Introduction

DIG includes unified implementations of data interfaces, common algorithms, and evaluation metrics for several advanced tasks. Our goal is to enable researchers to easily implement and benchmark algorithms. Currently, we consider the following research directions.

• Graph Augmentation: dig.auggraph

• Graph Generation: dig.ggraph

• Self-supervised Learning on Graphs: dig.sslgraph

• Explainability of Graph Neural Networks: dig.xgraph

• Deep Learning on 3D Graphs: dig.threedgraph

• Fair Graph Representations: dig.fairgraph

We provide a hands-on tutorial for each direction to help you to get started with DIG:

• Tutorial for Graph Generation

• Tutorial for Self-supervised Learning on Graphs

• Tutorial for Explainability of Graph Neural Networks

• Tutorial for Deep Learning on 3D Graphs

• Tutorial for Learning Fair Graph Representations

You can also refer to our provided examples about how to use APIs in DIG.