Efficient computation of node proximity queries such as transition probabilities, Personalized PageRank, and Katz are of fundamental importance in various graph mining and learning tasks. In particular, several recent works leverage fast node proximity computation to improve the scalability of Graph Neural Networks (GNN). However, prior studies on proximity computation and GNN feature propagation are on a case-by-case basis, with each paper focusing on a particular proximity measure. In this paper, we propose Approximate Graph Propagation (AGP), a unified randomized algorithm that computes various proximity queries and GNN feature propagation, including transition probabilities, Personalized PageRank, heat kernel PageRank, Katz, SGC, GDC, and APPNP. Our algorithm provides a theoretical bounded error guarantee and runs in almost optimal time complexity. We conduct an extensive experimental study to demonstrate AGP's effectiveness in two concrete applications: local clustering with heat kernel PageRank and node classification with GNNs. Most notably, we present an empirical study on a billion-edge graph Papers100M, the largest publicly available GNN dataset so far. The results show that AGP can significantly improve various existing GNN models' scalability without sacrificing prediction accuracy.
翻译:在各种图表采矿和学习任务中,高效计算节点近距离询问,如过渡概率、个性化PageRank和Katz等,具有至关重要的意义。特别是,最近一些工程利用快速节点近距离计算,以提高图形神经网络(GNN)的可缩缩缩性。然而,先前关于近距离计算和GNN特征传播的研究是在个案基础上进行的,每份文件都侧重于特定的近距离测量。在本文中,我们提议采用一个统一的随机算法,计算各种近距离查询和GNN特征传播,包括过渡概率、个性化PealRank、热内尔PageRank、Katz、SG、GDC和APPNP。我们的算法提供了理论约束性误差保证,而且几乎是最佳的复杂时间。我们进行了广泛的实验研究,以在两种具体应用中显示AGPA的效果:用热内子PageRank进行本地组合和与GNNN的节点分类。最显著的是,我们介绍了关于10亿个远的GGGPPPP100M的实证研究,最大的现有GNNS的精确性能展示了现有的各种数据。