LineaREInteraction

class LineaREInteraction(p: int, power_norm: bool = False)[source]

Bases: NormBasedInteraction[Tensor, tuple[Tensor, Tensor, Tensor], Tensor]

The LineaRE interaction described by [peng2020].

It is given by

\[\mathbf{h} \odot \mathbf{r}_h - \mathbf{t} \odot \mathbf{r}_t + \mathbf{r}\]

where \(\mathbf{r}_{h}, \mathbf{r}, \mathbf{r}_{t} \in \mathbb{R}^d\) are relation-specific terms, and \(\mathbf{h}, \mathbf{t} \in \mathbb{R}^n\) the head and tail entity representation.

Note

the original paper only describes the interaction for \(L_1\) norm, but we extend it to the general \(L_p\) norm as well as its powered variant.

Note

This interaction is equivalent to TripleREInteraction without the \(u\) term.

Initialize the norm-based interaction function.

Parameters:

p (int) – The norm used with torch.linalg.vector_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

relation_shape

The symbolic shapes for relation representations

Methods Summary

forward(h, r, t)

Evaluate the interaction function.

Attributes Documentation

relation_shape: Sequence[str] = ('d', 'd', 'd'): The symbolic shapes for relation representations

Methods Documentation

forward(h: Tensor, r: tuple[Tensor, Tensor, Tensor], t: Tensor) → Tensor[source]

Evaluate the interaction function.