DistMult

class ampligraph.latent_features.DistMult(k=100, eta=2, epochs=100, batches_count=100, seed=0, embedding_model_params={'corrupt_sides': ['s+o'], 'negative_corruption_entities': 'all', 'normalize_ent_emb': False}, optimizer='adam', optimizer_params={'lr': 0.0005}, loss='nll', loss_params={}, regularizer=None, regularizer_params={}, verbose=False)

The DistMult model

The model as described in [YYH+14].

The bilinear diagonal DistMult model uses the trilinear dot product as scoring function:

\[f_{DistMult}=\langle \mathbf{r}_p, \mathbf{e}_s, \mathbf{e}_o \rangle\]

where \(\mathbf{e}_{s}\) is the embedding of the subject, \(\mathbf{r}_{p}\) the embedding of the predicate and \(\mathbf{e}_{o}\) the embedding of the object.

Examples

>>> import numpy as np
>>> from ampligraph.latent_features import DistMult
>>> model = DistMult(batches_count=1, seed=555, epochs=20, k=10, loss='pairwise',
>>>         loss_params={'margin':5})
>>> X = np.array([['a', 'y', 'b'],
>>>               ['b', 'y', 'a'],
>>>               ['a', 'y', 'c'],
>>>               ['c', 'y', 'a'],
>>>               ['a', 'y', 'd'],
>>>               ['c', 'y', 'd'],
>>>               ['b', 'y', 'c'],
>>>               ['f', 'y', 'e']])
>>> model.fit(X)
>>> model.predict(np.array([['f', 'y', 'e'], ['b', 'y', 'd']]))
[-0.13863425, -0.09917116]
>>> model.get_embeddings(['f','e'], embedding_type='entity')
array([[ 0.10137264, -0.28248304,  0.6153027 , -0.13133956, -0.11675504,
-0.37876177,  0.06027773, -0.26390398,  0.254603  ,  0.1888549 ],
[-0.6467299 , -0.13729756,  0.3074872 ,  0.16966867, -0.04098966,
 0.25289047, -0.2212451 , -0.6527815 ,  0.5657673 , -0.03876532]],
dtype=float32)

Methods

__init__([k, eta, epochs, batches_count, …]) Initialize an EmbeddingModel
fit(X[, early_stopping, early_stopping_params]) Train an DistMult.
get_embeddings(entities[, embedding_type]) Get the embeddings of entities or relations.
predict(X[, from_idx, get_ranks]) Predict the scores of triples using a trained embedding model.
__init__(k=100, eta=2, epochs=100, batches_count=100, seed=0, embedding_model_params={'corrupt_sides': ['s+o'], 'negative_corruption_entities': 'all', 'normalize_ent_emb': False}, optimizer='adam', optimizer_params={'lr': 0.0005}, loss='nll', loss_params={}, regularizer=None, regularizer_params={}, verbose=False)

Initialize an EmbeddingModel

Also creates a new Tensorflow session for training.
Parameters:
  • k (int) – Embedding space dimensionality
  • eta (int) – The number of negatives that must be generated at runtime during training for each positive.
  • epochs (int) – The iterations of the training loop.
  • batches_count (int) – The number of batches in which the training set must be split during the training loop.
  • seed (int) – The seed used by the internal random numbers generator.
  • embedding_model_params (dict) –

    DistMult-specific hyperparams, passed to the model as a dictionary.

    Supported keys:

    • ’normalize_ent_emb’ (bool): flag to indicate whether to normalize entity embeddings after each batch update (default: False).
    • ’negative_corruption_entities’ - Entities to be used for generation of corruptions while training. It can take the following values : all (default: all entities), batch (entities present in each batch), list of entities or an int (which indicates how many entities that should be used for corruption generation).
    • corrupt_sides : Specifies how to generate corruptions for training. Takes values s, o, s+o or any combination passed as a list

    Example: embedding_model_params={'normalize_ent_emb': False}

  • optimizer (string) – The optimizer used to minimize the loss function. Choose between ‘sgd’, ‘adagrad’, ‘adam’, ‘momentum’.
  • optimizer_params (dict) –

    Arguments specific to the optimizer, passed as a dictionary.

    Supported keys:

    • ’lr’ (float): learning rate (used by all the optimizers). Default: 0.1.
    • ’momentum’ (float): learning momentum (only used when optimizer=momentum). Default: 0.9.

    Example: optimizer_params={'lr': 0.01}

  • loss (string) –

    The type of loss function to use during training.

    • pairwise the model will use pairwise margin-based loss function.
    • nll the model will use negative loss likelihood.
    • absolute_margin the model will use absolute margin likelihood.
    • self_adversarial the model will use adversarial sampling loss function.
    • multiclass_nll the model will use multiclass nll loss. Switch to multiclass loss defined in [aC15] by passing ‘corrupt_sides’ as [‘s’,’o’] to embedding_model_params. To use loss defined in [KBK17] pass ‘corrupt_sides’ as ‘o’ to embedding_model_params
  • loss_params (dict) –

    Dictionary of loss-specific hyperparameters. See loss functions documentation for additional details.

