InteractE: Improving Convolution-Based Knowledge Graph Embeddings by Increasing Feature Interactions

其它关于卷积知识图谱补全:
ConvR:Adaptive Convolution for Multi-Relational Learning
ConvE:Convolutional 2D Knowledge Graph Embeddings
ConvKB代码:A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network

1 介绍

1.1 引言

本篇论文是对于论文ConvE的模型进行改进,与ConvR论文类似,其都发现ConvE在实现实体entity与relation之间,进行交互时,只是进行简单的进行entity和relation之间的向量进行简单的堆积,其交互能力很低(来源于ConvR论文),大于只有20%的交互,与ConvR相比,该论文InteractE采用另外一种策略,增加其交互能力。

1.2 提高交互方法

  • feature permutation(特征进行全排类)
  • a novel feature reshaping(新型的reshape方式)
  • circular convolution(循环神经网络)

2 模型

2.1 Feature Permutation

生成 e s e_s es e r e_r er的t-random排列, P t = [ ( e s 1 , e r 1 ) , . . . . , ( e s t , e r t ) ] \mathcal P_{t} = [(e_s^1, e_r^1), ....,(e_s^t, e_r^t)] Pt=[(es1,er1),....,(est,ert)]作为一组,进行随机打乱,进行t次,每次随机打乱产生一组数据,产生t次数据,其作为输入数据的int_channel则为t,但由于所有的数据本质上是一样的,对每层进行卷积的卷积核应该一致,应该在初始时是一致的,在具体实现时采用分组卷积的形式。

2.2 Reshaping Function

InteractE: Improving Convolution-Based Knowledge Graph Embeddings by Increasing Feature Interactions_第1张图片

  • Stack

堆叠的形式,ConvE在实现时采用这种方式,其交互能力很低,只有20%,但其操作比较简单。

  • Alternate

交替形式,其采用实体的feature和关系的feature交替的方式,能有效的提高交互,交互能力有所提升。

  • Chequer

这种方式交互更加彻底,其在使用时,将其所有元组进行交替,能够更加充分。

2.3 循环卷积

常规的卷积,在使用时,边界与边界之间没有任何关系,因此提出循环卷积,在卷积的时候,使其边界之间的内容进行交互。其交互的方式是使边界 ⌊ k / 2 ⌋ \lfloor {k/2} \rfloor k/2,其中k为kernal_size。在实现时,将 ⌊ k / 2 ⌋ \lfloor {k/2} \rfloor k/2左侧内容放到右侧边界, ⌊ k / 2 ⌋ \lfloor {k/2} \rfloor k/2右侧内容放到左侧;同理下侧放到上侧,上侧放到下侧。
在这里插入图片描述
图解循环卷积:
InteractE: Improving Convolution-Based Knowledge Graph Embeddings by Increasing Feature Interactions_第2张图片

2.4 整体模型图

InteractE: Improving Convolution-Based Knowledge Graph Embeddings by Increasing Feature Interactions_第3张图片

  • 将头实体 e s 和 e r e_s和e_r eser进行全排列,进行t次全排列,产生t个通道
  • 进行reshape,采用Chequer方式进行reshape
  • 进行卷积,采用循环卷积
  • 进行全连接,映射维度为 e s e_s es的维度一致
  • 进行1-N评分,进行rank评分

2.5 评分函数

在这里插入图片描述

3 总结

InteractE: Improving Convolution-Based Knowledge Graph Embeddings by Increasing Feature Interactions_第4张图片
InteractE: Improving Convolution-Based Knowledge Graph Embeddings by Increasing Feature Interactions_第5张图片

4 代码

来源:在这

from helper import *

class InteractE(torch.nn.Module):
	"""
	Proposed method in the paper. Refer Section 6 of the paper for mode details 

	Parameters
	----------
	params:        	Hyperparameters of the model
	chequer_perm:   Reshaping to be used by the model
	
	Returns
	-------
	The InteractE model instance
		
	"""
	def __init__(self, params, chequer_perm):
		super(InteractE, self).__init__()

		self.p                  = params
		self.ent_embed		= torch.nn.Embedding(self.p.num_ent,   self.p.embed_dim, padding_idx=None); xavier_normal_(self.ent_embed.weight)
		self.rel_embed		= torch.nn.Embedding(self.p.num_rel*2, self.p.embed_dim, padding_idx=None); xavier_normal_(self.rel_embed.weight)
		self.bceloss		= torch.nn.BCELoss()

		self.inp_drop		= torch.nn.Dropout(self.p.inp_drop)
		self.hidden_drop	= torch.nn.Dropout(self.p.hid_drop)
		self.feature_map_drop	= torch.nn.Dropout2d(self.p.feat_drop)
		self.bn0		= torch.nn.BatchNorm2d(self.p.perm)

		flat_sz_h 		= self.p.k_h
		flat_sz_w 		= 2*self.p.k_w
		self.padding 		= 0

		self.bn1 		= torch.nn.BatchNorm2d(self.p.num_filt*self.p.perm)
		self.flat_sz 		= flat_sz_h * flat_sz_w * self.p.num_filt*self.p.perm

		self.bn2		= torch.nn.BatchNorm1d(self.p.embed_dim)
		self.fc 		= torch.nn.Linear(self.flat_sz, self.p.embed_dim)
		self.chequer_perm	= chequer_perm

		self.register_parameter('bias', Parameter(torch.zeros(self.p.num_ent)))
		self.register_parameter('conv_filt', Parameter(torch.zeros(self.p.num_filt, 1, self.p.ker_sz,  self.p.ker_sz))); xavier_normal_(self.conv_filt)
	#96
	def loss(self, pred, true_label=None, sub_samp=None):
		label_pos	= true_label[0]; 
		label_neg	= true_label[1:]
		loss 		= self.bceloss(pred, true_label)
		return loss

	def circular_padding_chw(self, batch, padding):
		upper_pad	= batch[..., -padding:, :]
		lower_pad	= batch[..., :padding, :]
		temp		= torch.cat([upper_pad, batch, lower_pad], dim=2)

		left_pad	= temp[..., -padding:]
		right_pad	= temp[..., :padding]
		padded		= torch.cat([left_pad, temp, right_pad], dim=3)
		return padded

	def forward(self, sub, rel, neg_ents, strategy='one_to_x'):
		sub_emb		= self.ent_embed(sub)
		rel_emb		= self.rel_embed(rel)
		comb_emb	= torch.cat([sub_emb, rel_emb], dim=1)
		chequer_perm	= comb_emb[:, self.chequer_perm]
		stack_inp	= chequer_perm.reshape((-1, self.p.perm, 2*self.p.k_w, self.p.k_h))
		stack_inp	= self.bn0(stack_inp)
		x		= self.inp_drop(stack_inp)
		x		= self.circular_padding_chw(x, self.p.ker_sz//2)
		x		= F.conv2d(x, self.conv_filt.repeat(self.p.perm, 1, 1, 1), padding=self.padding, groups=self.p.perm)
		x		= self.bn1(x)
		x		= F.relu(x)
		x		= self.feature_map_drop(x)
		x		= x.view(-1, self.flat_sz)
		x		= self.fc(x)
		x		= self.hidden_drop(x)
		x		= self.bn2(x)
		x		= F.relu(x)

		if strategy == 'one_to_n':
			x = torch.mm(x, self.ent_embed.weight.transpose(1,0))
			x += self.bias.expand_as(x)
		else:
			x = torch.mul(x.unsqueeze(1), self.ent_embed(neg_ents)).sum(dim=-1)
			x += self.bias[neg_ents]

		pred	= torch.sigmoid(x)

		return pred

你可能感兴趣的:(知识图谱补全,深度学习,机器学习,计算机视觉)