Residual Network and Embedding Usage: New Tricks of Node Classification with Graph Convolutional Networks

05/18/2021 ∙ by Huixuan Chi, et al. ∙ 0

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 https://github.com/ytchx1999/PyG-OGB-Tricks.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

Code Repositories

PyG-OGB-Tricks

Bags of Tricks in OGB (node classification) with GCNs.


view repo

GCN_res-CS-v2

This is an improvement of the GCN_res model, using the C&S method. This is the v2 version.


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.