Graph classification method of cyclic neural network model based on Attention

Abstract

The invention discloses a graph classification method of a cyclic neural network model based on Attention. The Attension idea is applied in the graph classification problem, and the graph classification problem is regarded as a decision process of interaction between a machine and a graph environment in reinforcement learning. Based on the Attention idea, the machine preferentially observes the target area of the graph classification task instead of directly processing the whole graph, so that the target area can be preferentially processed by ignoring the nodes irrelevant to the classification task, and the visual angle movement direction of the machine observation graph can be trained and determined by reinforcement learning rules. At the same time, the model can control the parameters and computational load, and get rid of the constraint on the size of graph data. The invention constructs a cyclic neural network, which integrates the local information of the graph observed before bythe machine through the hidden layer of the circulating neural network, and is used for assisting the decision of the angle of view movement and the graph classification. The invention avoids the problem of subgraph isomorphism in frequent subgraph mining and the problem that the graph kernel function method lacks scalability.

Description

technical field [0001] The invention belongs to the field of graph mining, and in particular relates to a graph classification method based on an Attention-based cyclic neural network model. Background technique [0002] A graph in graph theory is a graph composed of a number of given points and a line connecting two points. This graph is usually used to describe a certain relationship between certain things. Points represent things, and points connect two points. The line of represents that there is a certain relationship between the corresponding two things. The graph G in graph theory is an ordered pair (V, E), where V is called the vertex set, which is the set of all vertices in the graph, and E is called the edge set, which is the set of edges between all vertices. gather. Simply put, vertices represent things, and edges represent relationships between things. [0003] As a commonly used data structure, graph can accurately model the key characteristics and complex r...

AI Technical Summary

Problems solved by technology

The size of the subgraph depends on the support threshold setting when mining frequent subgraphs. When the support threshold is set too high, only a small number of extremely frequent subgraphs can be generated, resulting in the loss of effective patterns with high discrimination and affecting the performance of the classifier. When low, it will lead to low efficiency of frequent subgraph mining algorithm

At the same time, a large number of isomorphism detections are required in frequent subgraph mining, and the subgraph isomorphism problem is a classic NP (Non-deterministic Polynomial) complete problem with high computational complexity

The convolutional neural network is constrained by the size of the graph data, lacks adaptability to graphs of different sizes, and can only learn part of the information in the graph while losing complex subgraph features

In addition, the physical meaning of the convolution operation is not clear. For the graph classification problem, we cannot explain the specific meaning of the features extracted by the convolution layer.

Images