检索结果-内蒙古大学图书馆

Decoupled semantic graph neural network for knowledge graph embedding

NEUROCOMPUTING 2025年 611卷

作者： Li, Zhifei Huang, Wei Gong, Xuchao Luo, Xiangyu Xiao, Kui Deng, Honglian Zhang, Miao Zhang, Yan Hubei Univ Sch Comp Sci & Informat Engn Wuhan 430062 Peoples R China Hubei Univ Sch Cyber Sci & Technol Wuhan 430062 Peoples R China Sinopec Shengli Petr Management Bur Artificial Intelligence Res Inst Dongying 257000 Peoples R China Hubei Univ Sci & Technol Sch Educ Xianning 437100 Peoples R China Hubei Univ Sci & Technol Key Res Inst Humanities & Social Sci Hubei Prov Res Ctr Rural Educ & Cultural Dev Xianning 437100 Peoples R China Hubei Univ Hubei Key Lab Big Data Intelligent Anal & Applicat Wuhan 430062 Peoples R China Hubei Univ Key Lab Intelligent Sensing Syst & Secur Minist Educ Wuhan 430062 Peoples R China

knowledge graph embedding (KGE) learns an embedding space for a more accurate representation of entities and relations. Although the KGE model has proliferated, it often fails to fully capture the rich semantics in knowledge graphs. Some studies attempt to apply decoupling methods to decompose node representations, yet they neglect the semantic noise generated during the decoupled process. To address these issues, we introduce the decoupled semantic graph network for KGE (named DSGNet), which employs a novel approach that combines semantic decoupling with structural awareness. DSGNet begins by projecting the knowledge graph into distinct semantic spaces, ensuring minimal correlation between them to achieve effective semantic decoupling. To mitigate semantic noise, a top-k k sampling technique is applied to the decoupled graphs. DSGNet then aggregates these different semantic graphs using a relation-aware aggregation module, followed by a multi-layer aggregation process for enhanced node representation. The extensive experiments demonstrate that DSGNet performs competitively on two popular datasets. We make our code publicly available at https://***/HubuKG/DSGNet.

关键词： knowledge graphs knowledge graph embedding knowledge graph completion graph neural network

来源：评论

学校读者我要写书评

暂无评论

IF-NS: A New negative sampling framework for knowledge graph embedding using influence function

引用

knowledge-BASED SYSTEMS 2025年 315卷

作者： Cai, Ming Deng, Zhuolin Xiong, Chen Sun Yat Sen Univ Sch Intelligent Syst Engn Shenzhen 518107 Guangdong Peoples R China Sun Yat Sen Univ Guangdong Prov Key Lab Intelligent Transportat Sys Guangzhou 510275 Guangdong Peoples R China

knowledge graphs (KGs) are widely used in tasks such as recommendation and question answering, with the aid of knowledge graph embedding (KGE) models. These models incorporate negative sampling during training but face challenges, including vanishing gradients and false negatives, primarily due to the lack of incorrect facts in KGs. While score functions in KGE models help mitigate vanishing gradient issues, they often fail to address false-negative samples. Drawing inspiration from influence functions, we propose a new framework for translational distance KGE models called IF-NS, which leverages influence to select high-quality negative samples. The core idea is to assess how each sample contributes to the KGE model during training, effectively retaining high-quality negative samples. To reduce computational complexity, we also develop a simplified influence estimation algorithm tailored to the L2-norm distance in the KGE loss function. Furthermore, we introduce a repository for storing and tracking high-quality negative samples, employing repository-based sampling and dynamic updating strategies to balance exploration and exploitation. Experimental results show that IF-NS effectively mitigates the issues of vanishing gradients and false negatives, significantly improving KGE model performance.

