dgl.to_blockΒΆ

dgl.
to_block
(g, dst_nodes=None, include_dst_in_src=True, src_nodes=None)[source]ΒΆ Convert a graph into a bipartitestructured block for message passing.
A block is a graph consisting of two sets of nodes: the source nodes and destination nodes. The source and destination nodes can have multiple node types. All the edges connect from source nodes to destination nodes.
Specifically, the source nodes and destination nodes will have the same node types as the ones in the original graph. DGL maps each edge
(u, v)
with edge type(utype, etype, vtype)
in the original graph to the edge with typeetype
connecting from node IDu
of typeutype
in the source side to node IDv
of typevtype
in the destination side.For blocks returned by
to_block()
, the destination nodes of the block will only contain the nodes that have at least one inbound edge of any type. The source nodes of the block will only contain the nodes that appear in the destination nodes, as well as the nodes that have at least one outbound edge connecting to one of the destination nodes.The destination nodes are specified by the
dst_nodes
argument if it is not None. Parameters
graph (DGLGraph) β The graph. Can be either on CPU or GPU.
dst_nodes (Tensor or dict[str, Tensor], optional) β
The list of destination nodes.
If a tensor is given, the graph must have only one node type.
If given, it must be a superset of all the nodes that have at least one inbound edge. An error will be raised otherwise.
include_dst_in_src (bool) β
If False, do not include destination nodes in source nodes.
(Default: True)
src_nodes (Tensor or disct[str, Tensor], optional) β
The list of source nodes (and prefixed by destination nodes if include_dst_in_src is True).
If a tensor is given, the graph must have only one node type.
 Returns
The new graph describing the block.
The node IDs induced for each type in both sides would be stored in feature
dgl.NID
.The edge IDs induced for each type would be stored in feature
dgl.EID
. Return type
DGLBlock
 Raises
DGLError β If
dst_nodes
is specified but it is not a superset of all the nodes that have at least one inbound edge. Ifdst_nodes
is not None, andg
anddst_nodes
are not in the same context.
Notes
to_block()
is most commonly used in customizing neighborhood sampling for stochastic training on a large graph. Please refer to the user guide Chapter 6: Stochastic Training on Large Graphs for a more thorough discussion about the methodology of stochastic training.See also
create_block()
for more flexible construction of blocks.Examples
Converting a homogeneous graph to a block as described above:
>>> g = dgl.graph(([1, 2], [2, 3])) >>> block = dgl.to_block(g, torch.LongTensor([3, 2]))
The destination nodes would be exactly the same as the ones given: [3, 2].
>>> induced_dst = block.dstdata[dgl.NID] >>> induced_dst tensor([3, 2])
The first few source nodes would also be exactly the same as the ones given. The rest of the nodes are the ones necessary for message passing into nodes 3, 2. This means that the node 1 would be included.
>>> induced_src = block.srcdata[dgl.NID] >>> induced_src tensor([3, 2, 1])
You can notice that the first two nodes are identical to the given nodes as well as the destination nodes.
The induced edges can also be obtained by the following:
>>> block.edata[dgl.EID] tensor([2, 1])
This indicates that edge (2, 3) and (1, 2) are included in the result graph. You can verify that the first edge in the block indeed maps to the edge (2, 3), and the second edge in the block indeed maps to the edge (1, 2):
>>> src, dst = block.edges(order='eid') >>> induced_src[src], induced_dst[dst] (tensor([2, 1]), tensor([3, 2]))
The destination nodes specified must be a superset of the nodes that have edges connecting to them. For example, the following will raise an error since the destination nodes does not contain node 3, which has an edge connecting to it.
>>> g = dgl.graph(([1, 2], [2, 3])) >>> dgl.to_block(g, torch.LongTensor([2])) # error
Converting a heterogeneous graph to a block is similar, except that when specifying the destination nodes, you have to give a dict:
>>> g = dgl.heterograph({('A', '_E', 'B'): ([1, 2], [2, 3])})
If you donβt specify any node of type A on the destination side, the node type
A
in the block would have zero nodes on the destination side.>>> block = dgl.to_block(g, {'B': torch.LongTensor([3, 2])}) >>> block.number_of_dst_nodes('A') 0 >>> block.number_of_dst_nodes('B') 2 >>> block.dstnodes['B'].data[dgl.NID] tensor([3, 2])
The source side would contain all the nodes on the destination side:
>>> block.srcnodes['B'].data[dgl.NID] tensor([3, 2])
As well as all the nodes that have connections to the nodes on the destination side:
>>> block.srcnodes['A'].data[dgl.NID] tensor([2, 1])
See also