检索结果-内蒙古大学图书馆

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

Integrating Structure and Text for Enhancing hyper-relational knowledge graph Representation via Structure Soft Prompt Tuning 24

Integrating Structure and Text for Enhancing Hyper-relationa...

引用

33rd ACM International Conference on Information and knowledge Management (CIKM)

作者： