Graph classification method for multi-layer MLP network, medium and equipment

Abstract

The invention discloses a graph classification method for a multi-layer MLP network, a medium and equipment.The method comprises the steps: constructing a graph, and converting a node connection edge of the graph into an adjacent matrix; inputting the minimum batch of feature matrix into an input layer; inputting the minimum batch of representation vectors output by the input layer into a BatchnNormal layer for mean value normalization; multiplying a normalized minimum batch representation vector output by the BatchnNormal layer by the minimum batch adjacency matrix, inputting the product into the middle layer, and outputting a minimum batch representation vector; inputting the output minimum batch representation vector into a BatchNorm layer for normalization, multiplying the normalized representation vector by a minimum batch attention adjacency matrix, and inputting the product into an output layer; establishing a network model and training; and inputting to-be-predicted similar graphs into the trained neural network model, outputting graph labels, and completing a graph classification task. According to the method, different importance is distributed to different nodes in a neighborhood by adopting an attention mechanism according to the characteristics of the nodes, the characteristic vectors are aggregated for multiple times by using MLP, graph labels are better classified, and the classification precision is high.

Description

technical field [0001] The invention belongs to the technical field of computers, and in particular relates to a graph classification method, medium and equipment of a multi-layer MLP network. Background technique [0002] The graph classification method refers to the use of graph structure information and its label influence to train the neural network model, which can use the unknown same graph structure information to predict its label. Tags have different meanings in different fields. For example, tags represent molecular properties in biology and group categories in social networks. The model can classify the labels of the same class of graphs from a large range of homogeneous graphs, and then use this graph-like structure for other practical domain purposes. The current molecular activity prediction technology of graph classification in biology can not only simplify the drug development process, reduce the safety hazards of biological experiments, but also save the co...

AI Technical Summary

Problems solved by technology

[0003] The existing method does not highlight the importance of some nodes when constructing the second adjacency matrix, which destroys the integrity of th

Images