关键词： knowledge graph embedding Negative sampling Influence function

来源：评论

学校读者我要写书评

暂无评论

GeoEntity-type constrained knowledge graph embedding for predicting natural-language spatial relations

引用

INTERNATIONAL JOURNAL OF GEOgraphICAL INFORMATION SCIENCE 2025年第2期39卷 376-399页

作者： Hu, Lei Li, Wenwen Xu, Jun Zhu, Yunqiang Chinese Acad Sci Inst Geog Sci & Nat Resources Res State Key Lab Resources & Environm Informat Syst Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Arizona State Univ Sch Geog Sci & Urban Planning Tempe AZ 85287 USA

Natural-language spatial relations between geographic entities (geoentities) reflect diverse perceptions influenced by factors like location, culture, and linguistic conventions. These relations play a crucial role in supporting geospatial tasks, such as question answering and cognitive reasoning. While prior studies focused on a limited set of human-selected spatial terms and geometric attributes, they often overlooked essential semantic attributes. To overcome this limitation, we developed a Spatial Relation-based knowledge graph embedding framework, SR-KGE, with new KG fusion functions to predict spatial relation terms among distinct geoentities. This method not only considers graph structures and the diversity of natural language expressions in the embedding and learning process, but also incorporates geoentity types as a constraint to capture spatial and semantic relations more accurately. Our experiments on two knowledge graph datasets, one small-scale and one large-scale, have both shown its superior performance in spatial relation inference compared to popular KGE models, including TransE, RotatE, and HAKE. We hope our research will advance the classic study of natural language described spatial relations in a more automated and intelligent way.

关键词： Spatial relation natural language knowledge graph embedding joint training

来源：评论

学校读者我要写书评

暂无评论

Negative Sample Generation for Geographic knowledge graph embedding via Joint Entity Semantic Similarity and Clustering

引用

TRANSACTIONS IN GIS 2025年第2期29卷

作者： Qiu, Qinjun Lu, Siqi Ma, Kai Zhu, Yunqiang Huang, Zehua Xie, Zhong Tao, Liufeng Wang, Shu China Three Gorges Univ Hubei Key Lab Intelligent Vis Based Monitoring Hyd Yichang Hubei Peoples R China China Three Gorges Univ Coll Comp & Informat Technol Yichang Peoples R China China Univ Geosci Sch Comp Sci Wuhan Peoples R China Chinese Acad Sci Inst Geog Sci & Nat Resources State Key Lab Resources & Environm Informat Syst Beijing Peoples R China

Geographic knowledge graph (GKG) embedding (referred to as knowledge representation learning) enables the mapping of geographic entities and geographic relationships into a continuous vector space, thereby better capturing the semantic and structural information among entities in geographic space. The representation learning of GKGs requires generating corresponding negative samples based on positive samples. Negative sampling is an essential component of GKG embedding models. However, traditional negative sample generation algorithms suffer from high error rates and poor adaptability to GKGs, leading to potential replacements of entities that may not be logically reasonable in terms of geographic relationships, thus reducing the model's performance and generalization ability. To address the aforementioned challenge, this paper proposes a novel negative sampling approach for GKGs embedding, predicated on the amalgamation of entity semantic congruence and clustering techniques. Primarily, the proposed methodology employs the FastText model to encode entities within the KG into vector representations, thereby aiming to procure precise semantic embeddings of said entities. Subsequently, for improved delineation of semantically akin entities, the K-means algorithm is invoked to partition the entities into distinct clusters. Within the purview of negative sampling, entities within the same cluster as the substituted entity are randomly selected as negative instances, thus augmenting the fidelity of negative sample generation. Finally, experiments and analyses were conducted on the open-source datasets WN18, FB15k, and the constructed geographic dataset GKG12. The experimental results show that the proposed method can effectively improve the accuracy of GKG representation learning compared to the existing representation models.

关键词： entity semantic similarity geographic knowledge graph K-means knowledge graph embedding negative sample generation

来源：评论

学校读者我要写书评

暂无评论

BHRAM: a knowledge graph embedding model based on bidirectional and heterogeneous relational attention mechanism

引用

APPLIED INTELLIGENCE 2025年第3期55卷 1-19页

作者： Zhang, Chaoqun Li, Wanqiu Mo, Yuanbin Tang, Weidong Li, Haoran Zeng, Zhilin Guangxi Minzu Univ Coll Artificial Intelligence Nanning 530006 Peoples R China Guangxi Key Lab Hybrid Computat & IC Design Anal Nanning 530006 Peoples R China

