论文标题
波纹步行训练：大图神经网络的基于子图的培训框架
Ripple Walk Training: A Subgraph-based training framework for Large and Deep Graph Neural Network
论文作者
论文摘要
图形神经网络（GNN）在学习图形结构数据和各种任务方面取得了出色的表现。但是，许多当前的GNN在面对大型图表或使用更深层次结构时遇到了三个常见问题：邻居爆炸，节点依赖性和过度厚度。此类问题归因于图本身的数据结构或多层GNNS框架的设计，并且可以提高训练效率低下和高空间复杂性。为了解决这些问题，在本文中，我们提出了一个基于子图的一般培训框架，即连续训练（RWT），用于深度和大图神经网络。 RWT样品从完整图中的子图构成了一个迷你批次，并且根据迷你批处理梯度更新了完整的GNN。我们分析以理论方式训练GNN的高质量子图。一种新型的采样方法纹波步行采样器可用于对这些高质量的子图进行采样以构成迷你批次，该批量考虑了图形结构数据的随机性和连接性。对不同尺寸图的广泛实验证明了RWT在训练各种GNN（GCN＆GAT）中的有效性和效率。
Graph neural networks (GNNs) have achieved outstanding performance in learning graph-structured data and various tasks. However, many current GNNs suffer from three common problems when facing large-size graphs or using a deeper structure: neighbors explosion, node dependence, and oversmoothing. Such problems attribute to the data structures of the graph itself or the designing of the multi-layers GNNs framework, and can lead to low training efficiency and high space complexity. To deal with these problems, in this paper, we propose a general subgraph-based training framework, namely Ripple Walk Training (RWT), for deep and large graph neural networks. RWT samples subgraphs from the full graph to constitute a mini-batch, and the full GNN is updated based on the mini-batch gradient. We analyze the high-quality subgraphs to train GNNs in a theoretical way. A novel sampling method Ripple Walk Sampler works for sampling these high-quality subgraphs to constitute the mini-batch, which considers both the randomness and connectivity of the graph-structured data. Extensive experiments on different sizes of graphs demonstrate the effectiveness and efficiency of RWT in training various GNNs (GCN & GAT).
