TransE

class ampligraph.latent_features.layers.scoring.TransE(*args: Any, **kwargs: Any)

Translating Embeddings (TransE) scoring layer.

The model as described in [BUGD+13].

The scoring function of TransE computes a similarity between the embedding of the subject \(\mathbf{e}_{sub}\) translated by the embedding of the predicate \(\mathbf{e}_{pred}\), and the embedding of the object \(\mathbf{e}_{obj}\), using the \(L_1\) or \(L_2\) norm \(||\cdot||\) (default: \(L_1\)):

\[f_{TransE}=-||\mathbf{e}_{sub} + \mathbf{e}_{pred} - \mathbf{e}_{obj}||\]

Such scoring function is then used on positive and negative triples \(t^+, t^-\) in the loss function.

Attributes

class_params
external_params
name

Methods

__init__(k)	Initializes the scoring layer.
get_config()

__init__(k)

Initializes the scoring layer.

Parameters

• k (int) – Embedding size.

• max_rel_size (int) – This value specifies the number of relations in the KG. It is essential only for RotatE scoring layer (default: None).

get_config()