检索结果-内蒙古大学图书馆

knowledge graph embeddings based on 2d convolution and self-attention mechanisms for link prediction

APPLIED INTELLIGENCE 2025年第2期55卷 1-18页

作者： Zan, Shijie Ji, Weidong Zhou, Guohui Harbin Normal Univ Coll Comp Informat Engn Harbin 150025 Peoples R China

Link prediction refers to using existing facts in the knowledge graph to predict missing facts. This process can enhance the integrity of the knowledge graph and facilitate various downstream applications. However, existing link prediction models usually extract features only in a global or local scope, resulting in feature extraction being limited to a single scope. Additionally, to achieve optimal results, many models require increasing embedding dimensions and parameter numbers, which can lead to scalability issues when applied to large knowledge graphs. To address these issues, we propose a model that fuses the self-attention mechanism with 2D convolution for the link prediction task. The model utilizes a self-attention mechanism with numerous heads to capture feature interactions between entities and relations in the global scope. Furthermore, we innovatively introduce 2D convolution to capture feature interactions in the local scope. Results using FB15k-237 and WN18RR as standard link prediction benchmarks show that our fusion model has good comparable performance with current state-of-the-art models. In particular, compared to the ConvE model (which uses only 2D convolution), our proposed model achieves 13.7% and 14.7% improvement in MRR metrics, and compared to the SAttLE model (which uses only the self-attention mechanism) achieves 2.5% and 0.5% improvement in MRR metrics. Furthermore, due to the low-dimensional embedding of entities and relations, our proposed model has low complexity, good scalability, and thus can accomplish link prediction tasks on larger knowledge graphs in the real world.

关键词： knowledge graph Low-dimensional embedding 2D convolution Multi-head self-attention mechanism Feature interaction R-Drop structure

来源：评论

学校读者我要写书评

暂无评论

knowledge graph-driven personalized attractions recommendations with tourists' long- and short-term interest modeling

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 275卷

作者： Jiang, Qi Han, Yong Ocean Univ China Fac Informat Sci & Engn 238 Songling Rd Qingdao 266100 Peoples R China Qingdao Marine Sci & Technol Ctr Lab Reg Oceanog & Numer Modeling 1 Wenhai Rd Qingdao 266237 Peoples R China

Personalized tourism attraction recommendations are crucial for enhancing travel experiences and supporting the success of tourist attraction development. Despite significant progress in collective wisdom mining and tourist behavior modeling, challenges such as insufficient utilization of data associations and limited interpretability of recommendation results still exist. knowledge graphs (KGs), with their immense potential, remain fully underexplored in the domain of personalized attraction recommendations. To address this gap, we propose a novel knowledge graph Neural Attractions Recommendation (KGNARec) model, which integrates long-term and short-term interests for personalized attraction recommendation. Specifically, we employ graph Convolutional Networks (GCNs) to encode embedded representations of tourists and attractions, designing a personalized knowledge-aware attention mechanism to distinguish the importance of entities and relationships, thereby uncovering tourists' latent preferences. By recursively aggregating information from multi-hop neighbors within the KG, we can capture high-order structural and semantic information, forming a comprehensive representation of tourists' long-term interests. Simultaneously, we consider tourists' short-term interests, extracting insights from their recent travel records through a personalized attention-based Gated Recurrent Unit (GRU) network. These long-term and short-term interests are adaptively fused through a gated fusion network and then compared with candidate attractions to make personalized recommendations. Experiments on a real-world Beijing tourism KG demonstrate that KGNARec achieves an 8.6% improvement in AUC and a 7.1% improvement in ACC over state-of-the-art methods, highlighting its superior performance and interpretability. These findings provide valuable insights for advancing personalized travel services and the development of smart tourism.

关键词： Travel recommendation system knowledge graph graph convolutional networks Long-term interest Short-term interest Personalized recommendation

来源：评论

学校读者我要写书评

暂无评论

knowledge graph Construction: Extraction, Learning, and Evaluation

引用

APPLIED SCIENCES-BASEL 2025年第7期15卷 3727-3727页

作者： Choi, Seungmin Jung, Yuchul Kumoh Natl Inst Technol Dept Comp Engn Gumi 39177 South Korea Kumoh Natl Inst Technol Dept AI Engn Gumi 39177 South Korea

