Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A library for graph deep learning research
| Date | Stars |
|---|---|
| 2026-07-31 | 2005 |
| 2026-08-06 | 2005 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center">
<img src="https://github.com/divelab/DIG/blob/main/imgs/DIG-logo.jpg" width="500" class="center" alt="logo"/>
<br/>
</p>
[pypi-image]:https://badge.fury.io/py/dive-into-graphs.svg
[pypi-url]:https://pypi.org/project/dive-into-graphs/
[docs-image]: https://readthedocs.org/projects/diveintographs/badge/?version=latest
[docs-url]: https://diveintographs.readthedocs.io/en/latest/?badge=latest
[license-image]:https://img.shields.io/badge/license-GPL3.0-green.svg
[license-url]:https://github.com/divelab/DIG/blob/main/LICENSE
[contributor-image]:https://img.shields.io/github/contributors/divelab/DIG
[contributor-url]:https://github.com/divelab/DIG/graphs/contributors
[contributing-image]:https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat
[contributing-url]:https://diveintographs.readthedocs.io/en/latest/contribution/instruction.html
[![PyPI Version][pypi-image]][pypi-url]
[![Docs Status][docs-image]][docs-url]
[](https://travis-ci.com/divelab/DIG)
[](https://codecov.io/gh/divelab/DIG)
[![Contributing][contributing-image]][contributing-url]
[![License][license-image]][license-url]
[](https://pepy.tech/project/dive-into-graphs)
<!--- [![Contributors][contributor-image]][contributor-url] -->
**[Documentation](https://diveintographs.readthedocs.io)** | **[Paper [JMLR]](https://www.jmlr.org/papers/v22/21-0343.html)** | **[Tutorials](https://diveintographs.readthedocs.io/en/latest/tutorials/graphdf.html#)** | **[Benchmarks](https://github.com/divelab/DIG/tree/dig-stable/benchmarks)** | **[Examples](https://github.com/divelab/DIG/tree/dig-stable/examples)** | **[Colab Demo](https://colab.research.google.com/drive/1eM1vcjcMLbT9om15Env8F-s265GSm4qI?usp=sharing)** | **[slack community:fire:](https://join.slack.com/t/dive-into-graphs/shared_invite/zt-1i9kn731c-RhLA1zcEGHXbIToxdVqo0g)**
*DIG: Dive into Graphs* is a turnkey library for graph deep learning research.
:fire:**Update (2022/07): We have upgraded our DIG library based on PyG 2.0.0. We recommend installing our latest version.**
## Why DIG?
The key difference with current graph deep learning libraries, such as PyTorch Geometric (PyG) and Deep Graph Library (DGL), is that, while PyG and DGL support basic graph deep learning operations, DIG provides a unified testbed for higher-level, research-oriented graph deep learning tasks, such as graph generation, self-supervised learning, explainability, 3D graphs, and graph out-of-distribution.
If you are working or plan to work on research in graph deep learning, DIG enables you to develop your own methods within our extensible framework, and compare with current baseline methods using common datasets and evaluation metrics without extra effort.
## Overview
It 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`
* **Graph OOD**: `dig.oodgraph`
* **Graph Augmentation**: `dig.auggraph`
* **Fair Graph Learning**: `dig.fairgraph`
<p align="center">
<img src="https://github.com/divelab/DIG/blob/dig-stable/docs/imgs/DIG-overview.png" width="700" class="center" alt="logo"/>
<br/>
</p>
## Usage
Example: a few lines of code to run [SphereNet](https://openreview.net/forum?id=givsRXsOt9r) on [QM9Excerpt of 11,497 characters
Read on GitHub
96
87
87
75
71
56
56
41
31
27
25
22
22
13
13
11
9
8
3
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:a4562d92cc48ec11, topic:deep-learning