# dgl.sum_edges¶

dgl.sum_edges(graph, feat, weight=None)[source]

Sums all the values of edge field feat in graph, optionally multiplies the field by a scalar edge field weight.

Parameters: graph (DGLGraph) – The graph. feat (str) – The feature field. weight (str, optional) – The weight field. If None, no weighting will be performed, otherwise, weight each edge feature with field feat. for summation. The weight feature associated in the graph should be a tensor of shape [graph.number_of_edges(), 1]. The summed tensor. tensor

Notes

Return a stacked tensor with an extra first dimension whose size equals batch size of the input graph. The i-th row of the stacked tensor contains the readout result of the i-th graph in the batched graph. If a graph has no edges, a zero tensor with the same shape is returned at the corresponding row.

Examples

>>> import dgl
>>> import torch as th


Create two DGLGraph objects and initialize their edge features.

>>> g1 = dgl.DGLGraph()                           # Graph 1
>>> g1.edata['h'] = th.tensor([[1.], [2.]])
>>> g1.edata['w'] = th.tensor([[3.], [6.]])

>>> g2 = dgl.DGLGraph()                           # Graph 2
>>> g2.add_edges([0, 1, 2], [1, 2, 0])
>>> g2.edata['h'] = th.tensor([[1.], [2.], [3.]])


Sum over edge attribute h without weighting for each graph in a batched graph.

>>> bg = dgl.batch([g1, g2], edge_attrs='h')
>>> dgl.sum_edges(bg, 'h')
tensor([[3.],   # 1 + 2
[6.]])  # 1 + 2 + 3


Sum edge attribute h with weight from edge attribute w for a single graph.

>>> dgl.sum_edges(g1, 'h', 'w')
tensor([[15.]]) # 1 * 3 + 2 * 6