A SortPool layer as described by Zhang et al. This layers takes a graph signal \mjeqn\mathbfX and returns the topmost k rows according to the last column. If \mjeqn\mathbfX has less than k rows, the result is zero-padded to k.
Mode: single, disjoint, batch.
Input
Node features of shape ([batch], N, F)
;
Graph IDs of shape (N, )
(only in disjoint mode);
Output
Pooled node features of shape (batch, k, F)
(if single mode, shape will
be (1, k, F)
).
1 | layer_sort_pool(object, k, ...)
|
k |
integer, number of nodes to keep |
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.