layer_graph_conv: GraphConv

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

Description

\loadmathjax

A graph convolutional layer (GCN) as presented by Kipf & Welling (2016).

Mode: single, disjoint, mixed, batch.

This layer computes: \mjdeqn Z = \hat D^-1/2 \hat A \hat D^-1/2 X W + b where \mjeqn \hat A = A + I is the adjacency matrix with added self-loops and \mjeqn\hat D is its degree matrix.

Input

• Node features of shape ([batch], N, F);

• Modified Laplacian of shape ([batch], N, N); can be computed with spektral.utils.convolution.localpooling_filter.

Output

• Node features with the same shape as the input, but with the last dimension changed to channels.

Usage

layer_graph_conv(
  object,
  channels,
  activation = NULL,
  use_bias = TRUE,
  kernel_initializer = "glorot_uniform",
  bias_initializer = "zeros",
  kernel_regularizer = NULL,
  bias_regularizer = NULL,
  activity_regularizer = NULL,
  kernel_constraint = NULL,
  bias_constraint = NULL,
  ...
)

Arguments

channels	number of output channels
activation	activation function to use
use_bias	bool, add a bias vector to the output
kernel_initializer	initializer for the weights
bias_initializer	initializer for the bias vector
kernel_regularizer	regularization applied to the weights
bias_regularizer	regularization applied to the bias vector
activity_regularizer	regularization applied to the output
kernel_constraint	constraint applied to the weights
bias_constraint	constraint applied to the bias vector.

rdinnager/rspektral documentation built on June 12, 2021, 1:26 a.m.