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 Generation: dig.ggraph

• Self-supervised Learning on Graphs: dig.sslgraph

• Explainability of Graph Neural Networks: dig.xgraph

• Deep Learning on 3D Graphs: dig.threedgraph

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

You can also refer to benchmark implementations as examples to use APIs provided in DIG.