SubsetRepresentation

class SubsetRepresentation(max_id: int, shape: int | Sequence[int] | None = None, base: str | Representation | type[Representation] | None = None, base_kwargs: Mapping[str, Any] | None = None, **kwargs)[source]

Bases: Representation

A representation module, which only exposes a subset of representations of its base.

Note

At runtime, no index verification is made. Thus the only effect is based on the adjusted max_id.

Initialize the representations.

Parameters:

  • max_id (int) – The number of representations.

  • shape (OneOrSequence[int] | None) – The shape of an individual representation.

  • base (HintOrType[Representation]) – The base representation. Has to have a sufficient number of representations, i.e., at least max_id.

  • base_kwargs (OptionalKwargs) – Additional keyword arguments for the base representation.

  • kwargs – Additional keyword-based parameters passed to Representation.

Raises:

ValueError – if max_id is larger than the base representation’s max_id

Note

The parameter pair (base, base_kwargs) is used for pykeen.nn.representation_resolver

An explanation of resolvers and how to use them is given in https://class-resolver.readthedocs.io/en/latest/.