Graph classification method and device

Abstract

The invention provides a graph classification method and device based on a graph neural network technology of sub-graph division and inter-sub-graph pooling. The graph classification method comprisesthe steps of selecting a sub-graph extension center based on the node degree; according to a mode based on breadth-first traversal, obtaining sub-graphs through expansion; training a corresponding graph convolution network, and obtaining an intra-sub-graph feature vector of each sub-graph containing node features and adjacency relation information from the adjacency matrix and the feature matrix of each sub-graph; performing maximum pooling by taking the modulus lengths of the feature vectors in the sub-graphs as metrics, and selecting part of the feature vectors in the sub-graphs as GAT input; training a corresponding GAT, and taking the feature vector in the sub-graph selected by maximum pooling as a node input to obtain a sub-graph feature vector containing information between the sub-graphs; and utilizing a classifier to classify the sub-graph feature vectors to obtain sub-graph categories, and determining the graph categories according to a maximum voting principle. According to the technical scheme, the classification principle has good interpretability and a good classification effect.

Description

technical field [0001] The invention relates to machine learning technology, in particular to a graph classification method and device based on graph neural network technology of subgraph division and subgraph pooling. Background technique [0002] In the field of machine learning (Machine Learning, ML) technology, in order to make the machine understand the knowledge of certain professional fields and many irregular data structures of entities, the form of Graph in Graph Theory (Graph Theory) is often used to Knowledge and / or entities are described, or topological structures, such as social networks, knowledge graphs, chemical molecular structures, etc. In the field of chemistry, graph structures are especially used to describe the composition of compounds. Compared with the data whose processing object is Euclidean space, the characteristics of using graphs to describe knowledge and entities in certain professional fields and use them for analysis are that the node relatio...

AI Technical Summary

Problems solved by technology

[0004] Using the existing technology, the classification of graphs lacks good interpretability, and lacks consideration of certain fields. In the graph structure obtained, there are cases where graph features are determined by specific subgraph structures.

Images