Crate tranz 

tranz

Point-embedding knowledge graph completion models.

Entities are points in vector space. Relations are transformations (translation, rotation, diagonal scaling). Lower distance between transform(head, relation) and tail indicates a more likely triple.

Models

• TransE: head + relation ~ tail (Bordes et al., 2013)
• RotatE: head * relation ~ tail in complex space (Sun et al., 2019)
• ComplEx: Hermitian dot product in complex space (Trouillon et al., 2016)
• DistMult: diagonal bilinear in real space (Yang et al., 2015)
• temporal::TComplEx: ComplEx over quads (h, r, t, τ) with timestamp embeddings (Lacroix et al., 2020)

Feature flags

• rand (default): enables random initialization via Model::new().
• burn-ndarray: enables training via the burn_train module on the ndarray (CPU) backend.
• burn-wgpu: training on the WGPU backend (Metal/Vulkan/WebGPU).

Modules

burn_temporal

Burn trainer for crate::temporal::TComplEx.

burn_train

Burn-based training for KGE models.

dataset

Dataset loading for KGE benchmark triple files.

eval

Link prediction evaluation with filtered ranking.

io

Embedding import/export.

query

Fuzzy logic query answering (CQD-Beam).

temporal

Temporal knowledge graphs: quads (head, relation, tail, timestamp).

Structs

ComplEx

ComplEx: complex bilinear model.

DistMult

DistMult: diagonal bilinear model in real space.

EnsembledScorer

Ensemble scorer that averages scores from multiple models.

RotatE

RotatE: rotation in complex space.

TransE

TransE: translational distance model.

Enums

Error

Errors from tranz operations.

Traits

Scorer

Trait for scoring knowledge graph triples.