DIG: A Turnkey Library for Diving into Graph Deep Learning Research

TL;DR

DIG is an open-source, comprehensive library designed to streamline research in advanced graph deep learning tasks by providing unified implementations, datasets, and evaluation tools for researchers.

Contribution

The paper introduces DIG, a versatile library that simplifies implementing and benchmarking complex graph deep learning research tasks.

Findings

Provides unified data interfaces and algorithms for multiple graph tasks

Enables easy comparison with baseline methods using standard datasets

Supports research on graph generation, self-supervised learning, explainability, and 3D graphs

Abstract

Although there exist several libraries for deep learning on graphs, they are aiming at implementing basic operations for graph deep learning. In the research community, implementing and benchmarking various advanced tasks are still painful and time-consuming with existing libraries. To facilitate graph deep learning research, we introduce DIG: Dive into Graphs, a turnkey library that provides a unified testbed for higher level, research-oriented graph deep learning tasks. Currently, we consider graph generation, self-supervised learning on graphs, explainability of graph neural networks, and deep learning on 3D graphs. For each direction, we provide unified implementations of data interfaces, common algorithms, and evaluation metrics. Altogether, DIG is an extensible, open-source, and turnkey library for researchers to develop new methods and effortlessly compare with common baselines using widely used datasets and evaluation metrics. Source code is available at https://github.com/divelab/DIG.