Graph classification method and system fusing high-order structure embedding and composite pooling

Abstract

The invention belongs to the technical field of artificial intelligence graph classification, and provides a graph classification method and system fusing high-order structure embedding and composite pooling, and the method comprises the steps: obtaining a to-be-classified graph; inputting a to-be-classified graph into the graph neural network to obtain a category to which the graph belongs; wherein for each sub-graph set of the graph, each convolutional layer calculates the feature of each sub-graph based on the sub-graph set output by the previous neural network layer, each composite pooling layer updates the sub-graph set based on the feature of each sub-graph output by the convolutional layer, and meanwhile, for each sub-graph in the updated sub-graph set, the feature of each composite pooling layer is calculated based on the feature of each sub-graph output by the convolutional layer. The features of the sub-graphs in the local neighborhood are fused through an attention mechanism, and the features of the sub-graphs are updated; and obtaining a graph representation vector by the reading layer, and inputting the graph representation vector into the classifier to obtain a category to which the graph belongs. A high-order structure is utilized, messages are directly transmitted among the sub-graphs, structural information invisible in node level is captured, and the classification precision of the graphs is improved.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence graph classification, and in particular relates to a graph classification method and system integrating high-order structure embedding and compound pooling. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] In real life, many real-world data can be naturally represented by graphs. From biological and chemical informatics to social network analysis, graph-structured data is ubiquitous in application fields, and graph classification is one of the important applications. Briefly, given a dataset of graphs of the form (G, y), where G represents a graph and y is its class, the goal of the graph classification task is to use the given graph structure and node features to predict the The label associated with the graph. Many real graphs have typical loc...

AI Technical Summary

Problems solved by technology

[0004] (1) Existing models only use the information of vertices and edges in the graph for classification, lacking attention to high-order graph structure information, while in practical applications interactions may occur in groups of three or more nodes, they cannot Simply described as a pairwise relationship between entities, but can be decomposed and expressed as a higher-order structure at different levels, for example, figure 2 The high-order structure and node characteristics play an important role in the actor's social network graph. The yellow, green and blue dotted boxes represent the second-order subgraph, third-order subgraph and fourth-order subgraph respectively, and the existing models cannot express this complex relationship.

[0005] (2) Most of the existing models lack a hierarchical structure. The naturally formed graph structure itself is formed from a single node through interrelationships, which contains a large number of structural semantics. Learning the representation of graphs in a hierarchical manner is very important for capturing the existence of graphs. Local structure is very important

However, in the existing model, the graph pooling method is single, and the subgraphs that do not participate in the graph pooling are directly discarded during the topology generation process, resulting in the loss of graph feature information; and still only focus on the node level without considering higher-order structural information ; and did not explicitly consider both graph topology and node feature representation when generating the pooling graph topology

Images