$DGL is live: 58SXRrFik95UARYwohmWcT8hW7Ry14Qzd66vCoLPpump
Framework Agnostic
Build your models with PyTorch, TensorFlow or Apache MXNet.
Efficient And Scalable
Fast and memory-efficient message passing primitives for training Graph Neural Networks. Scale to giant graphs via multi-GPU acceleration and distributed training infrastructure.
Diverse Ecosystem
DGL empowers a variety of domain-specific projects including DGL-KE for learning large-scale knowledge graph embeddings, DGL-LifeSci for bioinformatics and cheminformatics, and many others.
Find An Example To Get Started
| Paper Title | Tags |
|---|---|
| Graph Transformer for Graph-to-Sequence Learning | graph transformer, graph-to-sequence, natural language processing |
| Heterogeneous Graph Transformer | heterogeneous graph, graph transformer, network embedding |
| Graph Convolutional Neural Networks for Web-Scale Recommender Systems | graph neural networks, recommender systems, scalability |
| Semi-Supervised Classification with Graph Convolutional Networks | graph neural networks, semi-supervised learning, node classification |
| Modeling Relational Data with Graph Convolutional Networks | graph neural networks, knowledge graphs, link prediction |
| How Powerful are Graph Neural Networks? | graph neural networks, theoretical analysis, expressiveness |
| Benchmarking Graph Neural Networks | graph neural networks, benchmarking, empirical analysis |
| A Comprehensive Survey on Graph Neural Networks | graph neural networks, survey, deep learning |
| Graph Neural Networks for Social Recommendation | graph neural networks, social networks, recommender systems |
| Deep Graph Infomax | graph neural networks, self-supervised learning, representation learning |
| Graph Attention Networks | graph neural networks, attention mechanism, node classification |
| DropEdge: Towards Deep Graph Convolutional Networks on Node Classification | graph neural networks, regularization, node classification |
| Position-aware Graph Neural Networks | graph neural networks, structural information, position encoding |
| Hierarchical Graph Representation Learning with Differentiable Pooling | graph neural networks, graph pooling, hierarchical representation |
| Graph U-Nets | graph neural networks, graph pooling, graph unpooling |
| Simplifying Graph Convolutional Networks | graph neural networks, model simplification, scalability |
| DeepGCNs: Can GCNs Go as Deep as CNNs? | graph neural networks, deep architectures, residual connections |
| Graph Neural Networks with Generated Parameters for Relation Extraction | graph neural networks, relation extraction, natural language processing |
| Heterogeneous Graph Neural Network | heterogeneous graph, graph neural networks, network embedding |
| Graph Neural Networks for Natural Language Processing | graph neural networks, natural language processing, survey |
| Temporal Graph Networks for Deep Learning on Dynamic Graphs | temporal graphs, dynamic graphs, graph neural networks |
| Graph Neural Networks Meet Neural-Symbolic Computing | neural-symbolic computing, graph neural networks, reasoning |
| A Practical Guide to Graph Neural Networks | graph neural networks, tutorial, practical guide |
| Graph Neural Networks for Small Graph and Giant Network Representation Learning | graph neural networks, scalability, large graphs |
| Combining Graph Neural Networks and Spatio-temporal Disease Models | graph neural networks, epidemiology, spatio-temporal |
| Self-Supervised Learning of Graph Neural Networks | self-supervised learning, graph neural networks, representation learning |
| Graph Neural Networks for Quantum Chemistry | quantum chemistry, graph neural networks, molecular properties |
| Explainability in Graph Neural Networks | explainability, graph neural networks, interpretability |
| Adversarial Attacks on Graph Neural Networks | adversarial attacks, graph neural networks, robustness |
| Graph Neural Networks for Recommendation Systems | recommender systems, graph neural networks, collaborative filtering |
| Few-Shot Learning with Graph Neural Networks | few-shot learning, graph neural networks, meta-learning |
| Geometric Deep Learning on Graphs | geometric deep learning, graph neural networks, manifolds |
| Graph Neural Networks for Computer Vision | computer vision, graph neural networks, visual reasoning |
| Bayesian Graph Neural Networks | bayesian learning, graph neural networks, uncertainty |
| Graph Neural Networks for Knowledge Graph Completion | knowledge graphs, graph neural networks, link prediction |
| Contrastive Learning of Graph Neural Networks | contrastive learning, graph neural networks, self-supervised |
GNN Training Acceleration With BFloat16 Data Type On CPU
Graph neural networks (GNN) have achieved state-of-the-art performance on various industrial tasks. However, most GNN operations are memory-bound and require a significant amount of RAM. To tackle this problem well...
Visit Blogs
Visit Blogs
Deep learning on graphs is very new direction. We use blogs to introduce new ideas and researches of this area and explains how DGL can support them very easily.
Read All Blogs
Slack Channel
Join Discussion
Join Discussion
Got questions? Interested in contributing? or simply want to know what others are playing with? Use our forum for all kinds of discussion.
Visit Our ForumWhat People Are Saying ...
"Brought to you by NYU, NYU-Shanghai, and Amazon AWS.
Yann LeCun
NYU Professor, Director of Facebook AI Lab
"By far the cleanest and most elegant library for graph neural networks in PyTorch. Highly recommended! Unifies Capsule Nets (GNNs on bipartite graphs) and Transformers (GCNs with attention on fully-connected graphs) in a single API.
Thomas Kipf
Inventor of Graph Convolutional Network
Sponsors
