检索结果-内蒙古大学图书馆

NEUROCOMPUTING 2022年 491卷 186-196页

作者： Li, Mingda Sun, Zhengya Zhang, Wensheng Univ Chinese Acad Sci UCAS Beijing 100049 Peoples R China Chinese Acad Sci Res Ctr Precis Sensing & Control Inst Automat Beijing 100190 Peoples R China

knowledge graph embedding acts as a pivotal role in predicting the missing information in knowledge graphs (KGs). Due to the evolving nature of real-world KGs, one requires the ability to make predictions for newly emerging entities besides those already observed at training time. Current studies have made great efforts to develop a neighborhood aggregator and embed out-of-knowledge-graph (OOKG) entities inductively, with less focus on exploiting the similarity between the existing and newly emerging enti-ties. Attaching importance to such similarity helps facilitate semantic transfer. In this work, we propose a similarity-aware aggregation network for embedding out-of-knowledge-graph entities. Motivated by the fact that similar entities are likely to occur in common graph context, we skillfully design a similarity-aware function, which measures the distance of each entity pair based on the contextual gap. Moreover, we aggregate the neighborhood surrounding the target entity and its similarity information by query-specific attention weights, which are optimized during the learning process. Extensive experi-ments on knowledge graph completion task show that our method achieves substantial improvements over baselines.(c) 2022 Elsevier B.V. All rights reserved.

关键词： knowledge graph embedding Out-of-knowledge-graph entities knowledge graph completion Similarity search

来源：评论

学校读者我要写书评

暂无评论

RIECN: learning relation-based interactive embedding convolutional network for knowledge graph

引用

NEURAL COMPUTING & APPLICATIONS 2023年第11期35卷 8343-8356页

作者： Wang, Wei Shen, Xiaoxuan Zhang, Huanyu Li, Zhifei Yi, Baolin Cent China Normal Univ Natl Engn Res Ctr Elearning Wuhan 430079 Peoples R China

Most knowledge graphs(KGs) are large and incomplete graph-structure database, which can be completed by predicting miss links according to the existing knowledge. The mainstream method is knowledge graph embedding (KGE) which is designed to learn low dimensional embedding of entities and relations. However, knowledge graph embedding still faces two major issues: (1) How to generate more expressive embeddings? (2) How to solve semantic polysemy of entities in different relations? In this paper, we propose a novel KG embedding model, RIECN (Relation-based Interactive embedding Convolutional Network), which achieves high-quality performance and shows some advancements in modeling complex relations. In RIECN, FIR (Feature Interaction Reshaping) method is introduced to increase the feature interactions between entity and relation embeddings to generate more expressive feature maps. In addition, a new method of generating relation-based dynamic convolution filters, RDCF, is proposed. RDCF generates specific relation and hybird-size convolution filters, which enriches the feature maps of each entity improving the accuracy of link prediction task especially in complex relations scenario. We tested the performance of our model on five benchmark datasets. The experimental results show that the RIECN model significantly outperforms recent state-of-the-art models by 0.1-3.2% and 1.1-3.7%, in terms of MMR metric and Hit@1 metric, respectively.

关键词： Link prediction knowledge graph embedding Convolution neural network Feature interaction Complex relations

来源：评论

学校读者我要写书评

暂无评论

graph embedding based Query Construction over knowledge graphs 9

Graph Embedding based Query Construction over Knowledge Grap...

引用

9th IEEE International Conference on Big knowledge (ICBK)

作者： Wang, Ruijie Wang, Meng Liu, Jun Yao, Siyu Zheng, Qinghua Xi An Jiao Tong Univ Shaanxi Prov Key Lab Satellite & Terr Network Tec Xian Shaanxi Peoples R China Xi An Jiao Tong Univ Sch Elect & Informat Engn Xian Shaanxi Peoples R China Southeast Univ Sch Comp Sci & Engn Nanjing Jiangsu Peoples R China Guang Dong Xian Jiaotong Univ Acad Shunde Guangdong Peoples R China

