TransHInteraction¶
-
class
TransHInteraction
(p, power_norm=False)[source]¶ Bases:
pykeen.nn.modules.TranslationalInteraction
[torch.FloatTensor
,Tuple
[torch.FloatTensor
,torch.FloatTensor
],torch.FloatTensor
]A stateful module for the TransH interaction function.
Initialize the translational interaction function.
- Parameters
p (
int
) – The norm used withtorch.norm()
. Typically is 1 or 2.power_norm (
bool
) – Whether to use the p-th power of the L_p norm. It has the advantage of being differentiable around 0, and numerically more stable.
Attributes Summary
The symbolic shapes for relation representations
Methods Summary
func
(w_r, d_r, t, p[, power_norm])Evaluate the DistMult interaction function.
Attributes Documentation
Methods Documentation
-
func
(w_r, d_r, t, p, power_norm=False)¶ Evaluate the DistMult interaction function.
- Parameters
h (
FloatTensor
) – shape: (batch_size, num_heads, 1, 1, dim) The head representations.w_r (
FloatTensor
) – shape: (batch_size, 1, num_relations, 1, dim) The relation normal vector representations.d_r (
FloatTensor
) – shape: (batch_size, 1, num_relations, 1, dim) The relation difference vector representations.t (
FloatTensor
) – shape: (batch_size, 1, 1, num_tails, dim) The tail representations.p (
int
) – The p for the norm. cf. torch.norm.power_norm (
bool
) – Whether to return \(|x-y|_p^p\).
- Return type
FloatTensor
- Returns
shape: (batch_size, num_heads, num_relations, num_tails) The scores.