检索结果-内蒙古大学图书馆

knowledge graph embedding by relational and entity rotation

knowledge-BASED SYSTEMS 2021年 229卷 107310-107310页

作者： Huang, Xuqian Tang, Jiuyang Tan, Zhen Zeng, Weixin Wang, Ji Zhao, Xiang Natl Univ Def Technol Sci & Technol Informat Syst Engn Lab Changsha 410073 Peoples R China

knowledge graphs are typical large-scale multi-relational structures and useful for many artificial intelligence tasks. However, knowledge graphs often have missing facts, which limits the development of downstream tasks. To refine the knowledge graphs, knowledge graph embedding models have been developed. knowledge graph embedding models aim to learn distributed representations for entities and relations and predict unknown triplets by scoring candidate triplets. Nevertheless, state-of-the-art works either aim to capture different relation patterns, or to model the multi-fold relations, and yet fail to consider these two aspects simultaneously. To fill this gap, in this paper, we propose a novel knowledge graph embedding model, MRotatE. It exploits triplet features from the perspective of relational and entity rotations, which can model and infer various relation patterns and handle with multi-fold relations at the same time. The experimental results demonstrate that MRotatE outperforms existing approaches and attains the state-of-the-art performance. (C) 2021 The Author(s). Published by Elsevier B.V.

关键词： knowledge graph embedding Relation pattern Multi-fold relation Relational and entity rotation

来源：评论

学校读者我要写书评

暂无评论

knowledge graph embedding by translating in time domain space for link prediction

引用

knowledge-BASED SYSTEMS 2021年 212卷 106564-106564页

作者： Zhang, Qianjin Wang, Ronggui Yang, Juan Xue, Lixia Hefei Univ Technol Sch Comp & Informat Hefei 230601 Peoples R China

knowledge graph embedding, which aims to learn distributed representations of entities and relations, has been proven to be an effective method for predicting missing links in knowledge graphs. Existing knowledge graph embedding models mainly consider that the space where head and tail entities are located has the same properties. However head and tail entities can be different types of objects, and they should not be located in the vector space with the same properties. In this paper, we propose a novel knowledge graph embedding model called TimE, which presents each entry of the head (or tail) entity embeddings as a point in time domain space, and the corresponding entry of tail (or head) entity embeddings as a point in frequency domain space. Specifically, TimE defines each relation as a composition relation, which consists of a translation between entities and a diagonal projection matrix that projects the entities into the time domain space. In addition, we propose a cross-operation to model inverse and symmetric relations. Experimental results show that TimE not only outperforms existing state-of-the-art models on several large-scale benchmark datasets for the link prediction task, but also can better capture diversity distribution of entity embeddings for different relation patterns effectively, and can also model all relation patterns (including symmetry/antisymmetry, inversion, and composition). (C) 2020 Elsevier B.V. All rights reserved.Y

关键词： knowledge graph embedding Link prediction Cross-operation Self-interaction

来源：评论

学校读者我要写书评

暂无评论

knowledge graph question answering based on TE-BiLTM and knowledge graph embedding 2021

Knowledge graph question answering based on TE-BiLTM and kno...

引用

5th International Conference on Innovation in Artificial Intelligence (ICIAI)

作者： Li, Jianbin Qu, Ketong Li, Kunchang Chen, Zhiqiang Fang, Suwan Yan, Jingchen North China Elect Power Univ Sch Control & Comp Engn Beijing Peoples R China

ISBN: (纸本)9781450388634

A Abstract: knowledge graph question answering (KGQA) aims to use facts in the knowledge graph to answer natural language questions. Relation extraction, as one of the sub-tasks of the KGQA, is an important and difficult problem in the KGQA. To improve the accuracy of relation extraction in KGQA, in this paper, we propose a new deep neural network model called Transformer Encoder-BiLSTM (TE-BiLSTM). We give the detailed design of our method and our experimental results demonstrate that our approach can not only achieve better results in relation extraction, but can also outperform the state-of-the-art approaches in the KGQA.

