mindspore_gl.graph.PadHomoGraph

class mindspore_gl.graph.PadHomoGraph(n_node=None, mode=PadMode.AUTO, n_edge=None, csr=False)[source]

Pad MindHomoGraph, We pad graph by adding additional nodes and edges between these nodes. In short, \(\text{PadHomoGraph}(graph1) = \text{BatchHomoGraph}(graph1, fake\_graph)\) node count and edge count in fake_graph is determined by user-specific parameters.

Parameters

n_node (int, optional) – target graph’s node count. Default: None.
n_edge (int, optional) – target graph’s edge count. Default: None.
mode (PadMode, optional) – Pad mode, if PadMode.CONST, target graph will have n_node nodes and n_edge edges. If PadMode.AUTO target graph’s node_count and edge_count is calculated according to input graph’s size by \(n\_node = 2^{\text{ceil}(\log_{2}(input\_graph.node\_count))}\) , \(n\_edge = 2^{\text{ceil}(\log_{2}(input\_graph.edge\_count))}\) . Default: mindspore_gl.graph.PadMode.AUTO.
csr (bool, optional) – Is the csr graph. Default: False.

Inputs:

graph (MindHomoGraph) - input graph.

Outputs:

MindHomoGraph, padded graph.

Supported Platforms:

Ascend GPU

Examples

>>> from mindspore_gl.graph.ops import BatchHomoGraph, PadHomoGraph, PadMode
>>> import numpy as np
>>> from mindspore_gl.graph.graph import MindHomoGraph
>>> graph_list = []
>>> for _ in range(1):
...     graph = MindHomoGraph()
...     edges = np.array([[0, 2, 2, 3, 4, 5, 5, 6], [1, 0, 1, 5, 3, 4, 6, 4]])
...     graph.set_topo_coo(edges)
...     graph.node_count = 7
...     graph.edge_count = 8
...     graph_list.append(graph)
>>> batch_fn = BatchHomoGraph()
>>> batch_graph = batch_fn(graph_list)
>>> n_node = graph.node_count + 1
>>> n_edge = graph.edge_count + 30
>>> pad_graph_op = PadHomoGraph(mode=PadMode.CONST, n_node=n_node, n_edge=n_edge)
>>> pad_res = pad_graph_op(batch_graph)
>>> print(pad_res[0].edge_count, pad_res[1].edge_count)
8   30
>>> print(pad_res[0].node_count, pad_res[1].node_count)
7   1