Documentation | DGL at a glance | Model Tutorials | Discussion Forum
Model Zoos: Chemistry | Citation Networks
DGL is a Python package that interfaces between existing tensor libraries and data being expressed as graphs.
It makes implementing graph neural networks (including Graph Convolution Networks, TreeLSTM, and many others) easy while maintaining high computation efficiency.
All model examples can be found here.
A summary of part of the model accuracy and training speed with the Pytorch backend (on Amazon EC2 p3.2x instance (w/ V100 GPU)), as compared with the best open-source implementations:
| Model | Reported Accuracy |
DGL Accuracy |
Author's training speed (epoch time) | DGL speed (epoch time) | Improvement |
|---|---|---|---|---|---|
| GCN | 81.5% | 81.0% | 0.0051s (TF) | 0.0031s | 1.64x |
| GAT | 83.0% | 83.9% | 0.0982s (TF) | 0.0113s | 8.69x |
| SGC | 81.0% | 81.9% | n/a | 0.0008s | n/a |
| TreeLSTM | 51.0% | 51.72% | 14.02s (DyNet) | 3.18s | 4.3x |
| R-GCN (classification) |
73.23% | 73.53% | 0.2853s (Theano) | 0.0075s | 38.2x |
| R-GCN (link prediction) |
0.158 | 0.151 | 2.204s (TF) | 0.453s | 4.86x |
| JTNN | 96.44% | 96.44% | 1826s (Pytorch) | 743s | 2.5x |
| LGNN | 94% | 94% | n/a | 1.45s | n/a |
| DGMG | 84% | 90% | n/a | 238s | n/a |
| GraphWriter | 14.3(BLEU) | 14.31(BLEU) | 1970s (PyTorch) | 1192s | 1.65x |
With the MXNet/Gluon backend , we scaled a graph of 50M nodes and 150M edges on a P3.8xlarge instance, with 160s per epoch, on SSE (Stochastic Steady-state Embedding), a model similar to GCN.
We are currently in Beta stage. More features and improvements are coming.
v0.4 has just been released! DGL now support heterogeneous graphs, and comes with a subpackage DGL-KE that computes embeddings for large knowledge graphs such as Freebase (1.9 billion triplets). See release note here.
We presented DGL at GTC 2019 as an instructor-led training session. Check out our slides and tutorial materials here!!!
DGL should work on
- all Linux distributions no earlier than Ubuntu 16.04
- macOS X
- Windows 10
DGL also requires Python 3.5 or later. Python 2 support is coming.
Right now, DGL works on PyTorch 0.4.1+ and MXNet nightly build.
conda install -c dglteam dgl # cpu version
conda install -c dglteam dgl-cuda9.0 # CUDA 9.0
conda install -c dglteam dgl-cuda9.2 # CUDA 9.2
conda install -c dglteam dgl-cuda10.0 # CUDA 10.0
conda install -c dglteam dgl-cuda10.1 # CUDA 10.1
pip install dgl # cpu version
pip install dgl-cu90 # CUDA 9.0
pip install dgl-cu92 # CUDA 9.2
pip install dgl-cu100 # CUDA 10.0
pip install dgl-cu101 # CUDA 10.1
Refer to the guide here.
A graph can be constructed with feature tensors like this:
import dgl
import torch as th
g = dgl.DGLGraph()
g.add_nodes(5) # add 5 nodes
g.add_edges([0, 0, 0, 0], [1, 2, 3, 4]) # add 4 edges 0->1, 0->2, 0->3, 0->4
g.ndata['h'] = th.randn(5, 3) # assign one 3D vector to each node
g.edata['h'] = th.randn(4, 4) # assign one 4D vector to each edgeThis is everything to implement a single layer for Graph Convolutional Network on PyTorch:
import dgl.function as fn
import torch.nn as nn
import torch.nn.functional as F
from dgl import DGLGraph
msg_func = fn.copy_src(src='h', out='m')
reduce_func = fn.sum(msg='m', out='h')
class GCNLayer(nn.Module):
def __init__(self, in_feats, out_feats):
super(GCNLayer, self).__init__()
self.linear = nn.Linear(in_feats, out_feats)
def apply(self, nodes):
return {'h': F.relu(self.linear(nodes.data['h']))}
def forward(self, g, feature):
g.ndata['h'] = feature
g.update_all(msg_func, reduce_func)
g.apply_nodes(func=self.apply)
return g.ndata.pop('h')One can also customize how message and reduce function works. The following code demonstrates a (simplified version of) Graph Attention Network (GAT) layer:
def msg_func(edges):
return {'k': edges.src['k'], 'v': edges.src['v']}
def reduce_func(nodes):
# nodes.data['q'] has the shape
# (number_of_nodes, feature_dims)
# nodes.data['k'] and nodes.data['v'] have the shape
# (number_of_nodes, number_of_incoming_messages, feature_dims)
# You only need to deal with the case where all nodes have the same number
# of incoming messages.
q = nodes.data['q'][:, None]
k = nodes.mailbox['k']
v = nodes.mailbox['v']
s = F.softmax((q * k).sum(-1), 1)[:, :, None]
return {'v': th.sum(s * v, 1)}
class GATLayer(nn.Module):
def __init__(self, in_feats, out_feats):
super(GATLayer, self).__init__()
self.Q = nn.Linear(in_feats, out_feats)
self.K = nn.Linear(in_feats, out_feats)
self.V = nn.Linear(in_feats, out_feats)
def apply(self, nodes):
return {'v': F.relu(self.linear(nodes.data['v']))}
def forward(self, g, feature):
g.ndata['v'] = self.V(feature)
g.ndata['q'] = self.Q(feature)
g.ndata['k'] = self.K(feature)
g.update_all(msg_func, reduce_func)
g.apply_nodes(func=self.apply)
return g.ndata['v']For the basics of coding with DGL, please see DGL basics.
For more realistic, end-to-end examples, please see model tutorials.
Check out the open source book Dive into Deep Learning.
Please let us know if you encounter a bug or have any suggestions by filing an issue.
We welcome all contributions from bug fixes to new features and extensions. We expect all contributions discussed in the issue tracker and going through PRs. Please refer to our contribution guide.
If you use DGL in a scientific publication, we would appreciate citations to the following paper:
@article{wang2019dgl,
title={Deep Graph Library: Towards Efficient and Scalable Deep Learning on Graphs},
url={https://arxiv.org/abs/1909.01315},
author={{Wang, Minjie and Yu, Lingfan and Zheng, Da and Gan, Quan and Gai, Yu and Ye, Zihao and Li, Mufei and Zhou, Jinjing and Huang, Qi and Ma, Chao and Huang, Ziyue and Guo, Qipeng and Zhang, Hao and Lin, Haibin and Zhao, Junbo and Li, Jinyang and Smola, Alexander J and Zhang, Zheng},
journal={ICLR Workshop on Representation Learning on Graphs and Manifolds},
year={2019}
}
DGL is developed and maintained by NYU, NYU Shanghai, AWS Shanghai AI Lab, and AWS MXNet Science Team.
DGL uses Apache License 2.0.