检索结果-内蒙古大学图书馆

Enhancing knowledge graph embedding by composite neighbors for link prediction

COMPUTING 2020年第12期102卷 2587-2606页

作者： Wang, Kai Liu, Yu Xu, Xiujuan Sheng, Quan Z. Dalian Univ Technol Sch Software Key Lab Ubiquitous Network & Serv Software Liaoni Dalian 116023 Peoples R China Macquarie Univ Dept Comp Sydney NSW 2109 Australia

knowledge graph embedding (KGE) aims to represent entities and relations in a low-dimensional continuous vector space. Recent KGE works focus on incorporating additional information, such as local neighbors and textual descriptions, to learn valuable representations. However, the non-uniformity and redundancy hinder the effectiveness of entity features from those information sources. In this paper, we propose a novel end-to-end framework, called composite neighborhood embedding (CoNE), utilizing composite neighbors to enhance the existing KGE methods. To ease past problems, the new composite neighbors are gathered from both entity descriptions and local neighbors. We design a novel graph Memory Networks to extract entity features from composite neighbors, and fulfill the entity representation in the target KGE method. The experimental results show that CoNE effectively enhances three different KGE methods, TransE, ConvE, and RotatE, and achieves the state-of-the-art results on four real-world large datasets. Furthermore, our approach outperforms the recent text-enhanced models with fewer parameters and calculation. The source code of our work can be obtained from.

关键词： knowledge graph embedding Link prediction graph memory networks knowledge graphs

来源：评论

学校读者我要写书评

暂无评论

A lightweight CNN-based knowledge graph embedding model with channel attention for link prediction

引用

MATHEMATICAL BIOSCIENCES AND ENGINEERING 2023年第6期20卷 9607-9624页

作者： Zhou, Xin Guo, Jingnan Jiang, Liling Ning, Bo Wang, Yanhao Dalian Maritime Univ Sch Informat Sci & Technol Dalian 116026 Peoples R China East China Normal Univ Sch Data Sci & Engn Shanghai 200062 Peoples R China

knowledge graph (KG) embedding is to embed the entities and relations of a KG into a low-dimensional continuous vector space while preserving the intrinsic semantic associations between entities and relations. One of the most important applications of knowledge graph embedding (KGE) is link prediction (LP), which aims to predict the missing fact triples in the KG. A promising approach to improving the performance of KGE for the task of LP is to increase the feature interactions between entities and relations so as to express richer semantics between them. Convolutional neural networks (CNNs) have thus become one of the most popular KGE models due to their strong expression and generalization abilities. To further enhance favorable features from increased feature interactions, we propose a lightweight CNN-based KGE model called IntSE in this paper. Specifically, IntSE not only increases the feature interactions between the components of entity and relationship embeddings with more efficient CNN components but also incorporates the channel attention mechanism that can adap-tively recalibrate channel-wise feature responses by modeling the interdependencies between channels to enhance the useful features while suppressing the useless ones for improving its performance for LP. The experimental results on public datasets confirm that IntSE is superior to state-of-the-art CNN-based KGE models for link prediction in KGs.

关键词： knowledge graph embedding convolutional neural network channel attention link prediction feature enhancement

来源：评论

学校读者我要写书评

暂无评论

Two flexible translation-based models for knowledge graph embedding

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2023年第2期44卷 3093-3105页

作者： Li, Zepeng Huang, Rikui Zhang, Yufeng Zhu, Jianghong Hu, Bin Lanzhou Univ Sch Informat Sci & Engn Gansu Prov Key Lab Wearable Comp Lanzhou Peoples R China Beijing Inst Technol Inst Engn Med Beijing Peoples R China Chinese Acad Sci CAS Ctr Excellence Brain Sci Shanghai Inst Biol Sci Shanghai Peoples R China Chinese Acad Sci Inst Biol Sci Shanghai Inst Biol Sci Shanghai Peoples R China

knowledge graph embedding (KGE), which aims to embed the entities and relations of a knowledge graph into a low-dimensional continuous space, has been proven to be an effective method for completing a knowledge graph and improving the quality of the knowledge graph. The translation-based models represented by TransE, TransH, TransR and TransD have achieved great success in this regard. There is still potential for improvement in dealing with complex relations. In this paper, we find that the lack of flexibility in entity embedding limits the model's ability to model complex relations. Therefore, we propose single-directional-flexible (sdf) models and multi-directional-flexible (mdf) models to increase the flexibility and expressiveness of entity embeddings. These two methods can be applied to the TransD model and its variant models without increasing any time cost and space cost. We conduct experiments on benchmarks such as WN18 and FB15k. The experimental results show that the models significantly surpasses the classical translation models in both tasks of triplet classification and link prediction. In particular, for Hits@1 of link prediction of WN18, we get 71.7% after applying our method to TransD, which is much better than 24.1% of TransD.

关键词： knowledge graph embedding translation model complex relation single-directional-flexible model multidirectional-flexible model

来源：评论

学校读者我要写书评

暂无评论

HARPA: hierarchical attention with relation paths for knowledge graph embedding adversarial learning

引用

DATA MINING AND knowledge DISCOVERY 2023年第2期37卷 521-551页

作者： Zhang, Naixin Wang, Jinmeng He, Jieyue Southeast Univ Sch Comp Sci & Engn Key Lab Comp Network & Informat Integrat MOE Nanjing 210018 Jiangsu Peoples R China

knowledge graph embedding (KGE) aims to map the knowledge graph into a low-dimensional continuous vector space and provide a unified underlying representation for downstream tasks. Recently, graph neural network (GNN) has been widely used in knowledge graph embedding because of its powerful feature extraction ability, and most KGE models based on GNN use aggregation operations to extract potential information from the triples. Unfortunately, they only emphasize entity embedding and use shallow operations to update relations. As a result, the learning of relation embedding is relatively simple. And they ignore the rich inference information contained in the multi-hop paths. In addition, their complex network structure lacks regularization constraint, which is prone to the over-fitting problem. Therefore, this paper proposes a novel hierarchical attention with relation paths model for knowledge graph embedding adversarial learning (HARPA). HARPA constructs a two-layer attention encoder to learn the information of triples and neighborhoods at the triples-level and further utilizes the rich inference information of paths to deeply learn relation embedding at the paths-level. Besides, HARPA proposes an improved generative adversarial network (GAN) named I-GAN as the regularization term of the model, which imposes constraints on the process of learning embedding and enables the model to learn high-quality and robust embedding. The link prediction experiments on four general knowledge graphs show that the HARPA model outperforms state-of-the-art methods.

关键词： knowledge graph embedding Attention mechanism Relation paths Generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

Deep hyperbolic convolutional model for knowledge graph embedding

引用

knowledge-BASED SYSTEMS 2024年 300卷

作者： Lu, Ming Li, Yancong Zhang, Jiangxiao Ren, Haiying Zhang, Xiaoming Beihang Univ Sch Cyber Sci & Technol Beijing Peoples R China Xingtai Univ Math & Informat Technol Inst Xingtai 054001 Hebei Peoples R China Beihang Univ Sch Comp Sci & Engn State Key Lab Software Dev Environm Beijing 100191 Peoples R China

Recent advancements in knowledge graph embedding have enabled the representation of entities and relations in continuous vector spaces. Performing link prediction on incomplete knowledge graphs using these embeddings has emerged as a challenging task, drawing considerable research interest. knowledge graphs in the real world typically exhibit a natural hierarchical structure. Hyperbolic embedding methods have shown promising results in modeling hierarchical data, especially in low-dimensional representations. However, existing hyperbolic models for knowledge graph embedding are generally shallow, resulting in limited expressiveness. Additionally, some deep hyperbolic models exist but are often constrained to fixed curvature spaces, which may not optimally capture varying hierarchical structures. In this work, we propose DeER, a novel multi-layer hyperbolic model that leverages a trainable curvature space, marking an advancement in the depth and adaptability of hyperbolic modeling for knowledge graph embeddings. We specifically design a hyperbolic convolutional neural network to learn the heterogeneous interactions between entities and relations within this adaptable hyperbolic space. Additionally, we introduce a hyperbolic feedforward neural network to transform hyperbolic features across multiple layers, enhancing the model's ability to capture complex hierarchical relationships. Experimental results on three benchmark datasets demonstrate that DeER significantly enhances expressiveness and hierarchical modeling performance when compared to both shallow and other deep baseline approaches.

关键词： knowledge graph embedding Link prediction Hyperbolic geometry Poincar & eacute ball Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network-Based Entity-Specific Common Feature Aggregation for knowledge graph embedding Learning

引用

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 2024年第1期70卷 3593-3602页

作者： Hu, Kairong Zhu, Xiaozhi Liu, Hai Qu, Yingying Wang, Fu Lee Hao, Tianyong South China Normal Univ Sch Comp Sci Guangzhou 510631 Peoples R China Guangdong Univ Foreign Studies Sch Business Guangzhou 510006 Peoples R China Hong Kong Metropolitan Univ Sch Sci & Technol Hong Kong Peoples R China

Deep learning models present impressive capability for automatic feature extraction, where common features-based aggregation have demonstrated valuable potential in improving the model performance on text classification, sentiment analysis, etc. However, leveraging entity-specific common feature aggregation for enhancing knowledge graph representation learning has not been fully explored yet, though diverse strategies in knowledge graph embedding models have been developed in recent years. This paper proposes an innovative Convolutional Neural Network-based Entity-specific Common Feature Aggregation strategy named CNN-ECFA. Besides, a new universal framework based on the CNN-ECFA strategy is introduced for knowledge graph embedding learning. Experiments are conducted on publicly-available standard datasets for a link prediction task including WN18RR, YAGO3-10 and NELL-995. Results show that the CNN-ECFA strategy outperforms the state-of-the-art feature projection strategies with average improvements of 0.6% and 0.7% of MRR and Hits@1 on all the datasets, demonstrating our CNN-ECFA strategy is more effective for knowledge graph embedding learning. In addition, our universal framework significantly outperforms a generalized relation learning framework on WN18RR and NELL-995 with average improvements of 1.7% and 1.9% on MRR and Hits@1. The source code is publicly available at https://***/peterhu95/ConvE-CNN-ECFA.

关键词： Convolutional neural networks Feature extraction knowledge graphs Task analysis Semantics Tail Predictive models Common feature knowledge graph knowledge graph embedding link prediction

来源：评论

学校读者我要写书评

暂无评论

Enhancing knowledge graph embedding with type-constraint features

引用

APPLIED INTELLIGENCE 2023年第1期53卷 984-995页

作者： Chen, Wenjie Zhao, Shuang Zhang, Xin Chinese Acad Chengdu Documentat & Informat Ctr 16South Sect 21st Ring Rd Chengdu Sichuan Peoples R China

knowledge graph (KG) embedding represents entities and relations with latent vectors, which has been widely adopted in relation extraction and KG completion. Among existing works, translation-based models treat each relation as the translation from head entitiy to tail entitiy and have attracted much attention. However, these models only utilize fact triples but ignore prior knowledge on relational type-constraints. This paper presents a generic framework to enhance knowledge graph embedding with type-constraint features (ETF). In ETF, the embedding of entity is comprised of two parts-entity-specific embedding and constraint-specific embedding. The former expresses translation features of entities, and the latter represents semantic constraints influence by linked relations. Besides, the adaptive margin-based loss is designed to learn embeddings, which effectively separates the negative and positive triples. Finally, the results on four public datasets demonstrate that ETF makes significant improvements over the baselines.

关键词： knowledge graph embedding Translation-based model Relational type-constraints Entity-specific embedding Constraint-specific embedding

来源：评论

学校读者我要写书评

暂无评论

Hyperplane-based time-aware knowledge graph embedding for temporal knowledge graph completion

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2022年第6期42卷 5457-5469页

作者： He, Peng Zhou, Gang Liu, Hongbo Xia, Yi Wang, Ling Informat Engn Univ Zhengzhou Peoples R China Zhengzhou Univ Technol Zhengzhou Peoples R China

knowledge graph (KG) embedding approaches have been proved effective to infer new facts for a KG based on the existing ones-a problem known as KG completion. However, most of them have focused on static KGs, in fact, relational facts in KGs often show temporal dynamics, e.g., the fact (US, has president, Barack Obama, [2009-2017]) is only valid from 2009 to 2017. Therefore, utilizing available time information to develop temporal KG embedding models is an increasingly important problem. In this paper, we propose a new hyperplane-based time-aware KG embedding model for temporalKGcompletion. By employing the method of time-specific hyperplanes, our model could explicitly incorporate time information in the entity-relation space to predict missing elements in the KG more effectively, especially temporal scopes for facts with missing time information. Moreover, in order to model and infer four important relation patterns including symmetry, antisymmetry, inversion and composition, we map facts happened at the same time into a polar coordinate system. During training procedure, a time-enhanced negative sampling strategy is proposed to get more effective negative samples. Experimental results on datasets extracted from real-world temporal KGs show that our model significantly outperforms existing state-of-the-art approaches for the KG completion task.

关键词： Temporal knowledge graph knowledge graph completion knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Service Recommendation Based on knowledge graph embedding

引用

IEEE TRANSACTIONS ON knowledge AND DATA ENGINEERING 2022年第11期34卷 5225-5238页

作者： Mezni, Haithem Benslimane, Djamal Bellatreche, Ladjel Taibah Univ Dept Comp Informat Sci Medina 42353 Saudi Arabia Claude Bernard Univ F-69373 Lyon France Natl Engn Sch Mech & Aerotech F-86961 Poitiers France

Over two decades, context awareness has been incorporated into recommender systems in order to provide, not only the top-rated items to consumers but also the ones that are suitable to the user context. As a class of context-aware systems, context-aware service recommendation (CASR) aims to bind high-quality services to users, while taking into account their context requirements, including invocation time, location, social profiles, connectivity, and so on. However, current CASR approaches are not scalable with the huge amount of service data (QoS and context information, users reviews and feedbacks). In addition, they lack a rich representation of contextual information, as they adopt a simple matrix view. Moreover, current CASR approaches adopt the traditional user-service relation and they do not allow for multi-relational interactions between users and services in different contexts. To offer a scalable and context-sensitive service recommendation with great analysis and learning capabilities, we provide a rich and multi-relational representation of the CASR knowledge, based on the concept of knowledge graph. The constructed context-aware service knowledge graph (C-SKG) is, then, transformed into a low-dimensional vector space to facilitate its processing. For this purpose, we adopt Dilated Recurrent Neural Networks to propose a context-aware knowledge graph embedding, based on the principles of first-order and subgraph-aware proximity. Finally, a recommendation algorithm is defined to deliver the top-rated services according to the target user's context. Experiments have proved the accuracy and scalability of our solution, compared to state-of-the-art CASR approaches.

关键词： knowledge engineering Context-aware services Recommender systems Data mining Context modeling Social networking (online) Data models Service recommendation context-awareness knowledge graph knowledge graph embedding subgraph-aware proximity dilated recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Developing a BERT based triple classification model using knowledge graph embedding for question answering system

引用

APPLIED INTELLIGENCE 2022年第1期52卷 636-651页

作者： Phuc Do Phan, Truong H., V Vietnam Natl Univ Univ Informat Technol Ho Chi Minh City Vietnam Van Lang Univ Ho Chi Minh City Vietnam

The current BERT-based question answering systems use a question and a contextual text to find the answer. This causes the systems to return wrong answers or nothing if the text contains irrelevant contents with the input question. Besides, the systems haven't answered yes-no and aggregate questions yet. Besides that, the systems only concentrate on the contents of text regardless of the relationship between entities in the corpus. This systems cannot validate the answer. In this paper, we presented a solution to solve these issues by using the BERT model and the knowledge graph to enhance a question answering system. We combined content-based and linked-based information for knowledge graph representation learning and classified triples into one of three classes such as base class, derived class, or non-existent class. We then used the BERT model to build two classifiers: BERT-based text classification for content information and BERT-based triple classification for link information. The former was able to make a contextual embedding vector for representing triples that were used to classify into the three above classes. The latter generated all path instances from all meta paths of a large heterogeneous information network by running the Motif Search method of Apache Spark on a distributed environment. After creating the path instances, we produced triples from these path instances. We made content-based information by converting triples into natural language text with labels and considered them as a text classification problem. Our proposed solution outperformed other embedding methods with an average accuracy of 92.34% on benchmark datasets and the Motif Finding algorithm with an average executive time improvement of 37% on the distributed environment.

关键词： BERT based triple classification model knowledge graph embedding Meta-path Motif finding

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：