complex_models

Attributes

seed

Classes

`Complex`	Base class for all neural network modules.
`ConEx`	Convolutional Complex Knowledge Graph Embeddings

Module Contents

complex_models.seed = 1

class complex_models.Complex(param)

Bases: torch.nn.Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:: training (bool) – Boolean represents whether this module is in training or evaluation mode.

name = 'Complex'

param

embedding_dim

num_entities

num_relations

Er

Rr

Ei

Ri

input_dropout

bn0

bn1

loss

init()

forward_head_batch(e1_idx, rel_idx)

forward_head_and_loss(e1_idx, rel_idx, targets)

get_embeddings()

abstract forward_triples(*args, **kwargs)

abstract forward_triples_and_loss(*args, **kwargs)

class complex_models.ConEx(params=None)

Bases: torch.nn.Module

Convolutional Complex Knowledge Graph Embeddings

name = 'ConEx'

loss

param

embedding_dim

num_entities

num_relations

kernel_size

num_of_output_channels

emb_ent_real

emb_ent_i

emb_rel_real

emb_rel_i

input_dp_ent_real

input_dp_ent_i

input_dp_rel_real

input_dp_rel_i

bn_ent_real

bn_ent_i

bn_rel_real

bn_rel_i

conv1

fc_num_input

fc

bn_conv1

bn_conv2

feature_map_dropout

residual_convolution(C_1, C_2)

forward_head_batch(*, e1_idx, rel_idx): 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|)

forward_head_and_loss(e1_idx, rel_idx, targets)

init()

get_embeddings()

forward_triples(*, e1_idx, rel_idx, e2_idx)

forward_triples_and_loss(e1_idx, rel_idx, e2_idx, targets)