提升标签对无标签节点的影响，让图卷积网络更有效利用标签信息。
Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks
- 先学习新图结构，让标签信息正向影响预测
- 通过对比学习增强表示能力，提升模型泛化性
- 适合标签稀疏场景下的图神经网络优化
图卷积网络（GCN）的消息传递机制使标签信息能传播到更多无标签邻居，从而提高标签利用率。然而，额外的标签信息并不总能带来正面效果。为此，我们提出一种两阶段框架ELU-GCN。第一阶段，通过图学习构建新图结构（即ELU图），使标签信息正向影响GCN预测；第二阶段，在GCN框架上设计图对比学习，挖掘学习得到的ELU图与原始图之间的一致性与互斥性信息，以提升表示学习效果。此外，我们理论上证明了该方法可保证GCN的泛化能力。大量实验验证了该方法的优越性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。