This API is mainly used in Graph Learning domain, which should be used
This API is mainly used in Graph Learning domain, which should be used
in conjunction with `graph_sample_neighbors` API. And the main purpose
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
is to reindex the ids information of the input nodes, and return the
corresponding graph edges after reindex.
corresponding graph edges after reindex.
**Notes**:
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],
The number in x should be unique, otherwise it would cause potential errors.
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].
We will reindex all the nodes from 0.
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
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:
1. reindex_src: [3, 4, 0, 5, 6, 7, 6]
2. reindex_dst: [0, 0, 1, 1, 1, 2, 2]
3. 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`.
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.
Args:
Args:
x (Tensor): The input nodes which we sample neighbors for. The available
x (Tensor): The input nodes which we sample neighbors for. The available
data type is int32, int64.
data type is int32, int64.
neighbors (Tensor): The neighbors of the input nodes `x`. The data type
neighbors (Tensor): The neighbors of the input nodes `x`. The data type
should be the same with `x`.
should be the same with `x`.
count (Tensor): The neighbor count of the input nodes `x`. And the
count (Tensor): The neighbor count of the input nodes `x`. And the
data type should be int32.
data type should be int32.
value_buffer (Tensor|None): Value buffer for hashtable. The data type should be int32,
value_buffer (Tensor|None): Value buffer for hashtable. The data type should be int32,
and should be filled with -1. Only useful for gpu version.
and should be filled with -1. Only useful for gpu version.
index_buffer (Tensor|None): Index buffer for hashtable. The data type should be int32,
index_buffer (Tensor|None): Index buffer for hashtable. The data type should be int32,
and should be filled with -1. Only useful for gpu version.
and should be filled with -1. Only useful for gpu version.
`value_buffer` and `index_buffer` should be both not None
`value_buffer` and `index_buffer` should be both not None
if you want to speed up by using hashtable buffer.
if you want to speed up by using hashtable buffer.
name (str, optional): Name for the operation (optional, default is None).
name (str, optional): Name for the operation (optional, default is None).
For more information, please refer to :ref:`api_guide_Name`.
For more information, please refer to :ref:`api_guide_Name`.
Returns:
Returns:
reindex_src (Tensor): The source node index of graph edges after reindex.
- 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:
- reindex_dst (Tensor), the destination node index of graph edges after reindex.
.. code-block:: python
import paddle
- 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.
This API is mainly used in Graph Learning domain, which should be used
This API is mainly used in Graph Learning domain, which should be used
in conjunction with `graph_sample_neighbors` API. And the main purpose
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
is to reindex the ids information of the input nodes, and return the
corresponding graph edges after reindex.
corresponding graph edges after reindex.
**Notes**:
Take input nodes x = [0, 1, 2] as an example. For graph A, suppose we have neighbors = [8, 9, 0, 4, 7, 6, 7], and count = [2, 3, 2],
The number in x should be unique, otherwise it would cause potential errors.
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]. For graph B,
We support multi-edge-types neighbors reindexing in reindex_heter_graph api.
suppose we have neighbors = [0, 2, 3, 5, 1], and count = [1, 3, 1], then we know that the neighbors of 0 is [0], the neighbors of 1 is [2, 3, 5],
We will reindex all the nodes from 0.
and the neighbors of 3 is [1]. We will get following outputs: reindex_src: [3, 4, 0, 5, 6, 7, 6, 0, 2, 8, 9, 1], reindex_dst: [0, 0, 1, 1, 1, 2, 2, 0, 1, 1, 1, 2]
and out_nodes: [0, 1, 2, 8, 9, 4, 7, 6, 3, 5].
Take input nodes x = [0, 1, 2] as an example.
For graph A, suppose we have neighbors = [8, 9, 0, 4, 7, 6, 7], and count = [2, 3, 2],
Note:
then we know that the neighbors of 0 is [8, 9], the neighbors of 1
The number in x should be unique, otherwise it would cause potential errors. We support multi-edge-types neighbors reindexing in reindex_heter_graph api. We will reindex all the nodes from 0.
is [0, 4, 7], and the neighbors of 2 is [6, 7].
For graph B, suppose we have neighbors = [0, 2, 3, 5, 1], and count = [1, 3, 1],
then we know that the neighbors of 0 is [0], the neighbors of 1 is [2, 3, 5],
