DGL is an easy-to-use, high performance and scalable Python package for deep learning on graphs. DGL is framework agnostic, meaning if a deep graph model is a component of an end-to-end application, the rest of the logics can be implemented in any major frameworks, such as PyTorch, Apache MXNet or TensorFlow.

<img src="http://data.dgl.ai/asset/image/DGL-Arch.png" alt="DGL v0.4 architecture" width="600"> Figure: DGL Overall Architecture

Highlighted Features

A GPU-ready graph library

DGL provides a powerful graph object that can reside on either CPU or GPU. It bundles structural data as well as features for better control. We provide a variety of functions for computing with graph objects including efficient and customizable message passing primitives for Graph Neural Networks.

A versatile tool for GNN researchers and practitioners

The field of graph deep learning is still rapidly evolving and many research ideas emerge by standing on the shoulders of giants. To ease the process, DGl-Go is a command-line interface to get started with training, using and studying state-of-the-art GNNs. DGL collects a rich set of example implementations of popular GNN models of a wide range of topics. Researchers can search for related models to innovate new ideas from or use them as baselines for experiments. Moreover, DGL provides many state-of-the-art GNN layers and modules for users to build new model architectures. DGL is one of the preferred platforms for many standard graph deep learning benchmarks including OGB and GNNBenchmarks.

Easy to learn and use

DGL provides plenty of learning materials for all kinds of users from ML researchers to domain experts. The Blitz Introduction to DGL is a 120-minute tour of the basics of graph machine learning. The User Guide explains in more details the concepts of graphs as well as the training methodology. All of them include code snippets in DGL that are runnable and ready to be plugged into one’s own pipeline.

Scalable and efficient

It is convenient to train models using DGL on large-scale graphs across multiple GPUs or multiple machines. DGL extensively optimizes the whole stack to reduce the overhead in communication, memory consumption and synchronization. As a result, DGL can easily scale to billion-sized graphs. Get started with the tutorials and user guide for distributed training. See the system performance note for the comparison with other tools.

Get Started

Users can install DGL from pip and conda. You can also download GPU enabled DGL docker containers (backended by PyTorch) from NVIDIA NGC for both x86 and ARM based linux systems. Advanced users can follow the instructions to install from source.

For absolute beginners, start with the Blitz Introduction to DGL. It covers the basic concepts of common graph machine learning tasks and a step-by-step on building Graph Neural Networks (GNNs) to solve them.

For acquainted users who wish to learn more,

Experience state-of-the-art GNN models in only two command-lines using DGL-Go.
Learn DGL by example implementations of popular GNN models.
Read the User Guide (中文版链接), which explains the concepts and usage of DGL in much more details.
Go through the tutorials for advanced features like stochastic training of GNNs, training on multi-GPU or multi-machine.
Study classical papers on graph machine learning alongside DGL.
Search for the usage of a specific API in the API reference manual, which organizes all DGL APIs by their namespace.

All the learning materials are available at our documentation site. If you are new to deep learning in general, check out the open source book Dive into Deep Learning.

Community

Get connected

We provide multiple channels to connect you to the community of the DGL developers, users, and the general GNN academic researchers:

Our Slack channel, click to join
Our discussion forum: https://discuss.dgl.ai/
Our Zhihu blog (in Chinese)
Monthly GNN User Group online seminar (event link | past videos)

Take the survey here and leave any feedback to make DGL better fit for your needs. Thanks!

DGL-powered projects

DGL-LifeSci: a DGL-based package for various applications in life science with graph neural networks. https://github.com/awslabs/dgl-lifesci
DGL-KE: a high performance, easy-to-use, and scalable package for learning large-scale knowledge graph embeddings. https://github.com/awslabs/dgl-ke
Benchmarking GNN: https://github.com/graphdeeplearning/benchmarking-gnns
OGB: a collection of realistic, large-scale, and diverse benchmark datasets for machine learning on graphs. https://ogb.stanford.edu/
Graph4NLP: an easy-to-use library for R&D at the intersection of Deep Learning on Graphs and Natural Language Processing. https://github.com/graph4ai/graph4nlp
GNN-RecSys: https://github.com/je-dbl/GNN-RecSys
Amazon Neptune ML: a new capability of Neptune that uses Graph Neural Networks (GNNs), a machine learning technique purpose-built for graphs, to make easy, fast, and more accurate predictions using graph data. https://aws.amazon.com/cn/neptune/machine-learning/
GNNLens2: Visualization tool for Graph Neural Networks. https://github.com/dmlc/GNNLens2
RNAGlib: A package to facilitate construction, analysis, visualization and machine learning on RNA 2.5D Graphs. Includes a pre-built dataset: https://rnaglib.cs.mcgill.ca
OpenHGNN: Model zoo and benchmarks for Heterogeneous Graph Neural Networks. https://github.com/BUPT-GAMMA/OpenHGNN
TGL: A graph learning framework for large-scale temporal graphs. https://github.com/amazon-research/tgl
gtrick: Bag of Tricks for Graph Neural Networks. https://github.com/sangyx/gtrick
ArangoDB-DGL Adapter: Import ArangoDB graphs into DGL and vice-versa. https://github.com/arangoml/dgl-adapter
DGLD: DGLD is an open-source library for Deep Graph Anomaly Detection based on pytorch and DGL.

Awesome Papers Using DGL

Benchmarking Graph Neural Networks, Vijay Prakash Dwivedi, Chaitanya K. Joshi, Thomas Laurent, Yoshua Bengio, Xavier Bresson
Open Graph Benchmarks: Datasets for Machine Learning on Graphs, NeurIPS'20, Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, Jure Leskovec
DropEdge: Towards Deep Graph Convolutional Networks on Node Classification, ICLR'20, Yu Rong, Wenbing Huang, Tingyang Xu, Junzhou Huan
Discourse-Aware Neural Extractive Text Summarization, ACL'20, Jiacheng Xu, Zhe Gan, Yu Cheng, Jingjing Liu
GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training, KDD'20, Jiezhong Qiu, Qibin Chen, Yuxiao Dong, Jing Zhang, Hongxia Yang, Ming Ding, Kuansan Wang, Jie Tang
DGL-KE: Training Knowledge Graph Embeddings at Scale, SIGIR'20, *Da Zheng, Xiang Song, Chao

Dgl

Install / Use

README