Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks
This work addresses a specific problem in graph neural networks for researchers, but it appears incremental as it builds on existing GCN methods.
The paper tackles the issue that additional label information in Graph Convolutional Networks (GCNs) does not always improve performance, proposing a two-step framework called ELU-GCN that learns a new graph structure and uses graph contrastive learning to enhance label influence, with extensive experiments validating its superiority.
The message-passing mechanism of graph convolutional networks (i.e., GCNs) enables label information to reach more unlabeled neighbors, thereby increasing the utilization of labels. However, the additional label information does not always contribute positively to the GCN. To address this issue, we propose a new two-step framework called ELU-GCN. In the first stage, ELU-GCN conducts graph learning to learn a new graph structure (i.e., ELU-graph), which allows the additional label information to positively influence the predictions of GCN. In the second stage, we design a new graph contrastive learning on the GCN framework for representation learning by exploring the consistency and mutually exclusive information between the learned ELU graph and the original graph. Moreover, we theoretically demonstrate that the proposed method can ensure the generalization ability of GCNs. Extensive experiments validate the superiority of our method.