mindspore_gl.nn.SortPooling

class mindspore_gl.nn.SortPooling(k)[source]

Apply sort pooling to the nodes in the graph.

From the paper End-to-End Deep Learning Architecture for Graph Classification . The sorting pool first sorts the node features in ascending order along the feature dimension, and then selects the ranking features of top-k nodes (sorted by the maximum value of each node).

Parameters: k (int) – Number of nodes to keep per graph.

Inputs:

x (Tensor) - The input node features to be updated. The shape is \((N, D)\) where \(N\) is the number of nodes, and \(D\) is the feature size of nodes.
g (BatchedGraph) - The input graph.

Outputs:

x (Tensor) - The output representation for graphs. The shape is \((2, D_{out})\) where \(D_{out}\) is the double feature size of nodes.

Raises: TypeError – If k is not an int.

Supported Platforms:: Ascend GPU

Examples

>>> import numpy as np
>>> import mindspore as ms
>>> from mindspore_gl.nn import SortPooling
>>> from mindspore_gl import BatchedGraphField
>>> n_nodes = 7
>>> n_edges = 8
>>> src_idx = ms.Tensor([0, 2, 2, 3, 4, 5, 5, 6], ms.int32)
>>> dst_idx = ms.Tensor([1, 0, 1, 5, 3, 4, 6, 4], ms.int32)
>>> ver_subgraph_idx = ms.Tensor([0, 0, 0, 1, 1, 1, 1], ms.int32)
>>> edge_subgraph_idx = ms.Tensor([0, 0, 0, 1, 1, 1, 1, 1], ms.int32)
>>> graph_mask = ms.Tensor([1, 1], ms.int32)
>>> batched_graph_field = BatchedGraphField(src_idx, dst_idx, n_nodes, n_edges, ver_subgraph_idx,
...                                         edge_subgraph_idx, graph_mask)
>>> node_feat = np.random.random((n_nodes, 4))
>>> node_feat = ms.Tensor(node_feat, ms.float32)
>>> net = SortPooling(k=2)
>>> ret = net(node_feat, *batched_graph_field.get_batched_graph())
>>> print(ret.shape)
(2, 8)