This DGL example implements the GNN model proposed in the paper Combining Label Propagation and Simple Models Out-performs Graph Neural Networks. For the original implementation, see here.
Contributor: xnuohz
The codebase is implemented in Python 3.7. For version requirement of packages, see below.
dgl 0.6.0.post1
torch 1.7.0
ogb 1.3.0
Open Graph Benchmark(OGB). Dataset summary:
| Dataset | #Nodes | #Edges | #Node Feats | Metric |
|---|---|---|---|---|
| ogbn-arxiv | 169,343 | 1,166,243 | 128 | Accuracy |
| ogbn-products | 2,449,029 | 61,859,140 | 100 | Accuracy |
Training a Base predictor and using Correct&Smooth which follows the original hyperparameters on different datasets.
- MLP + C&S
python main.py --dropout 0.5
python main.py --pretrain --correction-adj DA --smoothing-adj AD --autoscale- Linear + C&S
python main.py --model linear --dropout 0.5 --epochs 1000
python main.py --model linear --pretrain --correction-alpha 0.8 --smoothing-alpha 0.6 --correction-adj AD --autoscale- Linear + C&S
python main.py --dataset ogbn-products --model linear --dropout 0.5 --epochs 1000 --lr 0.1
python main.py --dataset ogbn-products --model linear --pretrain --correction-alpha 1. --smoothing-alpha 0.9| MLP | MLP + C&S | Linear | Linear + C&S | |
|---|---|---|---|---|
| Results(Author) | 55.58 | 68.72 | 51.06 | 70.24 |
| Results(DGL) | 56.55 | 70.93 | 52.48 | 72.60 |
| Linear | Linear + C&S | |
|---|---|---|
| Results(Author) | 47.67 | 82.34 |
| Results(DGL) | 47.65 | 82.86 |
| ogb-arxiv | Time | GPU Memory | Params |
|---|---|---|---|
| Author, Linear + C&S | 6.3 * 10 ^ -3 | 1,248M | 5,160 |
| DGL, Linear + C&S | 5.6 * 10 ^ -3 | 1,252M | 5,160 |