DGLGraph and Node/edge Features

Author: Minjie Wang, Quan Gan, Yu Gai, Zheng Zhang

In this tutorial, you learn how to create a graph and how to read and write node and edge representations.

Creating a graph

The design of DGLGraph was influenced by other graph libraries. You can create a graph from networkx and convert it into a DGLGraph and vice versa.

import networkx as nx
import dgl

g_nx = nx.petersen_graph()
g_dgl = dgl.DGLGraph(g_nx)

import matplotlib.pyplot as plt
nx.draw(g_nx, with_labels=True)
nx.draw(g_dgl.to_networkx(), with_labels=True)


The examples here show the same graph, except that DGLGraph is always directional.

You can also create a graph by calling the DGL interface.

In the next example, you build a star graph. DGLGraph nodes are a consecutive range of integers between 0 and number_of_nodes() and can grow by calling add_nodes. DGLGraph edges are in order of their additions. Note that edges are accessed in much the same way as nodes, with one extra feature: edge broadcasting.

import dgl
import torch as th

g = dgl.DGLGraph()
# A couple edges one-by-one
for i in range(1, 4):
    g.add_edge(i, 0)
# A few more with a paired list
src = list(range(5, 8)); dst = [0]*3
g.add_edges(src, dst)
# finish with a pair of tensors
src = th.tensor([8, 9]); dst = th.tensor([0, 0])
g.add_edges(src, dst)

# Edge broadcasting will do star graph in one go!
g.clear(); g.add_nodes(10)
src = th.tensor(list(range(1, 10)));
g.add_edges(src, 0)

import networkx as nx
import matplotlib.pyplot as plt
nx.draw(g.to_networkx(), with_labels=True)

Assigning a feature

You can also assign features to nodes and edges of a DGLGraph. The features are represented as dictionary of names (strings) and tensors, called fields.

The following code snippet assigns each node a vector (len=3).


DGL aims to be framework-agnostic, and currently it supports PyTorch and MXNet tensors. The following examples use PyTorch only.

import dgl
import torch as th

x = th.randn(10, 3)
g.ndata['x'] = x

ndata is a syntax sugar to access the state of all nodes. States are stored in a container data that hosts a user-defined dictionary.

print(g.ndata['x'] == g.nodes[:].data['x'])

# Access node set with integer, list, or integer tensor
g.nodes[0].data['x'] = th.zeros(1, 3)
g.nodes[[0, 1, 2]].data['x'] = th.zeros(3, 3)
g.nodes[th.tensor([0, 1, 2])].data['x'] = th.zeros(3, 3)


tensor([[True, True, True],
        [True, True, True],
        [True, True, True],
        [True, True, True],
        [True, True, True],
        [True, True, True],
        [True, True, True],
        [True, True, True],
        [True, True, True],
        [True, True, True]])

Assigning edge features is similar to that of node features, except that you can also do it by specifying endpoints of the edges.

g.edata['w'] = th.randn(9, 2)

# Access edge set with IDs in integer, list, or integer tensor
g.edges[1].data['w'] = th.randn(1, 2)
g.edges[[0, 1, 2]].data['w'] = th.zeros(3, 2)
g.edges[th.tensor([0, 1, 2])].data['w'] = th.zeros(3, 2)

# You can also access the edges by giving endpoints
g.edges[1, 0].data['w'] = th.ones(1, 2)                 # edge 1 -> 0
g.edges[[1, 2, 3], [0, 0, 0]].data['w'] = th.ones(3, 2) # edges [1, 2, 3] -> 0

After assignments, each node or edge field will be associated with a scheme containing the shape and data type (dtype) of its field value.

g.ndata['x'] = th.zeros((10, 4))


{'x': Scheme(shape=(3,), dtype=torch.float32)}
{'x': Scheme(shape=(4,), dtype=torch.float32)}

You can also remove node or edge states from the graph. This is particularly useful to save memory during inference.


Working with multigraphs

Many graph applications need parallel edges. To enable this, construct DGLGraph with multigraph=True.

g_multi = dgl.DGLGraph(multigraph=True)
g_multi.ndata['x'] = th.randn(10, 2)

g_multi.add_edges(list(range(1, 10)), 0)
g_multi.add_edge(1, 0) # two edges on 1->0

g_multi.edata['w'] = th.randn(10, 2)
g_multi.edges[1].data['w'] = th.zeros(1, 2)


(tensor([1, 2, 3, 4, 5, 6, 7, 8, 9, 1]), tensor([0, 0, 0, 0, 0, 0, 0, 0, 0, 0]))

An edge in multigraph cannot be uniquely identified by using its incident nodes \(u\) and \(v\); query their edge IDs use edge_id interface.

eid_10 = g_multi.edge_id(1, 0)
g_multi.edges[eid_10].data['w'] = th.ones(len(eid_10), 2)


tensor([[ 1.0000,  1.0000],
        [ 0.0000,  0.0000],
        [-0.8381, -0.2076],
        [-1.0214, -0.0418],
        [-0.4424, -1.2469],
        [ 0.3718, -0.7005],
        [-0.3940,  0.8561],
        [-0.5408,  0.1206],
        [ 1.0355,  0.4003],
        [ 1.0000,  1.0000]])


  • Nodes and edges can be added but not removed.
  • Updating a feature of different schemes raises the risk of error on individual nodes (or node subset).

Next steps

In the next tutorial you learn the DGL message passing interface by implementing PageRank.

Total running time of the script: ( 0 minutes 0.518 seconds)

Gallery generated by Sphinx-Gallery