Measuring and sampling: A metric‐guided subgraph learning framework for graph neural network
Measuring and sampling: A metric‐guided subgraph learning framework for graph neural network
复制标题
DOI：
10.1002/int.22891
复制
发表时间：
2021-12
影响因子：
7
通讯作者：
Jiyang Bai;Yuxiang Ren;Jiawei Zhang
中科院分区：
文献类型：
--
作者：
Jiyang Bai;Yuxiang Ren;Jiawei Zhang
图神经网络（GNN）在学习强大的节点表示方面表现出令人信服的性能，这些节点表示保留了节点属性和图结构信息。然而，许多GNN在设计有更深的网络结构或处理大型图时会遇到有效性和效率方面的问题。已经提出了几种采样算法来改进和加速GNN的训练，但它们忽略了理解GNN性能增益的来源。图数据中信息的测量可以帮助采样算法在去除冗余信息甚至噪声的同时保持高价值信息。在本文中，我们提出了一个用于GNN的度量引导（MeGuide）子图学习框架。MeGuide采用了两个新的指标：特征平滑度和连接失败距离来指导子图采样和基于小批量的训练。特征平滑度用于分析节点的特征以保留最有价值的信息，而连接失败距离用于度量结构信息以控制子图的大小。我们证明了MeGuide在多个数据集上训练各种GNN的有效性和效率。
Graph neural networks (GNNs) have shown convincing performance in learning powerful node representations that preserve both node attributes and graph structural information. However, many GNNs encounter problems in effectiveness and efficiency when they are designed with a deeper network structure or handle large‐sized graphs. Several sampling algorithms have been proposed for improving and accelerating the training of GNNs, yet they ignore understanding the source of GNNs performance gain. The measurement of information within graph data can help the sampling algorithms to keep high‐value information while removing redundant information and even noise. In this paper, we propose a Metric‐Guided (MeGuide) subgraph learning framework for GNNs. MeGuide employs two novel metrics: Feature Smoothness and Connection Failure Distance to guide the subgraph sampling and mini‐batch based training. Feature Smoothness is designed for analyzing the feature of nodes to retain the most valuable information, while Connection Failure Distance can measure the structural information to control the size of subgraphs. We demonstrate the effectiveness and efficiency of MeGuide in training various GNNs on multiple data sets.