提出通道感知的图神经网络，缓解深度模型过平滑问题。
Channel-Attentive Graph Neural Networks
- 按通道自适应选择邻居信息进行消息传递
- 在高异质性图上优于现有基线模型
- 适合处理深层图结构数据的任务
图神经网络（GNN）在图结构数据表示学习中处于领先地位，广泛应用于社交网络、分子结构等场景。多数GNN采用消息传递机制，在多种任务上表现优异。然而，随着模型深度增加，消息传递机制易引发过平滑问题，导致无关节点表示趋于相似，性能下降。本文提出一种自适应通道级消息传递方法，构建了通道感知图神经网络（Channel-Attentive GNN），能够学习如何关注邻居节点及其特征通道，从而在消息传递过程中传输更丰富的信息。在多个主流基准数据集上的实验表明，该模型比基线方法更抗过平滑，在具有强异质性的各类图上均达到领先性能。代码已开源：https://github.com/ALLab-Boun/CHAT-GNN。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) set the state-of-the-art in representation learning for graph-structured data. They are used in many domains, from online social networks to complex molecules. Most GNNs leverage the message-passing paradigm and achieve strong performances on various tasks. However, the message-passing mechanism used in most models suffers from over-smoothing as a GNN's depth increases. The over-smoothing degrades GNN's performance due to the increased similarity between the representations of unrelated nodes. This study proposes an adaptive channel-wise message-passing approach to alleviate the over-smoothing. The proposed model, Channel-Attentive GNN, learns how to attend to neighboring nodes and their feature channels. Thus, much diverse information can be transferred between nodes during message-passing. Experiments with widely used benchmark datasets show that the proposed model is more resistant to over-smoothing than baselines and achieves state-of-the-art performances for various graphs with strong heterophily. Our code is at https://github.com/ALLab-Boun/CHAT-GNN.
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。