置、设备和存储介质 |
CN112232528A (zh) * | 2020-12-15 | 2021-01-15 | 之江实验室 | 一种联邦学习模型训练方法、装置及联邦学习系统 |
WO2022141841A1 (zh) * | 2020-12-29 | 2022-07-07 | 平安科技(深圳)有限公司 | 联邦学习的过程中模型参数的处理方法、装置及相关设备 |
CN113391897A (zh) * | 2021-06-15 | 2021-09-14 | 电子科技大学 | 一种面向异构场景的联邦学习训练加速方法 |
CN114169412A (zh) * | 2021-11-23 | 2022-03-11 | 北京邮电大学 | 面向大规模产业链隐私计算的联邦学习模型训练方法 |
CN114219097A (zh) * | 2021-11-30 | 2022-03-22 | 华南理工大学 | 一种基于异构资源之上的联邦学习训练和预测方法及系统 |
CN114492833A (zh) * | 2021-12-29 | 2022-05-13 | 上海智能网联汽车技术中心有限公司 | 基于梯度记忆的车联网联邦学习分层知识安全迁移方法 |
CN114580663A (zh) * | 2022-03-01 | 2022-06-03 | 浙江大学 | 面向数据非独立同分布场景的联邦学习方法及系统 |
CN114912705A (zh) * | 2022-06-01 | 2022-08-16 | 南京理工大学 | 一种联邦学习中异质模型融合的优化方法 |
CN114943345A (zh) * | 2022-06-10 | 2022-08-26 | 西安电子科技大学 | 基于主动学习和模型压缩的联邦学习全局模型训练方法 |
CN115062710A (zh) * | 2022-06-22 | 2022-09-16 | 西安电子科技大学 | 基于深度确定性策略梯度的联邦学习分类模型训练方法 |
Non-Patent Citations (1)
Title |
---|
联邦学习模型在涉密数据处理中的应用;贾延延;张昭;冯键;王春凯;;中国电子科学研究院学报(第01期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN115496204A (zh) | 2022-12-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115496204B (zh) | 一种跨域异质场景下的面向联邦学习的评测方法及装置 | |
US11295208B2 (en) | Robust gradient weight compression schemes for deep learning applications | |
CN112862011A (zh) | 基于联邦学习的模型训练方法、装置及联邦学习系统 | |
CN113850272A (zh) | 基于本地差分隐私的联邦学习图像分类方法 | |
CN113077060A (zh) | 针对边云协同的联邦学习系统及方法 | |
CN111931241B (zh) | 基于隐私保护的线性回归特征显著性检验方法、装置 | |
EP3863003B1 (en) | Hidden sigmoid function calculation system, hidden logistic regression calculation system, hidden sigmoid function calculation device, hidden logistic regression calculation device, hidden sigmoid function calculation method, hidden logistic regression calculation method, and program | |
US11991156B2 (en) | Systems and methods for secure averaging of models for federated learning and blind learning using secure multi-party computation | |
CN111639367B (zh) | 基于树模型的两方联合分类方法、装置、设备及介质 | |
KR20220101671A (ko) | 그래디언트 부스팅을 통한 프라이버시 보호 기계 학습 | |
US20230368019A1 (en) | Deep learning system for performing private inference and operating method thereof | |
CN114448598A (zh) | 密文压缩方法、密文解压缩方法、装置、设备和存储介质 | |
CN115907231A (zh) | 一种电网数据预测的方法及装置 | |
CN113379039B (zh) | 一种模型训练的方法、系统及装置 | |
CN117744123A (zh) | 隐私数据的安全保护方法、系统、电子设备及存储介质 | |
US11329808B2 (en) | Secure computation device, secure computation authentication system, secure computation method, and program | |
US12088565B2 (en) | Systems and methods for privacy preserving training and inference of decentralized recommendation systems from decentralized data | |
TW202145078A (zh) | 具有動態最小批次尺寸之運算方法,以及用於執行該方法之運算系統及電腦可讀儲存媒體 | |
EP4399647A1 (en) | Systems and methods for providing a split inference approach to protect data and model | |
CN111052204B (zh) | 份额生成装置、份额变换装置、秘密计算系统、它们的方法及记录介质 | |
CN112417478A (zh) | 数据处理方法、装置、设备及存储介质 | |
CN113052323B (zh) | 基于联邦学习的模型训练方法、装置和电子设备 | |
CN112765898B (zh) | 多任务联合训练模型方法、系统、电子设备和存储介质 | |
CN115580493B (zh) | 电力数据分类加密传输方法、装置和计算机设备 | |
CN117454185B (zh) | 联邦模型训练方法、装置、计算机设备和存储介质 |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CB03 | Change of inventor or designer information |
Inventor after: Liu Miao Inventor after: Guo Liang Inventor after: Lin Wanru Inventor after: Li Ningdong Inventor after: Gui Guan Inventor after: Yang Jie Inventor before: Liu Miao Inventor before: Guo Liang Inventor before: Lin Wanru Inventor before: Li Ningdong Inventor before: Gui Guan Inventor before: Yang Jie |