nsl.keras.layers.make_missing_neighbor_inputs

View source on GitHub

Makes additional inputs for neighbor features if necessary.

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.

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