A knowledge graph (KG), which structurally represents entities (nodes) and relationships (edges), offers a powerful and flexible approach to knowledge representation in the field of Artificial Intelligence (AI). KGs have been increasingly applied in various domains-such as natural language processing (NLP), recommendation systems, knowledge search, and medical diagnostics-spurring continuous research on effective methods for their construction and maintenance. Recently, efforts to combine large language models (LLMs), particularly those aimed at managing hallucination symptoms, with KGs have gained attention. Consequently, new approaches have emerged in each phase of KG development, including Extraction, Learning Paradigm, and Evaluation Methodology. In this paper, we focus on major publications released after 2022 to systematically examine the process of KG construction along three core dimensions: Extraction, Learning Paradigm, and Evaluation Methodology. Specifically, we investigate (1) large-scale data preprocessing and multimodal extraction techniques in the KG Extraction domain, (2) the refinement of traditional embedding methods and the application of cutting-edge techniques-such as graph Neural Networks, Transformers, and LLMs-in the KG Learning domain, and (3) both intrinsic and extrinsic metrics in the KG Evaluation domain, as well as various approaches to ensure interpretability and reliability.

关键词： knowledge graph LLM extraction learning evaluation application specific domain

来源：评论

学校读者我要写书评

暂无评论

knowledge graph applications and multi-relation learning for drug repurposing: A scoping review

引用

COMPUTATIONAL BIOLOGY AND CHEMISTRY 2025年 115卷 108364页

作者： Kumar, A. Arun Bhandary, Samarth Hegde, Swathi Gopal Chatterjee, Jhinuk PES Univ Dept Biotechnol Bangalore 560085 India

Objective: Development of novel drug solutions has always been an expensive endeavour, hence drug repurposing as an approach has gained popularity in recent years. In this review we intend to examine one of the most unique computational methods for drug repurposing, that being knowledge graphs. Method: Through literature review we looked at the application of knowledge graphs in medicine, specifically at its use in drug repurposing. We also looked at literature embedding methods, integration of machine learning models and approaches to completion of knowledge graphs. Result: After filtering 43 papers were used for analysis. Timeline, country distribution, application areas of knowledge graph was highlighted. General trends in the use of knowledge graphs for drug repurposing and any shortcomings of the approach was discussed. Conclusion: This approach has gained popularity only very recently;hence it is in a nascent phase.

关键词： Drug repurposing knowledge graph Embedding Multimodal frameworks

来源：评论

学校读者我要写书评

暂无评论

knowledge graph-Augmented ERNIE-CNN Method for Risk Assessment in Secondary Power System Operations

引用

ENERGIES 2025年第8期18卷 2104-2104页

作者： Huang, Xiang Li, Ping Wang, Ye Ren, Xuchao Zhao, Zhenbing Li, Gang State Grid Jiangsu Elect Power Co Nanjing 200024 Peoples R China State Grid Jiangsu Elect Power Co Ltd Huaian Power Supply Branch Huaian 223000 Peoples R China North China Elect Power Univ Sch Elect & Elect Engn Baoding 071003 Peoples R China North China Elect Power Univ Dept Comp Baoding 071003 Peoples R China

With the increasing complexity of modern power systems, traditional risk assessment methods relying on expert experience and historical data face challenges in accuracy and adaptability. This study proposes a knowledge graph-augmented ERNIE-CNN method to enhance risk assessment in secondary power system operations. First, we construct a domain-specific knowledge graph by integrating expert knowledge and operational standards, which enhances semantic understanding and logical reasoning capabilities. Second, an improved ERNIE-CNN model is developed, incorporating an attention mechanism to effectively fuse semantic features and spatial patterns from operational texts. The experimental results on a dataset of 3240 secondary operation records demonstrate the model's superior performance, achieving precision, recall, and F1-scores of 0.878, 0.861, and 0.869, respectively, outperforming benchmarks like BERT. Furthermore, a visualization of the knowledge graph is implemented, providing interpretable decision support for risk management. The proposed method offers a robust framework for automating risk assessment in power systems, with potential applications in smart grid maintenance and safety-critical operational planning.

关键词： knowledge graph smart grid secondary power operations risk assessment ERNIE

来源：评论

学校读者我要写书评

暂无评论

knowledge graph-Enhanced Digital Twin Framework for Optimized Job Shop Scheduling in Smart Manufacturing

引用

IEEE ACCESS 2025年 13卷 19863-19887页

作者： Tarek, Nehal Algarni, Abeer D. El-Hefnawy, Nancy A. Abdel-Kader, Hatem Abdelatey, Amira Menoufia Univ Fac Comp & Informat Informat Syst Dept Shibin Al Kawm 32626 Egypt Princess Nourah Bint AbdulRahman Univ Coll Comp & Informat Sci Dept Informat Technol POB 84428 Riyadh 11671 Saudi Arabia Tanta Univ Fac Comp & Informat Informat Syst Dept Tanta 31527 Egypt

The emergence of Digital Twin (DT) technology over the past decade has introduced a transformative perspective to various research areas, notably the Job Shop Scheduling Problem (JSSP) in smart manufacturing. This paper proposes a novel algorithm to address the JSSP in industrial contexts, operating under different modes to minimize makespan and calculate energy consumption. The approach is grounded in a DT framework that leverages a knowledge graph to represent the assets of the manufacturing system. Two algorithms are designed to balance the time required to complete a list of jobs with the energy consumed by the machines in the factory, all while considering the delivery deadline of the final product. The first algorithm is a genetic algorithm (GA) that minimizes the makespan required to complete the job list for each mode of operation followed by a grey wolf optimization algorithm (GWO) to verify and enhance the results of the GA. The second algorithm uses the results of the first algorithm to calculate the running time and energy consumption for each machine in each production line, considering that the production lines of the factory vary in capacity and power, then computes the total energy consumption and presents the results to the decision maker via a dashboard. The dashboard displays, for each mode of operation, the makespan, total energy consumption, and the deadline for all the jobs. To validate the efficiency and accuracy, a case study of a Smart Poultry Feed Planet (SPFP) has been conducted.

关键词： Job shop scheduling Genetic algorithms Production Optimization Digital twins Smart manufacturing Real-time systems knowledge graphs Energy consumption Databases Digital twin job shop scheduling problem smart manufacturing genetic algorithm grey wolf optimization knowledge graph energy consumption

来源：评论

学校读者我要写书评

暂无评论

knowledge graph-driven decision support for manufacturing process: A graph neural network-based knowledge reasoning approach

引用

ADVANCED ENGINEERING INFORMATICS 2025年 64卷

作者： Su, Chang Jiang, Qi Han, Yong Wang, Tao He, Qingchen Ocean Univ China Dept Informat Sci & Engn Qingdao 266100 Peoples R China Qingdao Marine Sci & Technol Ctr Lab Reg Oceanog & Numer Modeling Qingdao Peoples R China

In modern manufacturing, effectively reusing and sharing knowledge is essential due to the vast amounts of data and resources available. This research introduces a three-layer cognitive manufacturing paradigm that integrates data, knowledge, and decision-making. Our model uses a manufacturing knowledge graph to organize various data sources and applies a dual-driven knowledge reasoning strategy for smooth data-to-knowledge transitions. We developed an automated framework to construct knowledge graphs specifically for machining product knowledge and implemented an RGAT-PRotatE method for regular knowledge updates. The RGAT encoder effectively captures complex relational dynamics using attention mechanisms to focus on key interactions within mechanical processes. Meanwhile, the PRotatE decoder predicts and fills in missing information in the graph. We also introduce a knowledge-centric decision support system that utilizes the knowledge graph's reasoning capabilities. An empirical study on the fabrication of aero-engine casings demonstrates the practicality and effectiveness of our framework, contributing to advancements in cognitive manufacturing and decision-making.

关键词： knowledge graph Manufacturing process Representation learning knowledge reasoning Decision support system graph neural network

来源：评论

学校读者我要写书评

暂无评论

knowledge graph based entity selection framework for ad-hoc retrieval

引用

JOURNAL OF WEB SEMANTICS 2025年 84卷

作者： Singh, Pankaj Bhowmick, Plaban Kumar Symbiosis Inst Technol Dept Artificial Intelligence & Machine Learning Pune 412115 Maharastra India Indian Inst Technol Dept Artificial Intelligence Kharagpur 721302 W Bengal India

Recent entity-based retrieval models utilizing knowledge bases have shown significant improvement in ad-hoc retrieval. However, a lack of coherence between candidate entities can lead to query intent drift at retrieval time. To address this issue, we present an entity selection algorithm that utilizes a graph clustering framework to discover the semantics between entities and encompass the query with highly coherent entities accumulated from different resources, including knowledge bases, and pseudo-relevance feedback documents. Through this work, we propose: (1) An entity acquisition strategy to systematically acquire coherent entities for query expansion. (2) We propose a graph representation of entities to capture the coherence between entities where nodes correspond to the entities and edges represent semantic relatedness between entities. (3) We propose two different entity ranking approaches to select candidate entities based on the coherence with query entities and other coherent entities. A set of experiments on five TREC collections: ClueWeb09B, ClueWeb12B, Robust04, GOV2, and MS-Marco dataset under document retrieval task were conducted to verify the proposed algorithm's performance. The reported results indicated that the proposed methodology outperforms existing state-of-theart retrieval approaches in terms of MAP, NDCG, and P@20. The code and relevant data are available in https://***/pankajkashyap65/knowledgegraph.

关键词： Information retrieval Entity-based retrieval Query expansion knowledge graph Pseudo-relevance feedback

来源：评论

学校读者我要写书评

暂无评论

knowledge graph completion with low-dimensional gated hierarchical hyperbolic embedding

引用

knowledge-BASED SYSTEMS 2025年 309卷

作者： Fang, Yan Liu, Xiaodong Lu, Wei Pedrycz, Witold Lang, Qi Yang, Jianhua Dalian Univ Technol Fac Elect Informat & Elect Engn Sch Control Sci & Engn Dalian 116024 Peoples R China Univ Alberta Dept Elect & Comp Engn Edmonton AB T6R 2V4 Canada Northeast Normal Univ Sch Comp Sci & Informat Technol Changchun 130117 Peoples R China

knowledge graph embedding aims to advance learning performance by deliberating the complexity of hierarchical data structures in a finite-dimensional space. Most traditional Euclidean models struggle to accurately describe and navigate intricate hierarchical relationships between nodes. Hyperbolic embedding methods, particularly when combined with graph neural networks, offer promise ineffectively modeling complex hierarchies in a limited-dimensional space. These methods can incorporate more information about nodes under the same conditions but are also more susceptible to interference from complex neighborhood features. This paper introduces HyperGatE, which novelty combines a hyperbolic graph hierarchical neighbor structure based on a gated filter and a hyperbolic isometric rotation model for knowledge graph completion. By analyzing the hierarchical structure of the knowledge base and using a gated mechanism to form multi-layer embedding networks of entity-relational paths, the gated selects diverse uneven multi-hop relations within the entity neighborhood and measures them through graph attention networks. Furthermore, the simplified hyperbolic isometric model allows for uncovering hierarchical structures in the data. HyperGatE experimentally surpasses some state-of-the-art Euclidean and hyperbolic space models in high and low dimensions across four well-known data, namely WN18RR, FB15k-237, NELL-995, and Kinship.

关键词： knowledge graph Link prediction graph attention networks Poincar & eacute ball model

来源：评论

学校读者我要写书评

暂无评论

knowledge graph as Pre-Training Corpus for Structural Reasoning via Multi-Hop Linearization

引用

IEEE ACCESS 2025年 13卷 7273-7283页

作者： Kim, Wooyoung Jung, Haemin Kim, Wooju Yonsei Univ Dept Ind Engn Seoul 03722 South Korea Korea Natl Univ Transportat Dept Ind Management Engn Chungju Si 27469 Chungcheongbuk South Korea

Large language models have demonstrated exceptional performance across various natural language processing tasks. However, their reliance on unstructured text corpora for pre-training limits their effectiveness in tasks requiring structured reasoning such as multi-hop question-answering. knowledge graphs provide a rich, structured source of relational data, offering an opportunity to enhance the reasoning capabilities of Large language models. In this paper, we propose a novel framework, knowledge graph as Pre-training Corpus (KGPC), which transforms knowledge graphs into text using a multi-hop linearization process. Unlike existing approaches that linearize singular triples, our method captures the interconnected nature of knowledge graphs by linking multiple triples across multiple hops, preserving their relational structure during the pre-training phase. This structured knowledge injection improves language models to perform complex reasoning tasks. We evaluate our approach on multi-hop reasoning benchmarks, demonstrating significant performance gains over existing models, particularly in question-answering tasks. Our results highlight the potential of multi-hop linearization in enhancing the structural reasoning capacity of language models, reducing error propagation, and improving the integration of structured knowledge into language models.

关键词： Cognition knowledge graphs Training Data models Periodic structures Large language models Accuracy Natural language processing knowledge based systems Electronic mail Large language model knowledge graph multi-hop reasoning question-answering

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：