knowledge graph embedding (KGE) is a method designed to predict missing relations between entities in a knowledge graph (KG), which has garnered much attention in recent years due to the incompleteness of KGs. However, existing KGE models have limitations in dealing with heterogeneous KGs and relation direction prediction. To address this issue, a novel KGE model called BHRAM is proposed. It is based on a bidirectional and heterogeneous relational attention mechanism. Specifically, BHRAM comprises three primary components, namely entity aggregation, relation aggregation and triplet prediction. The entity aggregation module divides the adjacency matrix into original and reverse relation adjacency matrices, using graph convolution to aggregate node features and subsequently form entity embedding representations. The relation aggregation module leverages bidirectional relations for feature extraction, learns the weight information of diverse paths independently and generates embedding representations of relation paths through an aggregation function. Finally, the triplet prediction module utilizes a score function for probabilistic predictions. To validate the superiority of BHRAM, comprehensive experiments were conducted on four well-known datasets, including baseline comparisons, relation classification tasks and ablation study. The results demonstrate that BHRAM significantly outperforms the other baselines on the FB15k-237, Kinship and UMLS datasets, while achieving similar or better performance than the baselines on the WN18RR dataset. These findings indicate that BHRAM can serve as a robust and effective model for addressing the heterogeneity in KGs.

关键词： Attention mechanism graph convolutional network Heterogeneity problem knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

Drug repositioning model based on knowledge graph embedding

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-15页

作者： He, Shufang Zhao, Xiaoyu Geely Univ China Sch Intelligence Technol 123Sect 2 Chengjian Ave Chengdu 641423 Sichuan Peoples R China

Drug repositioning utilizes existing drugs for new therapeutic applications, driven by the rapid increase in disease and drug-related data. However, organizing knowledge in this field and integrating the complex and scattered data from multiple systems into a cohesive knowledge network have become urgent problems to address. In this paper, we propose a drug repositioning model based on knowledge graph embedding. The model employs multivariate relational data to embed entities and relationships in a low-dimensional vector space. It also innovatively introduces the attention mechanism into translation and bilinear models, forming new models such as Attranse, Attdismult, and Attrescal. This model's feature extraction does not rely on a single approach, instead, it integrates multiple models and combines their screening results to enhance drug screening quality. The model's effectiveness was validated using COVID-19 data, yielding results consistent with 7 clinically approved drugs for COVID-19 treatment, indicating high accuracy in identifying new drug indications. The successful application of this model to COVID-19 suggests its potential for broader use in emerging infectious diseases and complex conditions, providing valuable insights for future drug development.

关键词： Drug repositioning knowledge graph embedding Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Effective knowledge graph embedding with Quaternion Convolutional Networks 13th

Effective Knowledge Graph Embedding with Quaternion Convolut...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Liang, Qiuyu Wang, Weihua Yu, Lie Bao, Feilong Inner Mongolia Univ Coll Comp Sci Hohhot Peoples R China Natl & Local Joint Engn Res Ctr Intelligent Infor Hohhot Peoples R China Inner Mongolia Key Lab Multilingual Artificial In Hohhot Peoples R China Natl Univ Def Technol Coll Comp Sci Changsha Peoples R China

ISBN: (纸本)9789819794362;9789819794379

Convolutional Neural Networks (CNNs) have demonstrated effectiveness in knowledge graph embedding, but existing CNN-based methods encounter two main challenges. Firstly, CNN-based models with simple architectures are unable to extract latent features. Secondly, these models enhance feature extraction by adding extra modules, which inevitably increases training cost with limited performance improvement. To address these challenges, we go beyond traditional CNNs and propose a novel knowledge graph embedding model, which utilizes the powerful capability of Quaternion Convolutional Neural Networks (QCNNs) for effective representation learning. Specifically, we learn representations of entities and relations in a quaternion space and utilize QCNN to extract the inherent information of the entity-relation matrix. We evaluate the performance of our model on multiple knowledge graph completion benchmark datasets. Experimental results show that our model achieves effective improvements compared to existing CNN-based models. Moreover, in terms of training time, our model is faster than other outstanding models. The code of all experiments is available at https://***/llqy123/ConvQE.

