reindex_graph

paddle.geometric. reindex_graph ( x, neighbors, count, value_buffer=None, index_buffer=None, name=None ) [source]

Reindex Graph API.

This API is mainly used in Graph Learning domain, which should be used in conjunction with paddle.geometric.sample_neighbors API. And the main purpose is to reindex the ids information of the input nodes, and return the corresponding graph edges after reindex.

Take input nodes x = [0, 1, 2] as an example. If we have neighbors = [8, 9, 0, 4, 7, 6, 7], and count = [2, 3, 2], then we know that the neighbors of 0 is [8, 9], the neighbors of 1 is [0, 4, 7], and the neighbors of 2 is [6, 7]. Then after graph_reindex, we will have 3 different outputs: reindex_src: [3, 4, 0, 5, 6, 7, 6], reindex_dst: [0, 0, 1, 1, 1, 2, 2] and out_nodes: [0, 1, 2, 8, 9, 4, 7, 6]. We can see that the numbers in reindex_src and reindex_dst is the corresponding index of nodes in out_nodes.

Note

The number in x should be unique, otherwise it would cause potential errors. We will reindex all the nodes from 0.

Parameters
  • x (Tensor) – The input nodes which we sample neighbors for. The available data type is int32, int64.

  • neighbors (Tensor) – The neighbors of the input nodes x. The data type should be the same with x.

  • count (Tensor) – The neighbor count of the input nodes x. And the data type should be int32.

  • value_buffer (Tensor, optional) – Value buffer for hashtable. The data type should be int32, and should be filled with -1. Only useful for gpu version. Default is None.

  • index_buffer (Tensor, optional) – Index buffer for hashtable. The data type should be int32, and should be filled with -1. Only useful for gpu version. value_buffer and index_buffer should be both not None if you want to speed up by using hashtable buffer. Default is None.

  • name (str, optional) – Name for the operation (optional, default is None). For more information, please refer to Name.

Returns

  • reindex_src (Tensor), the source node index of graph edges after reindex.

  • reindex_dst (Tensor), the destination node index of graph edges after reindex.

  • out_nodes (Tensor), the index of unique input nodes and neighbors before reindex, where we put the input nodes x in the front, and put neighbor nodes in the back.

Examples

>>> import paddle

>>> x = [0, 1, 2]
>>> neighbors = [8, 9, 0, 4, 7, 6, 7]
>>> count = [2, 3, 2]
>>> x = paddle.to_tensor(x, dtype="int64")
>>> neighbors = paddle.to_tensor(neighbors, dtype="int64")
>>> count = paddle.to_tensor(count, dtype="int32")
>>> reindex_src, reindex_dst, out_nodes = paddle.geometric.reindex_graph(x, neighbors, count)
>>> print(reindex_src.numpy())
[3 4 0 5 6 7 6]
>>> print(reindex_dst.numpy())
[0 0 1 1 1 2 2]
>>> print(out_nodes.numpy())
[0 1 2 8 9 4 7 6]