用贝叶斯方法自适应确定图神经网络的邻居范围，提升性能与可靠性。
Bayesian Neighborhood Adaptation for Graph Neural Networks
- 将邻居范围建模为贝叶斯随机过程，同步优化聚合范围与模型参数。
- 在同质与异质图上均实现优于或相当的节点分类准确率。
- 可适配主流GNN结构，提供更可靠的预测置信度，适合实际部署。
图神经网络（GNN）在刻画节点统计特性时依赖的邻域范围（即跳数）对其性能至关重要。现有两阶段方法需对预设的多个邻域范围逐一训练验证，耗时且易受搜索空间设计偏差影响。如何自适应地为同质与异质图确定合适的聚合邻域范围仍待解决。本文提出将GNN的消息传递行为建模为随机过程，将跳数视为贝塔过程。该贝叶斯框架可在优化GNN参数的同时推断最合理的邻域范围。理论分析表明，该范围推断提升了GNN的表达能力。在基准同质与异质数据集上的实验显示，该方法兼容主流GNN变体，在节点分类任务中表现竞争或更优，并提供校准良好的预测结果。代码已开源：https://github.com/paribeshregmi/BNA-GNN。
原文摘要 · Abstract (English)
The neighborhood scope (i.e., number of hops) where graph neural networks (GNNs) aggregate information to characterize a node's statistical property is critical to GNNs' performance. Two-stage approaches, training and validating GNNs for every pre-specified neighborhood scope to search for the best setting, is a time-consuming task and tends to be biased due to the search space design. How to adaptively determine proper neighborhood scopes for the aggregation process for both homophilic and heterophilic graphs remains largely unexplored. We thus propose to model the GNNs' message-passing behavior on a graph as a stochastic process by treating the number of hops as a beta process. This Bayesian framework allows us to infer the most plausible neighborhood scope for message aggregation simultaneously with the optimization of GNN parameters. Our theoretical analysis shows that the scope inference improves the expressivity of a GNN. Experiments on benchmark homophilic and heterophilic datasets show that the proposed method is compatible with state-of-the-art GNN variants, achieving competitive or superior performance on the node classification task, and providing well-calibrated predictions. Implementation is available at : https://github.com/paribeshregmi/BNA-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。