UniformStrategy

class KGE.ns_strategy.UniformStrategy[source]

Bases: KGE.ns_strategy.NegativeSampler

An implementation of uniform negative sampling

Uniform sampling is the most simple negative sampling strategy, usually is the default setting of knowledge graph embedding models. It sample entities from all entites with uniform distribution, and replaces either head or tail entity.

Methods Summary

__call__(X, negative_ratio, side)

perform negative sampling

Methods Documentation

__call__(X, negative_ratio, side)[source]

perform negative sampling

Parameters
  • X (tf.Tensor) – positive triplets to be corrupt.

  • negative_ratio (int) – number of negative sample.

  • side (str) – corrup from which side, can be 'h' or 't'

Returns

sampling entities

Return type

tf.Tensor

__init__(sample_pool)[source]

Initialize UniformStrategy negative sampler.

Parameters

sample_pool (tf.Tensor) – entities pool that used to sample.

__new__(*args, **kwargs)