GOOD.networks.models.MixupGNN

GIN and GIN-virtual implementation of the Mixup algorithm from “Mixup for Node and Graph Classification” paper

Classes

Mixup_GIN(config)	The Graph Neural Network modified from the "Mixup for Node and Graph Classification" paper and "How Powerful are Graph Neural Networks?" paper.
Mixup_vGIN(config)	The Graph Neural Network modified from the "Mixup for Node and Graph Classification" paper and "Neural Message Passing for Quantum Chemistry" paper.

class GOOD.networks.models.MixupGNN.Mixup_GIN(config: Union[CommonArgs, Munch])

Bases: GNNBasic

The Graph Neural Network modified from the “Mixup for Node and Graph Classification” 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

The Mixup-GIN model implementation.

Parameters

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

• **kwargs (dict) –

  1. dictionary of OOD args (kwargs.ood_algorithm) (2) key word arguments for the use of arguments_read. Refer to arguments_read

Returns (Tensor):

label predictions

class GOOD.networks.models.MixupGNN.Mixup_vGIN(config: Union[CommonArgs, Munch])

Bases: Mixup_GIN

The Graph Neural Network modified from the “Mixup for Node and Graph Classification” 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)