arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.10619cs.LG
收藏

节点分类任务中图神经网络公平比较的流水线

A pipeline for fair comparison of graph neural networks in node classification tasks

Zhejiang University of Technology(浙江工业大学);Zhejiang Institute of Mechanical & Electrical Engineering(浙江机电职业技术学院);University of Portsmouth(朴茨茅斯大学)

Wentao Zhao, Dalin Zhou, Xinguo Qiu, Wei Jiang

摘要:

已经研究了图神经网络(GNN)在采用图数据的多个领域中的潜在适用性。然而,没有标准的训练设置来确保新方法之间的公平比较,包括不同的模型架构和数据增强技术。我们引入了一个标准的,可重复的基准,相同的训练设置可以应用于节点分类。对于这个基准测试,我们构建了9个数据集,包括来自不同领域的中小规模数据集和7个不同的模型。我们为小数据集设计了一个k倍模型评估策略,为所有数据集设计了一套标准的模型训练程序,为GNN提供了一个标准的实验管道,以帮助确保公平的模型架构比较。我们使用node2vec和拉普拉斯特征向量来执行数据增强,以研究输入特征如何影响模型的性能。我们发现拓扑信息是重要的节点分类任务。增加模型层的数量不会提高性能,但在PATTERN和CLUSTER数据集上除外,在这两个数据集中,图形是不连接的。数据增强非常有用,特别是在基线中使用node2vec,可以显著提高基线性能。

英文摘要:

Graph neural networks (GNNs) have been investigated for potential applicability in multiple fields that employ graph data. However, there are no standard training settings to ensure fair comparisons among new methods, including different model architectures and data augmentation techniques. We introduce a standard, reproducible benchmark to which the same training settings can be applied for node classification. For this benchmark, we constructed 9 datasets, including both small- and medium-scale datasets from different fields, and 7 different models. We design a k-fold model assessment strategy for small datasets and a standard set of model training procedures for all datasets, enabling a standard experimental pipeline for GNNs to help ensure fair model architecture comparisons. We use node2vec and Laplacian eigenvectors to perform data augmentation to investigate how input features affect the performance of the models. We find topological information is important for node classification tasks. Increasing the number of model layers does not improve the performance except on the PATTERN and CLUSTER datasets, in which the graphs are not connected. Data augmentation is highly useful, especially using node2vec in the baseline, resulting in a substantial baseline performance improvement.

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。

↑