Research On Network Representation Learning Algorithm Based On Subgraph Convolution Auto-Encoder

In the real world,data are usually organized into graphs,which are widely used in various fields,such as urban transportation network,power network and etc.The graph data contains a wealth of information,and the effective analysis and application of graph data is becoming more and more significant.Therefore,using network representation learning technology to process graph data has become a research hotspot.Network representation learning(NRL)aims to map vertices of a graph into a low-dimensional space which preserves the network structure and its inherent properties.Most existing methods for network representation adopt shallow models which have relatively limited capacity to capture highly non-linear network structures,resulting in sub-optimal network representations.Therefore,it is nontrivial to explore how to effectively capture highly non-linear network structure and preserve the global and local structure in NRL.To solve this problem,in this paper we propose a new graph convolutional auto-encoder architecture based on a depth-based representation of graph structure,referred to as the depth-based subgraph convolutional auto-encoder(DS-CAE),which integrates both the global topological,local connectivity structures and the node's own feature information within a graph.Our idea is to first decompose a graph into a family of K-layer expansion subgraphs rooted at each vertex aimed at better capturing long-range vertex interdependencies.Then a set of convolution filters slide over the entire sets of subgraphs of a vertex to extract the local connectivity structural information.This is analogous to the standard convolution operation on European data.In contrast to most existing models for unsupervised learning on graph-structured data,our model can capture highly non-linear structure by simultaneously integrating node features and network structure into network representation learning.Experimental results show that this algorithm has strong representation learning ability,significantly improves the prediction performance on a number of benchmark datasets and has a good visual performance.