检索结果-内蒙古大学图书馆

knowledge graph embedding based on embedding permutation and high-frequency feature fusion for link prediction

NEUROCOMPUTING 2025年 633卷

作者： Yu, Qien Vargas, Danilo Vasconcellos Kyushu Univ Dept Informat Sci & Technol 744 MotookaNishi Ku Fukuoka 8190395 Japan

knowledge graph embedding has excellent performance in capturing intrinsic relations and semantics in a wealth of information for link prediction. knowledge graph embedding methods have achieved impressive results in recent years, especially those using convolutional neural networks. However, many previous approaches focus on interactions between relations and entities, ignoring interactions of internal data elements and the crucial role of high-frequency features. In this paper, we propose a novel approach, a knowledge graph embedding model using 2D convolution operations integrating embedding permutation strategy and High-frequency features fusion mechanism, named EHE, for link prediction. First, we design the embedding permutation mechanism for the embedding vectors. This mechanism leverages internal element permutation, efficiently broadening the local interactions of internal elements, especially for far-flung data elements in the one-dimensional space. Subsequently, a high-frequency feature fusion module is proposed to capture the high-frequency feature representations by using Sobel and Laplacian operators. Additionally, the projection attention mechanism is utilized to emphasize the unique semantic regions of interest in entities and relations. We assess our approach on several benchmark link prediction datasets. Considering the important metrics, MRR and H@1, our method achieves the overall best performance compared with existing state-of-the-art methods on five public datasets, showcasing its superior capacity for link prediction.

关键词： knowledge graph embedding Link prediction Feature fusion Convolutional neural network embedding permutation Projection attention

来源：评论

学校读者我要写书评

暂无评论

Co-occurrence graph Convolutional Networks with Approximate Entailment for knowledge graph embedding

引用

APPLIED SOFT COMPUTING 2025年 170卷

作者： Zhang, Dong Li, Wenhao Qiu, Tianbo Li, Guanyu Dalian Maritime Univ Informat Sci & Technol Coll Dalian 116026 Liaoning Peoples R China

The goal of knowledge graph completion (KGC) is to address the issue of missing triples and enhance the overall completeness of the knowledge graph. However, existing methods face three key challenges: (1) Weak semantic correlation between entities and relations in the knowledge graph. (2) Insufficient extraction of local features in the model. (3) Limited ability to represent complex semantic relations. This paper proposes a G raph C onvolutional N etwork framework that leverages C o-occurrence features, local structural features, and A pproximate E ntailment (CoAE-GCN). The CoAE-GCN model is designed to overcome these challenges. The CoAE-GCN model addresses these issues by (1) enumerating the co-occurrence of entities and relations and using resulting weighted information as input for the model. (2) We employ graph Neural Networks (GNNs) to learn structural features while using attention mechanisms to capture local structural features from incoming and outgoing neighbors. (3) We are applying approximate entailment to enhance the representational capacity of relations. Experimental results on benchmark datasets demonstrate that the CoAE-GCN model is outperformance and effective.

关键词： knowledge graph embedding Link prediction Approximate entailment Local attention

来源：评论

学校读者我要写书评

暂无评论

knowledge Augmented Expert finding framework via knowledge graph embedding for Community Question Answering

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 142卷

作者： Liu, Yue Liu, Zitu Yu, Zhenyao Fu, Qingshan Tang, Weize Yao, Wenxuan Sun, Zhibin Shanghai Univ Sch Comp Engn & Sci Shanghai 200444 Peoples R China Shanghai Engn Res Ctr Intelligent Comp Syst Shanghai 200444 Peoples R China Nanjing Normal Univ Sch Math Sci Jiangsu Key Lab Numer Simulat Large Scale Complex Nanjing 210023 Peoples R China

Expert Finding in Community Question Answering aims to recommend appropriate experts to answer posted questions. However, existing approaches focus on exploiting semantic extraction and authority analysis techniques, failing to realize the latent knowledge-aspect connections between questions and experts. Therefore, the experts recommended for posted questions are limited to text-to-text approximation or domain-independent authority. In this study, we propose a knowledge Augmented Expert finding framework (KAExpert) that introduces knowledge level information into semantic-based and authority-based expert finding method. A community knowledge graph is firstly constructed by acquiring ternary relations from public databases based on question tags and knowledge-related phrases. Then a flexible knowledge graph embedding is designed to extract the matching relationship between questions and experts at the knowledge level. Along this line, the knowledge- level authority is calculated based on the knowledge graph embedding to optimize the results of domain matching. According to knowledge graph embedding and knowledge-level authority, KAExpert is constructed to optimize the results of domain matching so that the found experts set consists of high-level expert with semantic matching and knowledge matching. Finally, experimental results on two real-world datasets collected from two major commercial question answering web sites show that KAExpert can outperform baseline methods with a significant margin.

关键词： Expert finding Community question answering knowledge graph knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

QUERY2TREE: a reasoning model for answering logical queries based on knowledge graph embedding and large language model

引用

knowledge AND INFORMATION SYSTEMS 2025年第6期67卷 5271-5300页

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

Reasoning to answer logical queries over a knowledge graph has been paid attention to research recently. Previous studies have only used either distance measurement or machine learning approaches processed logical operators such as conjunction, disjunction, and negation but considering the entity description information of knowledge graph yet. This study proposes a model, named QUERY2TREE, to combine a graph representative learning model and large language model to augment semantic for embedded entities of the knowledge graph such that these entities can handle logical operations more accurately during the reasoning process. Specifically, the QUERY2TREE used the graph neural network (GNN) to embed entities and Gemma model, a family of Google Gemini model, to embed the entity's descriptive information into low-dimensional space. Then, these embedded entities were indexed by K-D tree according to each relation over the knowledge graph. Next, we used nearest neighbor search algorithm of K-D tree to build logical operations such as projection, intersection, union, and negation. Finally, we applied these created logical operations to infer the answer to complex questions. We experimented with our model over benchmark knowledge graphs such as FB15k, FB15k-237, and NELL995. As a result, the QUERY2TREE model improved the accuracy better than the baseline models QUERY2BOX, ConE, CQD-CO, MLP, SILR, GNN-QE, CKGR, LACK, and LACT by up to 69.6% of MRR and by up to 69.4% of hits@3.

关键词： Logical query K-D tree Nearest neighbor search Multi-hop reasoning knowledge graph embedding Large language model

来源：评论

学校读者我要写书评

暂无评论

MHRN: A multi-perspective hierarchical relation network for knowledge graph embedding

引用

knowledge-BASED SYSTEMS 2025年 313卷

作者： Xue, Zengcan Zhang, Zhaoli Liu, Hai Li, Zhifei Han, Shuyun Zhang, Erqi Cent China Normal Univ Natl Engn Res Ctr Elearning Wuhan 430079 Peoples R China Hubei Univ Sch Comp Sci Wuhan 430062 Peoples R China

knowledge graph embedding (KGE) aims to improve entity and relation representations, enhancing the accuracy of link prediction tasks. Recently, deep neural networks have been widely adopted for KGE. However, existing methods mainly focus on improving feature interactions through permutation and reshaping embeddings from a translational perspective, often overlooking the rotational interactions between entities and relations. Furthermore, these models tend to treat all relations in the knowledge graph uniformly, neglecting their heterogeneous characteristics. A novel KGE model with a multi-perspective hierarchical relation network (MHRN) is proposed to mitigate the two problems. Specifically, it generates multi-perspective rotation embeddings by leveraging a group equivariant convolutional layer that incorporates both translation and rotation transformations. This approach captures rotational interactions and significantly enhances the expressiveness of the neural network, all without adding extra parameters. Additionally, the hierarchical relation component employs relation-oriented convolutional filters to preserve the diverse characteristics of different relations. The hierarchical mechanism further extends the receptive field, integrating global information while retaining detailed local features during the aggregation process. Experimental results demonstrate that MHRN excels in capturing rotational interactions and preserving relational characteristics. It delivers outstanding performance on seven benchmark datasets, surpassing baseline methods in 2 out of 4 indicators on FB15k-237, and in all 4 indicators on both FB15k and YAGO3-10 datasets.

关键词： knowledge graph embedding Group equivariant convolution Rotational interaction Relational characteristic Link prediction

来源：评论

学校读者我要写书评

暂无评论

Entity-relation aggregation mechanism graph neural network for knowledge graph embedding

引用

APPLIED INTELLIGENCE 2025年第1期55卷 1-14页

作者： Xu, Guoshun Rao, Guozheng Zhang, Li Cong, Qing Tianjin Univ Coll Intelligence & Comp Tianjin 300350 Peoples R China Tianjin Univ Sci & Technol Sch Econ & Management Tianjin 300222 Peoples R China Tianjin Univ Sch New Media & Commun Tianjin 300072 Peoples R China Tianjin Key Lab Cognit Comp & Applicat Tianjin 300350 Peoples R China

graph Neural Networks (GNNs) are inherently suited for modeling graph-structured data and have been extensively utilized in knowledge graph embedding (KGE). Current GNN-based KGE models primarily focus on message aggregation among entities, often neglecting the aggregation of messages related to relations. Additionally, the interaction information between entities and relations, as well as their distinctions, is overlooked during the updating of relations. To address these issues, we propose the Entity-Relation Aggregation Mechanism graph Neural Network (ERAGNN), where relations are also considered as nodes in the graph for message aggregation. The ERAGNN layer comprises an entity aggregation sublayer and a relation aggregation sublayer. The entity aggregation sublayer employs an entity-relation composition operation to aggregate messages across entity nodes, while the relation aggregation sublayer utilizes an entity-entity composition operation. Furthermore, shared-weight matrices are implemented to enhance interactions between entities and relations. Lastly, an attention mechanism is incorporated to differentiate neighboring messages during the update of relation embeddings. Experimental results demonstrate that ERAGNN achieves state-of-the-art link prediction performance on three benchmark datasets: FB15k-237, WN18RR, and WN18.

关键词： knowledge graph completion knowledge graph embedding graph neural networks Entity-relation aggregation

来源：评论

学校读者我要写书评

暂无评论

TH-RotatE: A Hybrid knowledge graph embedding Framework for Fault Diagnosis in Railway Operational Equipment

引用

ELECTRONICS 2025年第8期14卷 1656-1656页

作者： Yang, Xiaorui Li, Honghui Yan, Jiahe He, Ruiyi Beijing Jiaotong Univ Sch Comp Sci & Technol Beijing 100044 Peoples R China Minist Educ Engn Res Ctr High Speed Railway Network Management Beijing 100044 Peoples R China

Reliable fault diagnosis in railway operational equipment is critical to ensuring system safety, operational efficiency, and predictive maintenance. Existing methods struggle to capture the intricate interdependencies among fault causes, failure modes, and corrective actions, limiting their ability to model fault propagation effectively. To address this, we propose TH-RotatE, a novel knowledge graph (KG) embedding framework that integrates TransH's hierarchical modeling with RotatE's complex space transformations, while incorporating a hybrid scoring function and self-adversarial negative sampling to enhance embedding quality and fault relationship differentiation. This approach effectively captures hierarchical dependencies, cyclic patterns, and asymmetric transitions inherent in railway faults, enabling a more expressive representation of fault propagation. Furthermore, we construct the Chinese railway operational equipment fault knowledge graph (CROEFKG), a structured multi-relational repository encoding fault descriptions, causal chains, and mitigation strategies. Extensive experiments on real-world railway fault data demonstrate that TH-RotatE outperforms both traditional and advanced KG embedding models, achieving superior fault diagnosis accuracy and link prediction effectiveness. In practical applications, TH-RotatE enables timely fault diagnosis and detection of cascading failures, providing interpretable fault propagation pathways through the CROEFKG's structured representation. These capabilities offer a scalable, knowledge-driven solution for railway systems, improving diagnostic accuracy while reducing safety risks and unplanned downtime. This work advances domain-specific KG embeddings, bridging the gap between theoretical innovation and industrial reliability.

关键词： fault diagnosis knowledge graph embedding railway operational equipment TH-RotatE link prediction

来源：评论

学校读者我要写书评

暂无评论

Efficient Parameterization for knowledge graph embedding Using Hierarchical Attention Network

引用

Computers, Materials & Continua 2025年第3期82卷 4287-4300页

作者： Zhen-Yu Chen Feng-Chi Liu Xin Wang Cheng-Hsiung Lee Ching-Sheng Lin Master Program of Digital Innovation Tunghai UniversityTaichung40704Taiwan Department of Statistics Feng Chia UniversityTaichung40724Taiwan College of Integrated Health Sciences and the AI Plus Institute The University at AlbanyState University of New York(SUNY)AlbanyNY 12222USA

In the domain of knowledge graph embedding,conventional approaches typically transform entities and relations into continuous vector ***,parameter efficiency becomes increasingly crucial when dealing with large-scale knowledge graphs that contain vast numbers of entities and *** particular,resource-intensive embeddings often lead to increased computational costs,and may limit scalability and adaptability in practical environ-ments,such as in low-resource settings or real-world *** paper explores an approach to knowledge graph representation learning that leverages small,reserved entities and relation sets for parameter-efficient *** introduce a hierarchical attention network designed to refine and maximize the representational quality of embeddings by selectively focusing on these reserved sets,thereby reducing model *** assessments validate that our model achieves high performance on the benchmark dataset with fewer parameters and smaller embedding *** ablation studies further highlight the impact and contribution of each component in the proposed hierarchical attention structure.

关键词： knowledge graph embedding parameter efficiency representation learning reserved entity and relation sets hierarchical attention network

来源：评论

学校读者我要写书评

暂无评论

A data-centric framework of improving graph neural networks for knowledge graph embedding

引用

WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS 2025年第1期28卷 1-21页

作者： Cao, Yanan Lin, Xixun Wu, Yongxuan Shi, Fengzhao Shang, Yanmin Tan, Qingfeng Zhou, Chuan Zhang, Peng Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China Guangzhou Univ Cyberspace Inst Adv Technol Guangzhou Peoples R China Chinese Acad Sci Acad Math & Syst Sci Beijing Peoples R China

knowledge graph embedding (KGE) aims to learn representations of entities and relations of knowledge graph (KG). Recently graph Neural Networks (GNNs) have gained great success on KGE, but for the reason behind it, most views simply attribute to the well learning of knowledge graph structure, which still remains a limited understanding of the internal mechanism. In this work, we first study a fundamental problem, i.e., what are the important factors for GNNs to help KGE. To investigate this problem, we discuss the core idea of current GNN models for KG, and propose a new assumption of relational homophily that connected nodes possess similar features after relation's transforming, to explain why aggregating neighbors with relation can help KGE. Based on the model and empirical analyses, we then introduce a novel data-centric framework for applying GNNs to KGE called KSG-GNN. In KSG-GNN, we construct a new graph structure from KG named knowledge Similarity graph (KSG), where each node connects with its similar nodes as neighbors, and then we apply GNNs on this graph to perform KGE. Instead of following the relational homophily assumption in KG, KSG aligns with homogeneous graphs that can directly satisfy homophily assumption. Hence, any GNN developed on homogeneous graphs like GCN, GAT, graphSAGE, etc., can be applied out-of-the-box as KSG-GNN without modification, which provides a more general and effective GNN paradigm. Finally, we conduct extensive experiments on two benchmark datasets, i.e., FB15k-237 and WN18RR, demonstrating the superior performance of KSG-GNN over multiple strong baselines. The source code is available at https://***/advancer99/WWWJ-KGE.

关键词： knowledge graph embedding graph homophily graph neural networks Data-centric learning

来源：评论

学校读者我要写书评

暂无评论

C-KGE: Curriculum learning-based knowledge graph embedding

引用

COMPUTER SPEECH AND LANGUAGE 2025年 89卷

作者： Zhou, Diange Li, Shengwen Dong, Lijun Chen, Renyao Peng, Xiaoyue Yao, Hong China Univ Geosci State Key Lab Biogeol & Environm Geol Wuhan 430078 Peoples R China China Univ Geosci Sch Comp Sci Wuhan 430078 Peoples R China China Univ Geosci Hubei Key Lab Intelligent Geoinformat Proc Wuhan 430078 Peoples R China

knowledge graph embedding (KGE) aims to embed entities and relations in knowledge graphs (KGs) into a continuous, low-dimensional vector space. It has been shown as an effective tool for integrating knowledge graphs to improve various intelligent applications, such as question answering and information extraction. However, previous KGE models ignore the hidden natural order of knowledge learning on learning the embeddings of entities and relations, leaving room for improvement in their performance. Inspired by the easy-to-hard pattern used in human knowledge learning, this paper proposes a C urriculum learning-based KGE (C-KGE) model, which learns the embeddings of entities and relations from "basic knowledge"to "domain knowledge". Specifically, a seed set representing the basic knowledge and several knowledge subsets are identified from KG. Then, entity overlap is employed to score the learning difficulty of each subset. Finally, C-KGE trains the entities and relations in each subset according to the learning difficulty score of each subset. C-KGE leverages trained embeddings of the seed set as prior knowledge and learns knowledge subsets iteratively to transfer knowledge between the seed set and subsets, smoothing the learning process of knowledge facts. Experimental results on real-world datasets demonstrate that the proposed model achieves improved embedding performances as well as reducing training time. Our codes and data will be released later.

关键词： knowledge graph embedding knowledge graph Curriculum learning Link prediction

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：