Federal learning method and device based on blockchain

Abstract

The embodiment of the invention provides a federal learning method and device based on a blockchain, and the method comprises the steps: a first node carries out training an ith round of local model based on local training data, determines the gradient information of the trained (i+1) th round of local model, cuts and quantifies each piece of first sub-gradient information in the gradient information of the (i+1) th round of local model based on a gradient cutting quantization rule to obtain each piece of second sub-gradient information, merges every m pieces of second sub-gradient information in each piece of second sub-gradient information according to a gradient merging rule to obtain n types of third sub-gradient information, and performs homomorphic encryption on the n types of third sub-gradient information to obtain n types of ciphertexts, and sends the n types of ciphertexts to the blockchain. According to the method, due to the fact that the first sub-gradient information in the local model gradient information is cut, quantified and merged, and then homomorphic encryption is carried out, computing resource consumption generated by homomorphic encryption can be reduced, and network resources consumed in the ciphertext transmission process can be reduced.

Description

technical field [0001] Embodiments of the present invention relate to the field of financial technology (Fintech), in particular to a blockchain-based federated learning method and device. Background technique [0002] With the development of computer technology, more and more technologies are applied in the financial field, and the traditional financial industry is gradually transforming into financial technology. However, due to the security and real-time requirements of the financial industry, higher requirements are also placed on technology. [0003] The existing federated learning method based on homomorphic encryption is generally: each device uses local data sets to train local models, obtains the gradient information of local models after training, and uses homomorphic encryption algorithms (such as Paillier algorithm, etc.) The encrypted local model gradient information is encrypted, and the encrypted local model gradient information is sent to the server. Then, a...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a blockchain-based federated learning method and device to solve the problems of high computational overhead and high communication overhead caused by homomorphic encryption of local model gradient information in the prior art

Images