A Training Method of Neural Network Model Based on Shared Learning

Abstract

The invention relates to the technical field of machine learning and aims to provide a training method of a neural network model based on shared learning. In this method, multiple shared learning participants perform mixed secure multi-party computing and central node local computing through secret sharing to realize neural network model training; specifically include: data preparation; data loading and initialization; loading the current training batch; computing the first One-layer linear output; calculate model prediction value; calculate model output gradient; update model and calculation; update local shared weights; evaluate on test set. The invention combines multi-party secure computing and local computing to improve the efficiency of shared learning. Through the online encrypted multiplication triplet provider, the efficiency of secure multi-party computation of secret sharing is improved, and the overhead is greatly reduced compared with homomorphic encryption and obfuscated circuits. It is suitable for vertical shared learning scenarios and enables all parties to perform federated modeling without any overlapping features.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a training method of a neural network model based on shared learning. Background technique [0002] With the widespread application of machine learning algorithms, a lot of data is used for the training of machine learning models. For example, a bank predicts the credit of other customers by training the data of some customers. The shared learning method is a privacy-preserving machine learning method that integrates local computing and multi-party secure computing, and is widely used in machine learning scenarios that require privacy protection. For example, one bank has the user's loan data, another bank has the user's transaction data, and the two banks want to share data for modeling and predict the user's credit level. But if the data is directly put together and trained with a neural network model, the data will leave at least one bank, thus bringing the risk of ...

AI Technical Summary

Problems solved by technology

However, the trusted execution environment has problems such as high cost and many restrictions on running programs, and cannot well support multiple algorithms.

[0007] There are other existing technologies, although they have solved the specific implementation problems of privacy-preserving machine learning to a certain extent, but there are still problems such as small scope of application, high computing and communication overhead, unstable model convergence, and lack of theoretical foundation.

Images