Trusted Node Federated Learning Reduces Data Volume
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Federated machine learning technologies face significant challenges due to the increased storage, computing, and network resource consumption caused by performing model training in an encrypted state, which is exacerbated by algorithms like homomorphic encryption that can increase data volume by over 30 times.
Innovation Solution
The implementation of a federated learning method that utilizes a trusted node to receive and decrypt encrypted data sets from participants, perform model training on unencrypted data, and update model parameters using intermediate training results from other trusted nodes, thereby reducing the need for encrypted computations and minimizing resource consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If homomorphic encryption algorithm is used for model training, then data security is improved, but data volume increases by more than 30 times
Solution Approach 1:
The patent introduces a trusted node as an intermediary between data participants. The trusted node receives encrypted data, decrypts it using secure key management, performs model training on the decrypted data, and returns results. This mediator approach allows decryption to occur in a controlled, secure environment rather than requiring encryption throughout the entire computation process, thereby reducing data volume while maintaining security through the trusted intermediary.
2Reliability
If model training is performed in encrypted state, then data privacy is protected, but computing resources consumption increases sharply
Solution Approach 1:
The trusted node serves as a mediator that handles the computationally intensive decryption and training operations. Instead of requiring all participants to perform encrypted computations (which is extremely resource-intensive), the system centralizes these operations at the trusted node which has dedicated computing resources, thereby reducing overall computing resource consumption while maintaining privacy through the trusted intermediary model.
3Reliability
If encrypted data is used for federated learning, then data security is maintained, but network bandwidth consumption increases due to large data volume
Solution Approach 1:
The trusted node acts as a data aggregation and processing intermediary. Participants send their local data to the trusted node (which manages encryption/decryption), and the trusted node performs centralized training. This eliminates the need for participants to exchange large volumes of encrypted data with each other, significantly reducing network bandwidth consumption while maintaining security through the trusted intermediary's key management and controlled decryption process.
Data Source
AI summary
Aspects relating to machine learning includes receiving, by a first trusted node, a first target data set sent by a first participant, wherein the first target data set is obtained via encrypting, by the first participant, a data set provided by the first participant based on a first preset encryption mode; decrypting the first target data set, determining first training data, and performing model training for a preset machine learning model based on the first training data to obtain a first intermediate training result; acquiring an encrypted second intermediate training result sent by at least one second trusted node; and performing federated learning for the preset machine learning model based on at least the first intermediate training result and the decrypted second intermediate training result, to update model parameters of the preset machine learning model and obtain a learning completed target model.