Residual Network and Embedding Usage: New Tricks of Node Classification with Graph Convolutional Networks
arXiv:2105.08330 · doi:10.1088/1742-6596/2171/1/012011
Abstract
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.
This work is still working in process. (14 pages, 6 figures)
References in corpus (12)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Semi-Supervised Classification with Graph Convolutional Networks
- Towards Deeper Graph Neural Networks
- FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
- Simple and Deep Graph Convolutional Networks
- DeeperGCN: All You Need to Train Deeper GCNs
- SIGN: Scalable Inception Graph Neural Networks
- GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
- Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
- Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification
- Bag of Tricks for Node Classification with Graph Neural Networks
- Understanding and Resolving Performance Degradation in Graph Convolutional Networks