Block chain-based distributed federal learning method and apparatus, and terminal device

Abstract

The invention discloses a distributed federal learning method and device based on a block chain and terminal equipment. The method comprises the following steps: determining a pre-created block chain; the participant node determines a global model parameter through the intelligent contract, updates a model parameter of the local network model based on the global model parameter, and trains the updated local network model based on the local training data to obtain a local model parameter; the participant node sends the local model parameters to the intelligent contract, and aggregates all the received local model parameters through the intelligent contract to update the global model parameters; and determining the reward resource corresponding to each participant node in the training process through the intelligent contract. According to the application, the function of the central server in the traditional federated learning is realized by using the intelligent contract on the block chain, so that the central server in the federated learning is replaced by using the intelligent contract capable of performing trusted computing, and the problem that the central server in the federated learning is not trusted can be solved.

Description

technical field [0001] This application relates to the technical field of blockchain, in particular to a distributed federated learning method, device and terminal equipment based on blockchain. Background technique [0002] In the process of Industry 4.0, the full utilization of data information has become an important force for enterprises to promote industrial transformation. However, due to privacy protection considerations and competition among enterprises, the amount of data that small companies can master is relatively small, which is not conducive to the development of these companies in the process of Industry 4.0. The emergence of the technology of federated learning has solved the problem of small amount of data held by small companies to a certain extent. That is, these companies can first use their own data for model training locally, and then upload the trained local model to the central server for aggregation. Then each company downloads the aggregated globa...

AI Technical Summary

Problems solved by technology

However, the central server cannot guarantee complete honesty, which makes the federated learning process a security problem

Images