HolE

class ampligraph.compat.HolE(k=100, eta=2, epochs=100, batches_count=100, seed=0, embedding_model_params={'corrupt_sides': ['s,o'], 'negative_corruption_entities': 'all', 'norm': 1, 'normalize_ent_emb': False}, optimizer='adam', optimizer_params={'lr': 0.0005}, loss='nll', loss_params={}, regularizer=None, regularizer_params={}, initializer='xavier', initializer_params={'uniform': False}, verbose=False, model=None)

Class wrapping around the ScoringBasedEmbeddingModel with the HolE scoring function.

Attributes

name

Methods

__init__([k, eta, epochs, batches_count, ...])

Initialize the ScoringBasedEmbeddingModel with the HolE scoring function.

__init__(k=100, eta=2, epochs=100, batches_count=100, seed=0, embedding_model_params={'corrupt_sides': ['s,o'], 'negative_corruption_entities': 'all', 'norm': 1, 'normalize_ent_emb': False}, optimizer='adam', optimizer_params={'lr': 0.0005}, loss='nll', loss_params={}, regularizer=None, regularizer_params={}, initializer='xavier', initializer_params={'uniform': False}, verbose=False, model=None)

Initialize the ScoringBasedEmbeddingModel with the HolE scoring function.