关键词： knowledge graph question answering knowledge graph embedding Deep learning Self-attention mechanism TE-BiLSTMJianbin Li Ketong Qu KunChang Li ZhiQiang Chen SuWan Fang Jingchen Yan. 2021

来源：评论

学校读者我要写书评

暂无评论

A knowledge graph embedding Based Approach for Learning Path Recommendation for Career Goals 13th

A Knowledge Graph Embedding Based Approach for Learning Path...

引用

13th International Conference on Computational Collective Intelligence (ICCCI)

作者： Nguyen, Thu Tran Minh Tran, Thinh Pham Quoc Univ Sci Fac Informat Technol Ho Chi Minh City Vietnam Viet Nam Natl Univ Ho Chi Minh City Vietnam

ISBN: (纸本)9783030880811;9783030880804

Nowadays, many online courses in the Information Technology (IT) field provided by different organizations make it difficult for learners to screen the courses that are best suitable for their career development. Many approaches have been raised to suggest a personalized learning path based on the learner's career goals;however, most of them use traditional techniques and face the problems of sparse data, cold start, and lack of advisory results' interpretation. In this paper, we address these problems by using knowledge graph embedding (KGE) which is known as one of approaches of graph-based models. This approach has emerged as a phenomenon and has not been widely applied in the field of learning path recommendation. We propose a new knowledge graph (KG) architecture for representing entities and their semantic relationships. The main entities identified in the KG are courses, occupations, the units of knowledge, and the relationships are the semantic connections between these entities. In existing KG architectures only exploit the hierarchy of intermediate knowledge units. Whereas, our KG architecture provides a specific classification of these learning objects, and this helps the semantic relationship of the subjects become more unambiguous and connected. Then, we explore and build experiments for our proposed KG architecture by using KGE techniques to prove the effectiveness. The experimental results show that our solution is worth considering and promises to bring a high degree of efficiency in the learning path recommendation system.

关键词： knowledge graph embedding knowledge graph structure Learning path recommendation for career goals graph database

来源：评论

学校读者我要写书评

暂无评论

LightCAKE: A Lightweight Framework for Context-Aware knowledge graph embedding 25th

LightCAKE: A Lightweight Framework for Context-Aware Knowled...

引用

25th Pacific-Asia Conference on knowledge Discovery and Data Mining (PAKDD)

作者： Ning, Zhiyuan Qiao, Ziyue Dong, Hao Du, Yi Zhou, Yuanchun Chinese Acad Sci Comp Network Informat Ctr Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (纸本)9783030757687;9783030757670

knowledge graph embedding (KGE) models learn to project symbolic entities and relations into a continuous vector space based on the observed triplets. However, existing KGE models cannot make a proper trade-off between the graph context and the model complexity, which makes them still far from satisfactory. In this paper, we propose a lightweight framework named LightCAKE for context-aware KGE. LightCAKE explicitly models the graph context without introducing redundant trainable parameters, and uses an iterative aggregation strategy to integrate the context information into the entity/relation embeddings. As a generic framework, it can be used with many simple KGE models to achieve excellent results. Finally, extensive experiments on public benchmarks demonstrate the efficiency and effectiveness of our framework.

关键词： knowledge graph embedding Lightweight graph context

来源：评论

学校读者我要写书评

暂无评论

knowledge graph embedding Based on Relevance and Inner Sequence of Relations 27th

Knowledge Graph Embedding Based on Relevance and Inner Seque...

