dicee.models.octonion

Classes

OMult	Base class for all Knowledge Graph Embedding models.
ConvO	Base class for all Knowledge Graph Embedding models.
AConvO	Additive Convolutional Octonion Knowledge Graph Embeddings

Functions

octonion_mul(*, O_1, O_2)
octonion_mul_norm(*, O_1, O_2)

Module Contents

dicee.models.octonion.octonion_mul(*, O_1, O_2)

dicee.models.octonion.octonion_mul_norm(*, O_1, O_2)

class dicee.models.octonion.OMult(args)

Bases: dicee.models.base_model.BaseKGE

Base class for all Knowledge Graph Embedding models.

Inherits the Lightning training loop from BaseKGELightning and adds the embedding tables, normalisation / dropout layers, and the routing logic that dispatches forward() calls to the appropriate scoring method.

Sub-classes must implement at minimum:

• forward_triples() — score a batch of (h, r, t) triples.

• forward_k_vs_all() — score a (h, r) batch against every entity.

Parameters:

args (dict) – Flat configuration dictionary produced by vars(argparse.Namespace). Required keys: embedding_dim, num_entities, num_relations, learning_rate (or lr), optim, scoring_technique.

name = 'OMult'

static octonion_normalizer(emb_rel_e0, emb_rel_e1, emb_rel_e2, emb_rel_e3, emb_rel_e4, emb_rel_e5, emb_rel_e6, emb_rel_e7)

score(head_ent_emb: torch.FloatTensor, rel_ent_emb: torch.FloatTensor, tail_ent_emb: torch.FloatTensor)

k_vs_all_score(bpe_head_ent_emb, bpe_rel_ent_emb, E)

forward_k_vs_all(x)

Completed. Given a head entity and a relation (h,r), we compute scores for all possible triples,i.e., [score(h,r,x)|x in Entities] => [0.0,0.1,…,0.8], shape=> (1, |Entities|) Given a batch of head entities and relations => shape (size of batch,| Entities|)

class dicee.models.octonion.ConvO(args: dict)

Bases: dicee.models.base_model.BaseKGE

Base class for all Knowledge Graph Embedding models.

Inherits the Lightning training loop from BaseKGELightning and adds the embedding tables, normalisation / dropout layers, and the routing logic that dispatches forward() calls to the appropriate scoring method.

Sub-classes must implement at minimum:

• forward_triples() — score a batch of (h, r, t) triples.

• forward_k_vs_all() — score a (h, r) batch against every entity.

Parameters:

args (dict) – Flat configuration dictionary produced by vars(argparse.Namespace). Required keys: embedding_dim, num_entities, num_relations, learning_rate (or lr), optim, scoring_technique.

name = 'ConvO'

conv2d

fc_num_input

fc1

bn_conv2d

norm_fc1

feature_map_dropout

static octonion_normalizer(emb_rel_e0, emb_rel_e1, emb_rel_e2, emb_rel_e3, emb_rel_e4, emb_rel_e5, emb_rel_e6, emb_rel_e7)

residual_convolution(O_1, O_2)

forward_triples(x: torch.Tensor) → torch.Tensor

Score a batch of (head, relation, tail) index triples.

Parameters:

x (torch.LongTensor) – Shape (batch_size, 3) integer tensor where each row is [head_idx, relation_idx, tail_idx].

Returns:

Shape (batch_size,) triple scores.

Return type:

torch.FloatTensor

forward_k_vs_all(x: torch.Tensor)

Given a head entity and a relation (h,r), we compute scores for all entities. [score(h,r,x)|x in Entities] => [0.0,0.1,…,0.8], shape=> (1, |Entities|) Given a batch of head entities and relations => shape (size of batch,| Entities|)

class dicee.models.octonion.AConvO(args: dict)

Bases: dicee.models.base_model.BaseKGE

Additive Convolutional Octonion Knowledge Graph Embeddings

name = 'AConvO'

conv2d

fc_num_input

fc1

bn_conv2d

norm_fc1

feature_map_dropout

static octonion_normalizer(emb_rel_e0, emb_rel_e1, emb_rel_e2, emb_rel_e3, emb_rel_e4, emb_rel_e5, emb_rel_e6, emb_rel_e7)

residual_convolution(O_1, O_2)

forward_triples(x: torch.Tensor) → torch.Tensor

Score a batch of (head, relation, tail) index triples.

Parameters:

x (torch.LongTensor) – Shape (batch_size, 3) integer tensor where each row is [head_idx, relation_idx, tail_idx].

Returns:

Shape (batch_size,) triple scores.

Return type:

torch.FloatTensor

forward_k_vs_all(x: torch.Tensor)

Given a head entity and a relation (h,r), we compute scores for all entities. [score(h,r,x)|x in Entities] => [0.0,0.1,…,0.8], shape=> (1, |Entities|) Given a batch of head entities and relations => shape (size of batch,| Entities|)