layer_sag_pool: SAGPool
In rdinnager/rspektral: What the Package Does (One Line, Title Case)

\loadmathjax

A self-attention graph pooling layer as presented by Lee et al. (2019).

Mode: single, disjoint.

This layer computes the following operations:

\mjdeqn\boldsymbol

y = \textrmGNN(\boldsymbolA, \boldsymbolX); \;\;\;\;\boldsymboli = \textrmrank(\boldsymboly, K); \;\;\;\;\boldsymbolX' = (\boldsymbolX \odot \textrmtanh(\boldsymboly))_\boldsymboli; \;\;\;\;\boldsymbolA' = \boldsymbolA _ \boldsymboli, \boldsymboli

where \mjeqn \textrmrank(\boldsymboly, K) returns the indices of the top K values of \mjeqn\boldsymboly, and \mjeqn\textrmGNN consists of one GraphConv layer with no activation. \mjeqnK is defined for each graph as a fraction of the number of nodes.

This layer temporarily makes the adjacency matrix dense in order to compute \mjeqn\boldsymbolA'. If memory is not an issue, considerable speedups can be achieved by using dense graphs directly. Converting a graph from sparse to dense and back to sparse is an expensive operation.

Input

Node features of shape (N, F);
Binary adjacency matrix of shape (N, N);
Graph IDs of shape (N, ) (only in disjoint mode);

Output

Reduced node features of shape (ratio * N, F);
Reduced adjacency matrix of shape (ratio * N, ratio * N);
Reduced graph IDs of shape (ratio * N, ) (only in disjoint mode);
If return_mask=True, the binary pooling mask of shape (ratio * N, ).

layer_sag_pool(
  object,
  ratio,
  return_mask = FALSE,
  sigmoid_gating = FALSE,
  kernel_initializer = "glorot_uniform",
  kernel_regularizer = NULL,
  kernel_constraint = NULL,
  ...
)

`ratio`	float between 0 and 1, ratio of nodes to keep in each graph
`return_mask`	boolean, whether to return the binary mask used for pooling
`sigmoid_gating`	boolean, use a sigmoid gating activation instead of a tanh
`kernel_initializer`	initializer for the weights
`kernel_regularizer`	regularization applied to the weights
`kernel_constraint`	constraint applied to the weights