DistMultLiteralGated
- class DistMultLiteralGated(triples_factory, embedding_dim=50, input_dropout=0.0, **kwargs)[source]
Bases:
pykeen.models.multimodal.base.LiteralModel
An implementation of the LiteralE model with thhe Gated DistMult interaction from [kristiadi2018].
This model is different from
pykeen.models.DistMultLiteral
because it uses a gate (like found in LSTMs) instead of a LinearDropout module.This gate implements the full \(g\) function described in the LiteralE paper (see equation 4).
Initialize the model.
- Parameters
triples_factory (
TriplesNumericLiteralsFactory
) – the (training) triples factoryembedding_dim (
int
) – the embedding dimensioninput_dropout (
float
) – the input dropout, cf.DistMultCombination.__init__()
kwargs – additional keyword-based parameters passed to
LiteralModel.__init__()
Attributes Summary
The default strategy for optimizing the model's hyper-parameters
The default parameters for the default loss function class
Attributes Documentation