通过随机游走学习图上的长程依赖
Learning Long Range Dependencies on Graphs via Random Walks
AI总结：
针对消息传递GNN长程依赖捕捉弱、图Transformer易简化图结构的问题，提出结合随机游走长程信息与局部消息传递的NeuralWalker框架，在19个基准数据集上实现显著性能提升。
摘要：
消息传递图神经网络（GNNs）擅长捕捉局部关系，但难以处理图中的长程依赖问题。相比之下，图Transformer（GTs）能够实现全局信息交换，但通常将图表示为固定长度向量的集合，过度简化了图结构。本研究提出了一种新型架构，将随机游走的长程信息与局部消息传递相结合，克服了上述两种方法的缺陷。该架构将随机游走视为序列，利用序列模型的最新进展有效捕捉这些游走路径中的长程依赖。基于这一理念，我们提出的框架具备三大特性：（1）通过随机游走序列获得表达能力更强的图表示；（2）能够使用任意序列模型捕捉长程依赖；（3）可灵活集成各类GNN和GT架构。实验评估表明，我们的方法在19个图和节点基准数据集上实现了显著的性能提升，在PascalVoc-SP和COCO-SP数据集上的表现尤为突出，较现有方法最高提升13%。代码可在https://github.com/BorgwardtLab/NeuralWalker获取。
英文摘要：
Message-passing graph neural networks (GNNs) excel at capturing local relationships but struggle with long-range dependencies in graphs. In contrast, graph transformers (GTs) enable global information exchange but often oversimplify the graph structure by representing graphs as sets of fixed-length vectors. This work introduces a novel architecture that overcomes the shortcomings of both approaches by combining the long-range information of random walks with local message passing. By treating random walks as sequences, our architecture leverages recent advances in sequence models to effectively capture long-range dependencies within these walks. Based on this concept, we propose a framework that offers (1) more expressive graph representations through random walk sequences, (2) the ability to utilize any sequence model for capturing long-range dependencies, and (3) the flexibility by integrating various GNN and GT architectures. Our experimental evaluations demonstrate that our approach achieves significant performance improvements on 19 graph and node benchmark datasets, notably outperforming existing methods by up to 13\% on the PascalVoc-SP and COCO-SP datasets. The code is available at https://github.com/BorgwardtLab/NeuralWalker.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
