Robustness federated learning algorithm based on partial parameter aggregation
A technology of parameter aggregation and learning algorithm, which is applied in computing, computer parts, digital data protection, etc., can solve the problem that the server is difficult to verify the correctness of users, and achieve the effects of weakening attack capabilities, improving robustness, and ensuring data privacy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0026] In order to explain the technical content, constructive features, the purpose and effects of the technical solution, and the specific embodiments are described below, and the accompanying drawings will be described in detail.
[0027] The present invention proposes a robust federal learning algorithm based on partial parameter polymerization, first defining a unified upload ratio of each client, and distributes to the client along with a global model. After the client calculates the update of the local model, select the parameters that meet the number of upload ratios in the model, effectively reduce the model information uploaded by the malicious client, but can guarantee the correct convergence of the global model. The present invention then designed to encrypt the partial model uploaded by the client, so that the server can only obtain the results of the model parameter aggregation, and cannot snally detect the true upload parameters of each client. At the same time, an ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap