gigl.src.common.models.layers.decoder

Classes

DecoderType	Generic enumeration.
LinkPredictionDecoder	Base class for all neural network modules.

Module Contents

class gigl.src.common.models.layers.decoder.DecoderType

Bases: enum.Enum

Generic enumeration.

Derive from this class to define new enumerations.

classmethod get_all_criteria()

Return type:

list[str]

hadamard_MLP = 'hadamard_MLP'

inner_product = 'inner_product'

class gigl.src.common.models.layers.decoder.LinkPredictionDecoder(decoder_type=DecoderType.inner_product, decoder_channel_list=None, act=F.relu, act_first=False, bias=False, plain_last=False, norm=None)

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) -> None:
        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.

Parameters:

• decoder_type (DecoderType)

• decoder_channel_list (Optional[list[int]])

• act (Union[str, Callable, None])

• act_first (bool)

• bias (Union[bool, list[bool]])

• plain_last (bool)

• norm (Optional[Union[str, Callable]])

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(query_embeddings, candidate_embeddings)

Return type:

torch.Tensor

decoder_channel_list = None

decoder_type