    Example: optimizer_params={'lr': 0.01} if loss='pairwise'.

  • regularizer (string) –

    The regularization strategy to use with the loss function.

    • None: the model will not use any regularizer (default)
    • ’LP’: the model will use L1, L2 or L3 based on the value of regularizer_params['p'] (see below).
  • regularizer_params (dict) –

    Dictionary of regularizer-specific hyperparameters. See the regularizers documentation for additional details.

    Example: regularizer_params={'lambda': 1e-5, 'p': 2} if regularizer='LP'.

  • verbose (bool) – Verbose mode
fit(X, early_stopping=False, early_stopping_params={})

Train an DistMult.

The model is trained on a training set X using the training protocol described in [TWR+16].
Parameters:
  • X (ndarray, shape [n, 3]) – The training triples
  • early_stopping (bool) –

    Flag to enable early stopping (default:False).

    If set to True, the training loop adopts the following early stopping heuristic:

    • The model will be trained regardless of early stopping for burn_in epochs.
    • Every check_interval epochs the method will compute the metric specified in criteria.

    If such metric decreases for stop_interval checks, we stop training early.

    Note the metric is computed on x_valid. This is usually a validation set that you held out.

    Also, because criteria is a ranking metric, it requires generating negatives. Entities used to generate corruptions can be specified, as long as the side(s) of a triple to corrupt. The method supports filtered metrics, by passing an array of positives to x_filter. This will be used to filter the negatives generated on the fly (i.e. the corruptions).

    Note

    Keep in mind the early stopping criteria may introduce a certain overhead (caused by the metric computation). The goal is to strike a good trade-off between such overhead and saving training epochs.

    A common approach is to use MRR unfiltered:

    early_stopping_params={x_valid=X['valid'], 'criteria': 'mrr'}

    Note the size of validation set also contributes to such overhead. In most cases a smaller validation set would be enough.

  • early_stopping_params (dictionary) –

    Dictionary of hyperparameters for the early stopping heuristics.

    The following string keys are supported:

    • ’x_valid’: ndarray, shape [n, 3] : Validation set to be used for early stopping.
    • ’criteria’: string : criteria for early stopping ‘hits10’, ‘hits3’, ‘hits1’ or ‘mrr’(default).
    • ’x_filter’: ndarray, shape [n, 3] : Positive triples to use as filter if a ‘filtered’ early stopping criteria is desired (i.e. filtered-MRR if ‘criteria’:’mrr’). Note this will affect training time (no filter by default).
    • ’burn_in’: int : Number of epochs to pass before kicking in early stopping (default: 100).
    • check_interval’: int : Early stopping interval after burn-in (default:10).
    • ’stop_interval’: int : Stop if criteria is performing worse over n consecutive checks (default: 3)
    • ’corruption_entities’: List of entities to be used for corruptions. If ‘all’, it uses all entities (default: ‘all’)
    • ’corrupt_side’: Specifies which side to corrupt. ‘s’, ‘o’, ‘s+o’ (default)

    Example: early_stopping_params={x_valid=X['valid'], 'criteria': 'mrr'}
get_embeddings(entities, embedding_type='entity')

Get the embeddings of entities or relations.

Note

Use ampligraph.utils.create_tensorboard_visualizations() to visualize the embeddings with TensorBoard.

Parameters:
  • entities (array-like, dtype=int, shape=[n]) – The entities (or relations) of interest. Element of the vector must be the original string literals, and not internal IDs.
  • embedding_type (string) – If ‘entity’, the entities argument will be considered as a list of knowledge graph entities (i.e. nodes). If set to ‘relation’, they will be treated as relation types instead (i.e. predicates).
Returns:

embeddings – An array of k-dimensional embeddings.
Return type:

ndarray, shape [n, k]
predict(X, from_idx=False, get_ranks=False)

Predict the scores of triples using a trained embedding model.

The function returns raw scores generated by the model.

Note

To obtain probability estimates, use a logistic sigmoid:

>>> model.fit(X)
>>> y_pred = model.predict(np.array([['f', 'y', 'e'], ['b', 'y', 'd']]))
>>> print(y_pred)
[-0.13863425, -0.09917116]
>>> from scipy.special import expit
>>> expit(y_pred)
array([0.4653968 , 0.47522753], dtype=float32)
Parameters:
  • X (ndarray, shape [n, 3]) – The triples to score.
  • from_idx (bool) – If True, will skip conversion to internal IDs. (default: False).
  • get_ranks (bool) – Flag to compute ranks by scoring against corruptions (default: False).
Returns:

  • scores_predict (ndarray, shape [n]) – The predicted scores for input triples X.
  • rank (ndarray, shape [n]) – Ranks of the triples (only returned if get_ranks=True.