Hypergraph neural network classification method and device

Abstract

The invention provides a hypergraph neural network classification method. The method comprises: obtaining to-be-predicted label data; constructing a hypergraph incidence matrix and an original feature matrix of the to-be-predicted label data; constructing a hypergraph neural network for different modes in the to-be-predicted label data, and generating a first hypergraph neural network model; matching and merging a preset second hypergraph neural network model and the first hypergraph neural network model, and replacing untrained parameters of each layer in the first hypergraph neural network model with trained feature conversion parameters; and inputting the hypergraph incidence matrix and the original feature matrix into the first hypergraph neural network model to obtain a final classification prediction result. Different types of node connections are quantified by defining the association rules, and complex association in a single mode-multi-mode is modeled hierarchically, so that knowledge learning of a complex network under multi-mode collaboration becomes faster and more accurate, and meanwhile, the classification prediction capability of complex association data is improved.

Description

technical field [0001] The present application relates to the technical field of complex network node classification, in particular to a hypergraph neural network classification method and device. Background technique [0002] Graph neural network has gradually attracted the attention of a large number of scholars due to its excellent performance in processing unstructured data. Compared with traditional convolutional neural networks, graph neural networks are usually used in complex network analysis, such as drug structure prediction, protein-target prediction, social network recommendation, etc. At present, the edges in the graph network can only connect two points, in other words, only pairwise associations can be modeled, which makes it very limited in modeling and learning high-order complex associated data. How to directly model high-order complex associations and improve the learning efficiency of the model becomes very important. At present, the main challenges for...

AI Technical Summary

Problems solved by technology

[0004] Therefore, the first purpose of this application is to propose a hypergraph neural network classification method, which solves the technical problems that the existing methods are difficult to directly model high-order complex associations and the learning efficiency of the model is low, and quantifies by defining association rules Different types of node connections, hierarchically model the complex associations under single-mode and multi-modality, making the knowledge learning of complex networks under multi-modal collaboration faster and more accurate, and at the same time by integrating traditional hypergraph learning and deep learning method, a high-order embedding fusion layer is designed to learn knowledge representation within and between modalities, which makes the hypergraph neural network system have more powerful modeling capabilities and improves the ability to classify and predict complex associated data

Images