Horizontal Federated Learning With Unified Privacy Data Isolation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing federated learning technologies fail to adequately protect user privacy while allowing applications to utilize user data for AI model training, leading to conflicts between privacy regulations and data usage needs.
Innovation Solution
Implement a unified federated learning service (UnifiedFED) that manages data access rights, isolates user privacy data from applications, and schedules tasks based on device conditions to ensure secure and efficient AI model training.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If applications directly access user data for AI model training, then data usage efficiency is improved, but user privacy protection deteriorates
Solution Approach 1:
The patent introduces a unified federated learning service (UnifiedFED) as an intermediary between applications and user data. This service manages data access rights, isolates user privacy data from applications, and coordinates federated learning tasks across multiple devices. The intermediary enables data usage efficiency by facilitating model training while protecting privacy through controlled access mechanisms and data isolation.
2Reliability
If user data is isolated from applications for privacy protection, then privacy security is improved, but AI model training capability deteriorates
Solution Approach 1:
The patent segments the federated learning system into multiple independent components: applications, unified federated learning service, and user devices. Each segment operates with specific responsibilities - applications initiate training requests, the unified service manages coordination and data access rights, and user devices provide local data for training. This segmentation enables privacy security through isolation while maintaining model training capability through coordinated collaboration among segments.
Solution Approach 2:
The unified federated learning service performs multiple functions: managing data access rights, coordinating training tasks across devices, isolating user data from applications, and enabling federated learning. This multi-functional intermediary ensures that privacy security and model training capability are both maintained through a single coordinated system rather than conflicting separate mechanisms.
3Ease of operation
If federated learning data access right is granted to applications, then data accessibility is improved, but privacy control deterioration
Solution Approach 1:
The unified federated learning service acts as an intermediary that manages data access rights between applications and user data. It provides a standardized interface for applications to request access while maintaining complex privacy management controls on the service side. This resolves the contradiction by improving data accessibility for applications through simple interfaces while the intermediary handles the complexity of privacy management, including determining which data can be accessed and under what conditions.
Data Source
AI summary
The present disclosure discloses a method for federated learning, including: requesting, by a target application, a user to provide a federated learning data access right to access privacy data; calling, by the target application, a unified federated learning service (UnifiedFED) application to perform horizontal federated learning, acquiring, by the UnifiedFED application, the privacy data isolated from the target application according to the federated learning data access right, receiving, by the UnifiedFED application, non-privacy data from the target application, and providing, by the UnifiedFED application, the privacy data and the non-privacy data to an artificial intelligence (AI) model for federated learning training.