LCWALitModule

class LCWALitModule(dataset='nations', dataset_kwargs=None, mode=None, model='distmult', model_kwargs=None, batch_size=32, learning_rate=0.001, label_smoothing=0.0, optimizer=None, optimizer_kwargs=None)[source]

Bases: LitModule

A PyTorch Lightning module for training a model with LCWA training loop.

See also

https://github.com/pykeen/pykeen/pull/905

Create the lightning module.

Parameters

  • dataset (Union[str, Dataset, Type[Dataset], None]) – the dataset, or a hint thereof

  • dataset_kwargs (Optional[Mapping[str, Any]]) – additional keyword-based parameters passed to the dataset

  • mode (Optional[Literal[‘training’, ‘validation’, ‘testing’]]) – the inductive mode; defaults to transductive training

  • model (Union[str, Model, Type[Model], None]) – the model, or a hint thereof

  • model_kwargs (Optional[Mapping[str, Any]]) – additional keyword-based parameters passed to the model

  • batch_size (int) – the training batch size

  • learning_rate (float) – the learning rate

  • label_smoothing (float) – the label smoothing

  • optimizer (Union[str, Optimizer, Type[Optimizer], None]) – the optimizer, or a hint thereof

  • optimizer_kwargs (Optional[Mapping[str, Any]]) – additional keyword-based parameters passed to the optimizer. should not contain lr, or params.