Representation Learning of Reconstructed Graphs Using Random Walk Graph Convolutional Network

TL;DR

This paper introduces wGCN, a graph neural network framework that leverages random walks to capture high-order local structures, improving node embedding quality and generalization in graph learning tasks.

Contribution

The paper proposes a novel method that incorporates mesoscopic structures via random walks to enhance graph representation learning and node embeddings.

Findings

Outperforms baseline methods on citation and social networks

Effectively generates embeddings for unseen data

Improves learning efficiency of graph neural networks

Abstract

Graphs are often used to organize data because of their simple topological structure, and therefore play a key role in machine learning. And it turns out that the low-dimensional embedded representation obtained by graph representation learning are extremely useful in various typical tasks, such as node classification, content recommendation and link prediction. However, the existing methods mostly start from the microstructure (i.e., the edges) in the graph, ignoring the mesoscopic structure (high-order local structure). Here, we propose wGCN -- a novel framework that utilizes random walk to obtain the node-specific mesoscopic structures of the graph, and utilizes these mesoscopic structures to reconstruct the graph And organize the characteristic information of the nodes. Our method can effectively generate node embeddings for previously unseen data, which has been proven in a series of experiments conducted on citation networks and social networks (our method has advantages over baseline methods). We believe that combining high-order local structural information can more efficiently explore the potential of the network, which will greatly improve the learning efficiency of graph neural network and promote the establishment of new learning models.