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

\loadmathjax

A Crystal Graph Convolutional layer as presented by Xie & Grossman (2018).

Mode: single, disjoint.

This layer expects a sparse adjacency matrix.

This layer computes for each node \mjeqni: \mjdeqn H_i = X_i + \sum\limits_j \in \mathcalN(i) \sigma \left( z_ij W^(f) + b^(f) \right) \odot g \left( z_ij W^(s) + b^(s) \right) where \mjeqnz_ij = X_i \| X_j \| E_ij , \mjeqn\sigma is a sigmoid activation, and \mjeqng is the activation function (defined by the activation argument).

Input

Node features of shape (N, F);
Binary adjacency matrix of shape (N, N).
Edge features of shape (num_edges, S).

Output

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

layer_crystal_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,
  ...
)

`channels`	integer, 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.