DistMult

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

DistMult scoring layer.

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.

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()