Network representation learning method based on meta-structure and graph neural network

Abstract

The invention provides a network representation learning method based on a meta-structure and a graph neural network. According to the method, the information of the neighbor nodes is aggregated through the graph neural network and the weighted attention mechanism, the candidate meta-structure set is generated through the hierarchical search algorithm, meta-structures do not need to be defined inadvance, and compared with a previous meta-path, the method can consider more complex structure information between the nodes. According to the method, the strong learning ability of the graph neuralnetwork and the rich semantics of the meta-structure are fused, and the problems that an existing meta-path-based method is single in consideration structure and needs to depend on experience to specify the meta-structure are effectively solved. Moreover, the introduction of a weighted attention mechanism can explicitly consider the quantity information in the meta-structure. And a final node which is more accurate than a result of a traditional representation classification mode is generated, and the final node can be used as vector representation to be used in subsequent other machine learning figures.

Description

technical field [0001] The invention belongs to the technical field of big data, and in particular relates to a network representation learning method based on a meta structure and a graph neural network. Background technique [0002] Networks exist widely in the real world, and in many real-world scenarios, objects and connections between objects can be modeled and represented through networks or graphs. Many research works focus on the representation learning of nodes in networks or graphs, which represent the nodes contained in complex and irregular graphs as vectors of equal length and low dimensionality, and applying vectors to subsequent machine learning tasks can express It can produce better results, such as node classification, node clustering, anomaly detection and link prediction, etc. A type of network that has received widespread attention is called a heterogeneous information network (Heterogeneous Information Network, HIN), such as a common citation network. ...

AI Technical Summary

Problems solved by technology

[0003] However, most of the current graph neural networks and attention mechanisms rely on pre-defined meta-paths, and pre-definition requires background knowledge or understanding of the dataset to pre-define the meta-path, which increases the operational difficulty of the mechanism. , while the meta-path representation also has the disadvantage of being too single

Images