残余网络和嵌入使用:图变网络的节点分类新伎俩 (Residual Network and Embedding Usage: New Tricks of Node Classification with Graph Convolutional Networks)

Graph Convolutional Networks (GCNs) and subsequent variants have been proposed to solve tasks on graphs, especially node classification tasks. In the literature, however, most tricks or techniques are either briefly mentioned as implementation details or only visible in source code. In this paper, we first summarize some existing effective tricks used in GCNs mini-batch training. Based on this, two novel tricks named GCN_res Framework and Embedding Usage are proposed by leveraging residual network and pre-trained embedding to improve baseline's test accuracy in different datasets. Experiments on Open Graph Benchmark (OGB) show that, by combining these techniques, the test accuracy of various GCNs increases by 1.21%~2.84%. We open source our implementation at https://github.com/ytchx1999/PyG-OGB-Tricks.

翻译：为了解决图表上的任务,特别是节点分类任务,提出了革命网络(GCN)和随后的变体,但在文献中,大多数技巧或技巧要么被简单提及为执行细节,要么只在源代码中可以看到。在本文中,我们首先总结了在GCN小型批次培训中使用的一些有效技巧。在此基础上,通过利用剩余网络和预先训练的嵌入来提高不同数据集中基准的测试准确性,提出了两个叫GCN_res框架和嵌入使用的新技巧。关于开放图表基准的实验表明,通过将这些技术结合起来,各种GCN的测试准确性增加了1.21 ⁇ 2.84%。我们在https://github.com/ytchx1999/PyG-OGB-Tricks网站打开了我们的执行源。