DeepMCGCN: Multi-channel Deep Graph Neural Networks

Abstract

Graph neural networks (GNNs) have shown powerful capabilities in modeling and representing graph structural data across various graph learning tasks as an emerging deep learning approach. However, most existing GNNs focus on single-relational graphs and fail to fully utilize the rich and diverse relational information present in real-world graph data. In addition, deeper GNNs tend to suffer from overfitting and oversmoothing issues, leading to degraded model performance. To deeply excavate the multi-relational features in graph data and strengthen the modeling and representation abilities of GNNs, this paper proposes a multi-channel deep graph convolutional neural network method called DeepMCGCN. It constructs multiple relational subgraphs and adopts multiple GCN channels to learn the characteristics of different relational subgraphs separately. Cross-channel connections are utilized to obtain interactions between different relational subgraphs, which can learn node embeddings richer and more discriminative than single-channel GNNs. Meanwhile, it alleviates overfitting issues of deep models by optimizing convolution functions and adding residual connections between and within channels. The DeepMCGCN method is evaluated on three real-world datasets, and the experimental results show that its node classification performance outperforms that of single-channel GCN and other benchmark models, which improves the modeling and representation capabilities of the model.

A graph residual generation network for node classification based on multi-information aggregation

“…D2GCN [16] solves the over-smoothing problem by applying residual connection to the two-channel graph convolution neural network and increasing the depth of the two-channel graph convolution neural network. DeepMCGCN [17] uses cross-channel connection to obtain the interaction between sub-graphs of different relationships, and alleviates the over-smoothing problem of depth model by optimizing convolution function and adding residual connection between channels and within channels. Although the above methods improve the GCN based model in various ways to solve the problem of over-smoothing, they do not fully consider the correlation between nearest neighbor information and distant neighbor information, and the lack of certain key information limits the upper limit of their application.…”