Federated learning method, device and system, electronic device, storage medium
A learning method and federated technology, applied in machine learning, computer security devices, electrical and digital data processing, etc., can solve the problem that the optimization result is not the best, and achieve the effect of improving the optimization effect.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
example 1
[0157] This example describes two federal learning processes based on the two federal learning systems.
[0158] Such as Figure 7 As shown, two federal learning systems include: EMS, a virtual NCCN, an NCCN, and four NE.
[0159] Among them, the virtual NCCN is set in the EMS, and two NEs are hanging in the virtual NCCN, which are NE1 and NE2; NCCN hung down the EMS, and the NCCN hangs two NEs, which are NE3 and NE4, respectively.
[0160] Among them, EMS includes: business application, first task management module, first global model management module, and weight indicator management module; virtual NCCN includes: second task management module and a second global model management module; NCCN includes: third task management Modules and Third Global Models Management Modules.
[0161] Among them, NE1, NE2, NE3, NE4, NCCN, and virtual NCCN are used to implement the first layer of federal learning process, NCCN, virtual NCCN, and EMS for implementing the second layer of federal lear...
example 2
[0177] This example describes the federal learning process based on the two-layer federal learning system.
[0178] Such as Figure 7 As shown, two federal learning systems include: EMS, a virtual NCCN, an NCCN, and four NE.
[0179] Among them, the virtual NCCN is set in the EMS, and two NEs are hanging in the virtual NCCN, which are NE1 and NE2; NCCN hung down the EMS, and the NCCN hangs two NEs, which are NE3 and NE4, respectively.
[0180] Among them, EMS includes: business application, first task management module, first global model management module, and weight indicator management module; virtual NCCN includes: second task management module and a second global model management module; NCCN includes: third task management Modules and Third Global Models Management Modules.
[0181] Among them, NE1, NE2, NE3, NE4, NCCN, and virtual NCCN are used to implement the first layer of federal learning process, NCCN, virtual NCCN, and EMS for implementing the second layer of federal l...
example 3
[0195] This example describes two federal learning processes based on the two federal learning systems.
[0196] Such as Figure 7 As shown, two federal learning systems include: EMS, a virtual NCCN, an NCCN, and four NE.
[0197] Among them, the virtual NCCN is set in the EMS, and two NEs are hanging in the virtual NCCN, which are NE1 and NE2; NCCN hung down the EMS, and the NCCN hangs two NEs, which are NE3 and NE4, respectively.
[0198] Among them, EMS includes: business application, first task management module, first global model management module, and weight indicator management module; virtual NCCN includes: second task management module and a second global model management module; NCCN includes: third task management Modules and Third Global Models Management Modules.
[0199] Among them, NE1, NE2, NE3, NE4, NCCN, and virtual NCCN are used to implement the first layer of federal learning process, NCCN, virtual NCCN, and EMS for implementing the second layer of federal lear...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More