让每个节点自己决定消息传递次数，提升图神经网络性能
ADMP-GNN: Adaptive Depth Message Passing GNN
- 根据节点特性动态调整消息传递层数，而非统一固定
- 在节点分类任务中优于传统GNN模型，提升明显
- 适用于所有基于消息传递的图神经网络架构
图神经网络（GNN）在各类图学习任务中表现优异，其核心特征是为图中所有节点使用固定数量的消息传递步骤，而忽视了节点间多样化的计算需求与特性。通过真实世界数据的实证分析，我们发现不同特性的节点其最优消息传递层数存在差异；该结论在合成数据集上的实验中也得到验证。为此，本文提出自适应深度消息传递图神经网络（ADMP-GNN），一种新型框架，可动态为每个节点调整消息传递层数，从而提升性能。该方法适用于任何遵循消息传递范式的模型。我们在节点分类任务上评估了ADMP-GNN，结果表明其显著优于基线GNN模型。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have proven to be highly effective in various graph learning tasks. A key characteristic of GNNs is their use of a fixed number of message-passing steps for all nodes in the graph, regardless of each node's diverse computational needs and characteristics. Through empirical real-world data analysis, we demonstrate that the optimal number of message-passing layers varies for nodes with different characteristics. This finding is further supported by experiments conducted on synthetic datasets. To address this, we propose Adaptive Depth Message Passing GNN (ADMP-GNN), a novel framework that dynamically adjusts the number of message passing layers for each node, resulting in improved performance. This approach applies to any model that follows the message passing scheme. We evaluate ADMP-GNN on the node classification task and observe performance improvements over baseline GNN models.
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。