Half-Hop: A graph upsampling approach for slowing down message passing
Half-Hop: A graph upsampling approach for slowing down message passing
复制标题
DOI：
10.48550/arxiv.2308.09198
复制
发表时间：
2023-07
期刊：
影响因子：
--
通讯作者：
Mehdi Azabou;Venkataraman Ganesh;S. Thakoor;Chi-Heng Lin;Lakshmi Sathidevi;Ran Liu;M. Vaĺko;
中科院分区：
文献类型：
--
作者：
Mehdi Azabou;Venkataraman Ganesh;S. Thakoor;Chi-Heng Lin;Lakshmi Sathidevi;Ran Liu;M. Vaĺko;
消息传递神经网络在图结构数据上取得了很大的成功。然而，在许多情况下，当相邻节点属于不同的类时，消息传递可能导致过度平滑或失败。在这项工作中，我们介绍了一个简单而通用的框架，用于改善消息传递神经网络的学习。我们的方法本质上是通过在每个边缘添加“慢节点”来对原始图中的边缘进行上采样，这些节点可以调解源节点和目标节点之间的通信。我们的方法只修改输入图，使其即插即用，易于与现有模型一起使用。为了理解减慢消息传递的好处，我们提供了理论和实证分析。我们报告了几个监督和自我监督基准的结果，并显示了全面的改进，特别是在相邻节点更有可能具有不同标签的异嗜条件下。最后，我们展示了我们的方法如何用于生成自监督学习的增强，其中慢节点被随机引入到图中的不同边缘，以生成具有可变路径长度的多尺度视图。
Message passing neural networks have shown a lot of success on graph-structured data. However, there are many instances where message passing can lead to over-smoothing or fail when neighboring nodes belong to different classes. In this work, we introduce a simple yet general framework for improving learning in message passing neural networks. Our approach essentially upsamples edges in the original graph by adding "slow nodes" at each edge that can mediate communication between a source and a target node. Our method only modifies the input graph, making it plug-and-play and easy to use with existing models. To understand the benefits of slowing down message passing, we provide theoretical and empirical analyses. We report results on several supervised and self-supervised benchmarks, and show improvements across the board, notably in heterophilic conditions where adjacent nodes are more likely to have different labels. Finally, we show how our approach can be used to generate augmentations for self-supervised learning, where slow nodes are randomly introduced into different edges in the graph to generate multi-scale views with variable path lengths.