Home

Awesome

gtrick: Bag of Tricks for Graph Neural Networks.

gtrick is an easy-to-use Python package that collects tricks for graph neural networks. It tests and provides powerful tricks to boost your models' performance.

Trick is all you need! (English Document | 中文介绍)

Library Highlights

Installation

Note: This is a developmental release.

pip install gtrick

Quick Start

It is very easy to get started with gtrick. You can enhance your GNN model with only a few lines of code.

quickstart

For more detailed examples, see Example in Trick.

Trick

TrickExampleTaskReference
VirtualNodeDGL<br>PyGgraphOGB Graph Property Prediction Examples
FLAGDGL<br>PyGnode*<br>graphRobust Optimization as Data Augmentation for Large-scale Graphs
FingerprintDGL<br>PyGmolecular graph*Extended-Connectivity Fingerprints
Random FeatureDGL<br>PyGgraph*Random Features Strengthen Graph Neural Networks
Label PropagationDGL<br>PyGnode*Learning from Labeled and Unlabeled Data with Label Propagation
Correct & SmoothDGL<br>PyGnode*Combining Label Propagation And Simple Models Out-performs Graph Neural Networks
Common NeighborsDGL<br>PyGlink*Link Prediction with Structural Information
Resource AllocationDGL<br>PyGlink*Link Prediction with Structural Information
Adamic AdarDGL<br>PyGlink*Link Prediction with Structural Information
Anchor DistanceDGL<br>PyGlink*Link Prediction with Structural Information

We have tested all these tricks on selected datasets, you can find the benchmark in PyG Benchmark and DGL Benchmark.

For the ogbg-molhiv GIN, please refer to @willy-b's code.

Contributing

Please let me know if you encounter a bug or have any suggestions by filing an issue.

All contributions for bug fixes, new tricks, and better examples are welcome.

There are also some tricks I'm planning to add, feel free to implement one of them for gtrick: