Representation Learning of Reconstructed Graphs Using Random Walk Graph Convolutional Network
This work offers an incremental improvement in graph representation learning for researchers and practitioners working with graph neural networks, particularly in tasks like node classification and link prediction, by incorporating higher-order structural information.
This paper addresses the limitation of existing graph representation learning methods that primarily focus on microstructures by proposing wGCN, a novel framework that uses random walks to capture node-specific mesoscopic structures. This approach reconstructs the graph and organizes characteristic node information, effectively generating node embeddings for unseen data, outperforming baseline methods on citation and social networks.
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.