gtrick 0.0.dev1

Bag of Tricks for Graph Neural Networks

gtrick: Bag of Tricks for Graph Neural Networks

Trick is all you need.

Trick

Trick	Example	Task	Reference
Virtual Node	DGL PyG	graph	Neural Message Passing for Quantum Chemistry
FLAG	DGL PyG	node* graph	Robust Optimization as Data Augmentation for Large-scale Graphs

Benchmark

The results listed below are implemented by PyG. You can find the results of DGL in DGL Benchmark.

Graph Property Prediction: ogbg-molhiv

Trick	GCN	GIN
—	0.7690 ± 0.0053	0.7778 ± 0.0130
+Virtual Node	0.7581 ± 0.0135	0.7713 ± 0.0036
+FLAG	0.7627 ± 0.0124	0.7764 ± 0.0083

Node Property Prediction: ogbn-arxiv

Trick	GCN	SAGE
—	0.7152 ± 0.0024	0.7153 ± 0.0028
+FLAG	0.7187 ± 0.0020	0.7206 ± 0.0013