Information interaction system and method suitable for federated learning

Abstract

The embodiment of the invention discloses an information interaction system and method suitable for federated learning. The system comprises at least two participants and a coordinator, each participant is provided with a graph network, and the graph network comprises a plurality of nodes; each participant represents all nodes in the graph network of the participant with a fixed-length vector to obtain a representation vector of each node, training of a graph neural network model is performed based on the representation vectors of the nodes, and gradient information is uploaded to the coordinator in the training process; the coordinator corrects the gradient information uploaded by each participant according to the gradient information uploaded by all participants, and issues the correctedgradient information to each participant; and each participant receives the corrected gradient information fed back by the coordinator, and updates the representation vector of the node based on thecorrected gradient information of the coordinator. Information interaction can be realized under the condition of guaranteeing the information security of each participant.

Description

technical field [0001] The invention belongs to the field of big data technology, and specifically, the invention relates to an information interaction system and method suitable for federated learning. Background technique [0002] Cooperation between enterprises has become commonplace, and there is also great potential for cross-field project cooperation, which can well make up for the shortcomings of all parties. For example, social enterprise (user basic information) cooperates with e-commerce (shopping, browsing history). In view of the potential of multi-party data complementarity and user privacy protection and data security requirements, federated learning came into being. Federated learning refers to efficient machine learning among multiple participants or multiple computing nodes under the premise of ensuring information security during big data exchange, protecting terminal data and personal data privacy, and ensuring compliance with laws and regulations. In ad...

AI Technical Summary

Problems solved by technology

[0003] In order to solve the technical problems of the random walk serialized encoding method in the prior art, such as easy loss of node information, low interaction frequency, unreliable accuracy of calculation results and low calculation efficiency, the disclosed embodiments of the present invention provide An information interaction system and method suitable for federated learning, which can make full use of the node's own attribute information through parallel encoding, increase the frequency of interaction, and improve the computational efficiency of data processing

Images