关键词： Quaternion algebra knowledge graph embedding Link prediction Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Multimodal knowledge graph embedding

Hyperbolic Multimodal Knowledge Graph Embedding

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Liang, Qiuyu Wang, Weihua Wang, Cunda Bao, Feilong Yu, Jie College of Computer Science Inner Mongolia University Hohhot China College of Computer Science National University of Defense Technology Changsha China

ISBN: (纸本)9798350368741

Multimodal knowledge graph embedding refers to learning multimodal entities and their relation representations in a low-dimensional space. However, existing multimodal embedding models tend to ignore the inherent structure of knowledge graphs. To address this issue, we propose a novel multimodal knowledge graph embedding model to simultaneously learn semantic relation and hierarchical structure of entities within a hyperbolic space. Specifically, we project all modalities features embedding into a hyperbolic space and unify these embeddings to form a multimodal embedding. Then, we model the knowledge graph triplets by treating the relation as a Lorentzian linear transformation from head entity to tail entity. The plausibility of triplets is measured by Lorentz distance. Extensive experiments on multimodal knowledge graph completion benchmarks validate that our model achieves the state-of-the-art results across most metrics. In terms of training speed, our model is one order of magnitude faster than the best one. The visualization results further reveal our model's ability to capture hierarchical structures. Our code is available at https://***/llqy123/HyME. © 2025 IEEE.

关键词： hyperbolic space knowledge graph embedding multimodal knowledge graph

来源：评论

学校读者我要写书评

暂无评论

NetVGE: Netwise Hardware Trojan Detection at RTL Using Variable Dependency and knowledge graph embedding

引用

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Popryho, Yaroslav Pal, Debjit Partin-Vaisband, Inna University of Illinois Chicago Department of Electrical and Computer Engineering Chicago 60607 IL United States

Hardware Trojans (HTs) can be maliciously inserted in integrated circuits (ICs) during various phases of the circuit design process, posing significant security risks. Existing solutions are limited by their dependency on golden references, poor scalability, and suffer from high false positive and negative rates, making them less effective in detecting and mitigating HTs. In this paper, a NetVGE framework is proposed for efficient HT detection at the register-transfer (RT) level. NetVGE generates weighted variable dependency graphs, which are embedded in a latent space in an unsupervised manner using the knowledge graph embedding (KGE) algorithm. The embedded HTs are accurately detected in the latent space with a HittER model. The effectiveness of NetVGE is demonstrated based on RT-level Trust-HUB benchmarks, yielding high recall (93%) and precision (98%). These results validate NetVGEs effectiveness for realworld hardware cybersecurity applications and demonstrate its scalability with increasing IC size compared to state-of-the-art HT detection methods. © 1982-2012 IEEE.

关键词： Hardware Trojans integrated circuits knowledge graph embedding RT-level Trust-HUB benchmarks variable dependency graphs

来源：评论

学校读者我要写书评

暂无评论

knowledge graph embedding in a uniform space

引用

INTELLIGENT DATA ANALYSIS 2024年第1期28卷 33-55页

作者： Tong, Da Chen, Shudong Ma, Rong Qi, Donglin Yu, Yong Chinese Acad Sci Inst Microelect Beijing Peoples R China Univ Chinese Acad Sci Sch Integrated Circuits Beijing Peoples R China

knowledge graph embedding (KGE) is typically used for link prediction to automatically predict missing links in knowledge graphs. Current KGE models are mainly based on complicated mathematical associations, which are highly expressive but ignore the uniformity behind the classical bilinear translational model TransE, a model that embeds all entities of knowledge graphs in a uniform space, enabling accurate embeddings. This study analyses the uniformity of TransE and proposes a novel KGE model called ConvUs that follows uniformity with expressiveness. Based on the convolution neural network (CNN), ConvUs proposes constraints on convolution filter values and employs a multi-layer, multi-scale CNN architecture with a non-parametric L2 norm-based scoring function for the calculation of triple scores. This addresses potential uniformity-related issues in existing CNN-based KGE models, allowing ConvUs to maintain a uniform embedding space while benefiting from the powerful expressiveness of CNNs. Furthermore, circular convolution is applied to alleviate the potential orderliness contradictions, making ConvUs more suitable for conducting uniform space KGE. Our model outperformed the base model ConvKB and several baselines on the link prediction benchmark WN18RR and FB15k-237, demonstrating strong applicability and generalization and indicating that the uniformity of embedding space with high expressiveness enables more efficient knowledge graph embeddings.

关键词： knowledge graph embedding link prediction representation learning convolutional neural network

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：