引用

27th International Conference on Neural Information Processing

作者： Peng, Jia Gao, Neng Li, Min Yuan, Jun Chinese Acad Sci Inst Informat Engn SKLOIS Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China

ISBN: (纸本)9783030638191;9783030638207

knowledge graph embedding can obtain the low-dimensional dense vectors, which helps to reduce the high dimension and heterogeneity of knowledge graph (KG), and enhance the application of KG. Many existing methods focus on building complex models, elaborate feature engineering or increasing learning parameters, to improve the performance of embedding. However, these methods rarely capture the influence of intrinsic relevance and inner sequence of the relations in KG simultaneously, while balancing the number of parameters and the complexity of the algorithm. In this paper, we propose a concatenate knowledge graph embedding method based on relevance and inner sequence of relations (KGERSR). In this model, for each < head, relation, tail > triple, we use two partially shared gates for head and tail entities. Then we concatenate these two gates to capture the inner sequence information of the triples. We demonstrate the effectiveness of the proposed KGERSR on standard FB15k-237 and WN18RR datasets, and it gives about 2% relative improvement over the state-of-the-art method in terms of Hits@1, and Hits@10. Furthermore, KGERSR has fewer parameters than ConmplEX and TransGate. These results indicate that our method could be able to find a better trade-off between complexity and performance.

关键词： knowledge graph embedding Relations relevance Inner sequence Cascade model

来源：评论

学校读者我要写书评

暂无评论

knowledge graph incremental embedding for unseen modalities

引用

knowledge AND INFORMATION SYSTEMS 2023年第9期65卷 3611-3631页

作者： Wei, Yuyang Chen, Wei Wen, Shiting Liu, An Zhao, Lei Soochow Univ Sch Comp Sci & Technol Suzhou 215006 Jiangsu Peoples R China NingboTech Univ Sch Comp & Data Engn Ningbo 315100 Zhejiang Peoples R China

knowledge graph embedding (KGE) projects entities and relations into low-dimension continuous vector space, which promotes the widespread use of knowledge graphs in many downstream applications. Despite the fact that most of existing KGE models focus on static single-modal knowledge graphs, many knowledge graphs are incremental and multi-modal in the real world. Especially, the incremental entities are accompanied by new modalities, i.e., unseen modalities in background knowledge graphs. To well address the novel task, i.e., incrementally embed the new entities with unseen modal information effectively and efficiently, we propose a novel incremental multi-modal knowledge graph embedding model entitled Multi-Modal Rotating on Hyperplanes, which consists of the following two modules. (1) To gain a high-quality background KGE space, the module Background knowledge graph embedding Module is developed to fuse seen modal information with a gated multi-modal encoder and decode the triples by a rotation-based KGE model. (2) The module Incremental knowledge graph embedding Module is designed to fuse unseen modal information of incremental entities and incrementally embed the new entities into the trained embedding space. Extensive experiments are conducted on two real-world multi-modal datasets, and the results demonstrate the superiority of the proposed model in terms of both effectiveness and efficiency compared with the state-of-the-art approaches.

关键词： knowledge graph knowledge graph embedding Incremental embedding Unseen modalities

来源：评论

学校读者我要写书评

暂无评论

Multi-hop knowledge graph Reasoning Based on Hyperbolic knowledge graph embedding and Reinforcement Learning 10

Multi-hop Knowledge Graph Reasoning Based on Hyperbolic Know...

引用

10th International Joint Conference on knowledge graphs (IJCKG)

作者： Zhou, Xingchen Wang, Peng Luo, Qiqing Pan, Zhe Southeast Univ Sch Comp Sci & Engn Nanjing Peoples R China

ISBN: (纸本)9781450395656

Some unseen facts in knowledge graphs (KGs) can be complemented by multi-hop knowledge graph reasoning. The process of multi-hop reasoning can be presented as a serialized decision problem, and then be solved with reinforcement learning (RL). However, existing RL-based reasoning methods cannot deal with the hierarchical information in KGs effectively. To solve this issue, we propose a novel RL-based multi-hop KG reasoning model Path Additional Actionspace Ranking (PAAR). Our model first proposes a hyperbolic knowledge graph embedding (KGE) model which can effectively capture hierarchical information in KGs. To introduce hierarchical information into RL, the hyperbolic KGE vector is subsequently added to the state space and helps to expand the action space. In order to alleviate the reward sparsity problem in RL, our model utilizes the score function of hyperbolic KGE model as a soft reward. Finally, the metric of hyperbolic space is added to the training of RL as a penalty strategy to constrain the sufficiency of multi-hop reasoning paths. Experimental results on two real-world datasets show that our proposed model not only provides effective answers but also offers sufficient paths.