ISBN: (纸本)9781538691250

graph-structured queries provide an efficient way to retrieve the desired data from large-scale knowledge graphs. However, it is difficult for non-expert users to write such queries, and users prefer expressing their query intention through natural language questions. Therefore, automatically constructing graph-structured queries of given natural language questions has received wide attention in recent years. Most existing methods rely on natural language processing techniques to perform the query construction process, which is complicated and time-consuming. In this paper, we focus on the query construction process and propose a novel framework which stands on recent advances in knowledge graph embedding techniques. Our framework first encodes the underlying knowledge graph into a low-dimensional embedding space by leveraging the generalized local knowledge graphs. Then, given a natural language question, our framework computes the structure of the target query and determines the vertices/edges which form the target query based on the learned embedding vectors. Finally, the target graph-structured query is constructed according to the query structure and determined vertices/edges. Extensive experiments were conducted on the benchmark dataset. The results demonstrate that our framework outperforms several state-of-the-art baseline models regarding effectiveness and efficiency.

关键词： knowledge graph query construction knowledge graph embedding natural language question answering

来源：评论

学校读者我要写书评

暂无评论

Re-evaluating embedding-Based knowledge graph Completion Methods 18

Re-evaluating Embedding-Based Knowledge Graph Completion Met...

引用

27th ACM International Conference on Information and knowledge Management (CIKM)

作者： Akrami, Farahnaz Guo, Lingbing Hu, Wei Li, Chengkai Univ Texas Arlington Arlington TX 76019 USA Nanjing Univ State Key Lab Novel Software Technol Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781450360142

Incompleteness of large knowledge graphs (KG) has motivated many researchers to propose methods to automatically find missing edges in KGs. A promising approach for KG completion (link prediction) is embedding a KG into a continuous vector space. There are different methods in the literature that learn a continuous representation of KG (latent features of KG). The benchmark dataset FB15k has been widely employed to evaluate these methods. However, It has been noted that FB15k contains many pairs of edges in which a pair represents the same relationship in reverse directions. Therefore, the inverse of numerous test triples occurs in the training set. To address this problem, FB15k-237, a subset of FB15k, was created by removing those inverse-duplicate relations to form a more challenging, realistic dataset. There is not any study that investigates how the aforementioned bias in this widely used benchmark dataset affects the results of embedding-based knowledge graph completion methods and whether their promising results are largely due to the bias. Motivated by this question, we conducted extensive experiments and report the link prediction results on FB15K and FB15k-237 using several embedding-based methods. We compare the results of different methods to see how their performances change in absence of inverse relations. Our experiment results demonstrate that the performance of embedding models in link prediction task diminishes tremendously when the inverse relationships do not exist anymore.

关键词： knowledge graph completion link prediction knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

HyperspherE: An embedding Method for knowledge graph Completion Based on Hypersphere 14th

HyperspherE: An Embedding Method for Knowledge Graph Complet...

引用

14th International Conference on knowledge Science, Engineering, and Management (KSEM)

作者： Dong, Yao Guo, Xiaobo Xiang, Ji Liu, Kai Tang, Zhihao Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China

ISBN: (纸本)9783030821364;9783030821357

knowledge graph completion (KGC) aims to predict missing facts by mining information already present in a knowledge graph (KG). A general solution for KGC task is embedding facts in KG into a low-dimensional vector space. Recently, several embedding models focus on modeling isA relations (i.e., instanceOf and subclassOf), and produce some state-of-the-art performance. However, most of them encode instances as vectors for simplification, which neglects the uncertainty of instances. In this paper, we present a new knowledge graph completion model called HyperspherE to alleviate this problem. Specifically, HyperspherE encodes both instances and concepts as hyperspheres. Relations between instances are encoded as vectors in the same vector space. Afterwards, HyperspherE formulates isA relations by the relative positions between hyperspheres. Experimental results on dataset YAGO39K empirically show that HyperspherE outperforms some existing state-of-the-art baselines, and demonstrate the effectiveness of the penalty term in score function.

