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

\loadmathjax

A node-attention global pooling layer. Pools a graph by learning attention coefficients to sum node features.

This layer computes: \mjdeqn\alpha = \textrmsoftmax( \boldsymbolX \boldsymbola); \\boldsymbolX' = \sum\limits_i=1^N \alpha_i \cdot \boldsymbolX _ i where \mjeqn\boldsymbola \in \mathbbR^F is a trainable vector. Note that the softmax is applied across nodes, and not across features.

Mode: single, disjoint, mixed, 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, F) (if single mode, shape will be (1, F)).

layer_global_attn_sum_pool(
  object,
  attn_kernel_initializer = "glorot_uniform",
  attn_kernel_regularizer = NULL,
  attn_kernel_constraint = NULL,
  ...
)

`attn_kernel_initializer`	initializer for the attention weights
`attn_kernel_regularizer`	regularization applied to the attention kernel matrix
`attn_kernel_constraint`	constraint applied to the attention kernel matrix