Join us at TensorFlow World, Oct 28-31. Use code TF20 for 20% off select passes. Register now

nsl.keras.layers.make_missing_neighbor_inputs

View source on GitHub

Makes additional inputs for neighbor features if necessary.

nsl.keras.layers.make_missing_neighbor_inputs(
    neighbor_config,
    inputs,
    weight_dtype=tf.float32
)

Args:

  • neighbor_config: An instance of configs.GraphNeighborConfig specifying the number of neighbors and how neighbor features should be named.
  • inputs: Dictionary of input tensors that may be missing neighbor features. The keys are the features names. See utils.unpack_neighbor_features for expected names of neighbor features and weights.
  • weight_dtype: tf.Dtype for neighbors weights. Defaults to tf.float32.

Returns:

A dictionary of neighbor feature and weight tensors that do not already exist in inputs. The keys are specified according to neighbor_config.