关键词： knowledge graph embedding Hypersphere Link prediction Instance Concept IsA relations

来源：评论

学校读者我要写书评

暂无评论

Learning embedding for knowledge graph Completion with Hypernetwork 13th

Learning Embedding for Knowledge Graph Completion with Hyper...

引用

13th International Conference on Computational Collective Intelligence (ICCCI)

作者： Le, Thanh Nguyen, Duy Le, Bac Univ Sci Fac Informat Technol Ho Chi Minh City Vietnam Vietnam Natl Univ Ho Chi Minh City Vietnam

ISBN: (纸本)9783030880811;9783030880804

Link prediction in knowledge graph, also called knowledge completion, is a significant problem in graph mining and has many applications for large companies. The more accurate the link prediction results will bring satisfaction, reduce and avoid risks, and commercial benefits. Almost all state-of-the-art models focus on the deep learning approach, especially using convolutional neural networks (CNN). By analysing the strengths and weaknesses of the CNN based models, we proposed a better model to improve the performance of the link prediction task. Specifically, we apply a CNN with specific filters generated through the Hypernetwork architecture. Moreover, we increase the depth of the model more than baseline models to help learn more helpful information. Experimental results show that the proposed model gets better results when compared to CNN-base models.

关键词： Link prediction knowledge graph embedding Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

CAKE: A Context-Aware knowledge embedding Model of knowledge graph 33rd

CAKE: A Context-Aware Knowledge Embedding Model of Knowledge...

引用

33rd International Conference on Database and Expert Systems Applications (DEXA)

作者： Chen, Jiadong Ke, Hua Mo, Haijian Gao, Xiaofeng Chen, Guihai Shanghai Jiao Tong Univ Dept Comp Sci & Engn MoE Key Lab Artificial Intelligence Shanghai Peoples R China Tongji Univ Shanghai Peoples R China Elect Technol Grp Corp Beijing Peoples R China

ISBN: (纸本)9783031124235;9783031124228

Recently, knowledge embedding on knowledge graph (KG) has drawn increasing attention from both academia and industry for its concise rationale and promising prospects. However, performances of existing knowledge embedding methods are mostly either far from satisfactory, or exhibits weakness for generalization. In this work, a context-aware knowledge embedding model (CAKE) has been proposed for applications like knowledge completion and link prediction. We model the generative process of KG formation based on latent Dirichlet allocation and hierarchical Dirichlet process, where the latent semantic structure of knowledge elements is learned as contexts. Contextual information, i.e. the context-specific probability distribution over elements, is thereafter leveraged in a translation-based embedding model. Essentially, we develop loss function in a probabilistic style to approximately realize the "attention" mechanism in our model. In this work, the learned embeddings of entities and relations are applied to link prediction and triple classification in experiments and our model shows the best performance compared with multiple baselines.

关键词： knowledge graph embedding Information system Latent Dirichlet allocation Hierarchical Dirichlet process

来源：评论

学校读者我要写书评

暂无评论

Independent embedding-Based Relational Enhancement Model for Hyper-Relational knowledge graph 29th

Independent Embedding-Based Relational Enhancement Model for...

引用

29th International Conference on Database Systems for Advanced Applications (DASFAA)

作者： Han, Qilong Li, Jiahang Lu, Dan Li, Lijie Xie, Bingyi Harbin Engn Univ Harbin Peoples R China Georgia State Univ Atlanta GA 30303 USA

ISBN: (纸本)9789819755615;9789819755622

The qualifiers (key-value pairs) in the hyper-relational knowledge graphs (HKGs) help the model accurately identify the target. The primary challenge of HKG is how to efficiently obtain the independent features of entities and relations from qualifiers, which can be utilized to address the issue of their potential confusion with the main triples. However, most current models for HKG utilize identical embedding matrices to represent entities within both main triples and qualifiers, making it hard to capture the precise influence of various qualifiers on relations. To address these issues, we propose an improved model IRE for HKG representation. IRE independently learns the embeddings of qualifiers, which promotes exploring interactions and features between qualifiers and main triples. Then, IRE leverages these features to enhance the semantic richness of relations. We incorporate contrastive learning to distinguish entities and relations with unique semantics further, enhancing the model's learning capabilities. IRE can be applied to various downstream tasks, and we conducted experiments using the link prediction task. Experimental evaluations of multiple datasets demonstrate that the IRE consistently outperforms several state-of-the-art baselines.

关键词： knowledge graph embedding Hyper-relational knowledge graph Contrastive Learning Link Prediction

来源：评论

学校读者我要写书评

暂无评论

ProjR: embedding Structure Diversity for knowledge graph Completion 7th

ProjR: Embedding Structure Diversity for Knowledge Graph Com...

引用

7th CCF International Conference on Natural Language Processing and Chinese Computing, NLPCC

作者： Zhang, Wen Li, Juan Chen, Huajun Zhejiang Univ Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9783319994956;9783319994949

knowledge graph completion aims to find new true links between entities. In this paper, we consider an approach to embed a knowledge graph into a continuous vector space. embedding methods, such as TransE, TransR and ProjE, are proposed in recent years and have achieved promising predictive performance. We discuss that a lot of substructures related with different relation properties in knowledge graph should be considered during embedding. We list 8 kinds of substructures and find that none of the existing embedding methods could encode all the substructures at the same time. Considering the structure diversity, we propose that a knowledge graph embedding method should have diverse representations for entities in different relation contexts and different entity positions. And we propose a new embedding method ProjR which combines TransR and ProjE together to achieve diverse representations by defining a unique combination operator for each relation. In ProjR, the input head entity-relation pairs with different relations will go through a different combination process. We conduct experiments with link prediction task on benchmark datasets for knowledge graph completion and the experiment results show that, with diverse representations, ProjR performs better compared with TransR and ProjE. We also analyze the performance of ProjR in the 8 different substructures listed in this paper and the results show that ProjR achieves better performance in most of the substructures.

关键词： Diversity structures knowledge graph embedding knowledge graph completion

来源：评论

学校读者我要写书评

暂无评论

knowledge graph-based multi-granularity tacit design knowledge reuse for product design

引用

JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING 2025年第1期12卷 53-79页

作者： Jia, Jia Zhang, Yingzhong Saad, Mohamed Dalian Univ Technol Sch Mech Engn Dalian 116024 Peoples R China Yunnan Econ Trade & Foreign Affairs Coll Intelligent Mfg & Automot Coll Kunming 650114 Peoples R China

Decomposing product design into multiple granularities is an effective strategy to implement complex product design. Tacit design knowledge (TDK), adhering to designers' experience and intuition, plays an essential role in the product design at various granularities, but it is difficult to acquire and reuse due to its implicity. Aiming at this issue, a knowledge graph-based multi-granularity TDK reuse framework for product design is presented. First, the design issue-solving oriented knowledge graph (DSKG) model is employed to indirectly capture TDK, where the design result data are represented as design solution nodes and the design issues that refine design solution are represented as relation edges. An improved ontological concept model is designed as the schema of the DSKG to represent the multi-granularity design knowledge on functions, behaviours, and structures of products. Afterwards, the framework supports two design modes, i.e., top-down design and bottom-up design, where the captured TDK is reused to create the design context and predict design solutions. DSKG embedding is employed for design solution prediction in both design modes, while the design context creation is achieved distinctively. In top-down design, the design issue-solving process starts from the design requirements and then gradually downward refines the design solutions at different granularities with breadth-first strategy, which naturally creates the continuous design context, until moving to the detailed design. In bottom-up design, the target design solution is commonly isolated at specific fine-grained granularity. This paper presents a novel approach to constructing design context based on path-ranking algorithm. Path-ranking algorithm can identify the design solution influence paths to build connections between the design requirements and the isolated design solution and thus construct the design context. Finally, a case study for stamping die design is implemented, which illustrat

关键词： tacit design knowledge knowledge graph embedding multi-granularity knowledge reuse design context influence path identification

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：