GOOD.networks.models.CoralNN

GIN and GIN-virtual implementation of the Deep Coral algorithm from “Deep CORAL: Correlation Alignment for Deep Domain Adaptation” paper

Classes

Coral_GIN(config)

The Graph Neural Network modified from the "Deep CORAL: Correlation Alignment for Deep Domain Adaptation" paper and "How Powerful are Graph Neural Networks?" paper.

Coral_vGIN(config)

The Graph Neural Network modified from the "Deep CORAL: Correlation Alignment for Deep Domain Adaptation" paper and "Neural Message Passing for Quantum Chemistry" paper.
class GOOD.networks.models.CoralNN.Coral_GIN(config: Union[CommonArgs, Munch])[source]

Bases: GNNBasic

The Graph Neural Network modified from the “Deep CORAL: Correlation Alignment for Deep Domain Adaptation” paper and “How Powerful are Graph Neural Networks?” paper.

Parameters

config (Union[CommonArgs, Munch]) – munchified dictionary of args (config.model.dim_hidden, config.model.model_layer, config.dataset.dim_node, config.dataset.num_classes, config.dataset.dataset_type)

forward(*args, **kwargs) → Tensor[source]

The Deep Coral-GIN model implementation.

Parameters

  • *args (list) – argument list for the use of arguments_read. Refer to arguments_read

  • **kwargs (dict) – key word arguments for the use of arguments_read. Refer to arguments_read

Returns (Tensor):

[label predictions, features]

class GOOD.networks.models.CoralNN.Coral_vGIN(config: Union[CommonArgs, Munch])[source]

Bases: Coral_GIN

The Graph Neural Network modified from the “Deep CORAL: Correlation Alignment for Deep Domain Adaptation” paper and “Neural Message Passing for Quantum Chemistry” paper.

Parameters

config (Union[CommonArgs, Munch]) – munchified dictionary of args (config.model.dim_hidden, config.model.model_layer, config.dataset.dim_node, config.dataset.num_classes, config.dataset.dataset_type, config.model.dropout_rate)