BoxEL

class mowl.models.BoxEL(dataset, embed_dim=50, min_bounds=(0.0001, 0.2), delta_bounds=(-0.1, 0), relation_bounds=(-0.1, 0.1), scaling_bounds=(0.9, 1.1), temperature=1.0, learning_rate=0.001, batch_size=32768, model_filepath=None, device='cpu', neg_sampling_gcis=None)

Bases: EmbeddingELModel

Implementation based on [xiong2022].

This model uses box embeddings where each class is represented as an axis-aligned box defined by a minimum point and a delta (size) vector.

Methods Summary

init_module()

Methods Documentation

init_module()