Loading patent…
AssigneeZhejiang University
InventorsJianwei Yin, Zhiling Luo, Zhaohui Wu, Shuiguang Deng, Ying Li, Jian Wu
Estimating the term…
A method and system of graph feature extraction and graph classification based on adjacency matrix is provided. The invention first concentrates the connection information elements in the adjacency matrix into a specific diagonal region of the adjacency matrix which reduces the non-connection information elements in advance. Then the subgraph structure of the graph is further extracted along the diagonal direction using the filter matrix. Further, it uses a stacked convolutional neural network to extract a larger subgraph structure. On one hand, it greatly reduces the amount of computation and complexity, getting rid of the limitations caused by computational complexity and window size. On the other hand, it can capture large subgraph structure through a small window, as well as deep features from the implicit correlation structures at both vertex and edge level, which improves speed and accuracy of graph classification.
A graph feature extraction system based on adjacency matrix in a computer environment, wherein the graph feature extraction system extracts features of a graph based on adjacency matrix of the graph, wherein the features correspond to subgraphs structures which directly support classification;
A graph feature extraction method based on adjacency matrix in a computer environment, wherein the method extracts features of a graph based on the adjacency matrix of the graph, and the features which correspond to subgraph structures directly support the classification, and the features are presented in a form of at least one vector, and each vector corresponds to a distribution of a mixed state in the graph;
Dependencies are inferred from the claim text.