关键词： knowledge graph reasoning reinforcement learning knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

HRS: Hybrid Recommendation System based on Attention Mechanism and knowledge graph embedding

HRS: Hybrid Recommendation System based on Attention Mechani...

引用

IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT)

作者： Dong, Chunfang Ju, Xuchan Ma, Yue Zhengzhou Univ Zhengzhou Key Lab Big Data Anal & Applicat Henan Acad Big Data Zhengzhou Peoples R China Shenzhen Univ Coll Math & Stat Shenzhen Peoples R China

ISBN: (纸本)9781450391870

Traditional recommendation methods often have sparsity and cold start problems in real applications. Researchers found that introducing knowledge graphs into recommender systems as a kind of auxiliary information can alleviate these problems and improve the performance of the recommender systems. This paper put forward a Hybrid Recommendation System based on Attention Mechanism and knowledge graph embedding (HRS). It uses cross&compress unit and preference propagation respectively to enrich the features of items and users. In this process, we use the attention mechanism and knowledge graph embedding to enhance the recommender system. After obtaining the user vector representation and the item vector representation, we can predict the probability of the user clicking on the item. The experiments on three datasets derived from the actual scenes demonstrate the competitiveness of HRS, compared with several state-of-the-art baselines in the recommendation.

关键词： recommender systems knowledge graph attention mechanism knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

A Lightweight knowledge graph embedding Framework for Efficient Inference and Storage 21

A Lightweight Knowledge Graph Embedding Framework for Effici...

引用

30th ACM International Conference on Information and knowledge Management (CIKM)

作者： Wang, Haoyu Wang, Yaqing Lian, Defu Gao, Jing Purdue Univ W Lafayette IN 47907 USA Univ Sci & Technol China Hefei Peoples R China Yangtze River Delta Informat Intelligence Innovat Wuhu Peoples R China

ISBN: (纸本)9781450384469

knowledge graphs, which consist of entities and their relations, have become a popular way to store structured knowledge. knowledge graph embedding (KGE), which derives a representation for each entity and relation, has been widely used to capture the semantics of the information in the knowledge graphs, and has demonstrated great success in many downstream applications, such as the extraction of similar entities in response to a query entity. However, existing KGE methods cannot work well on emerging knowledge graphs that are large-scale due to the constraints in storage and inference efficiency. In this paper, we propose a lightweight KGE model, LightKG, which significantly reduces storage as well as running time needed for inference. Instead of storing a continuous vector for every entity, LightKG only needs to store a few codebooks, each of which contains some codewords that correspond to the representatives among the embeddings, and the indices that correspond to the codeword selections for entities. Hence LightKG can achieve highly efficient storage. The efficiency of the downstream querying process can be significantly boosted too with the proposed LightKG model as the relevance score between the query and an entity can be efficiently calculated via a quick look-up in a table that contains the scores between the query and codewords. The storage and inference efficiency of LightKG is achieved by its novel design. LightKG is an end-to-end framework that automatically infers codebooks and codewords and generates an approximated embedding for each entity. A residual module is included in LightKG to induce the diversity among codebooks, and a continuous function is adopted to approximate codeword selection, which is non-differential. In addition, to further improve the performance of KGE, we propose a novel dynamic negative sampling method based on quantization, which can be applied to the proposed LightKG or other KGE methods. We conduct extensive experiments on

关键词： knowledge graph embedding quantization

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：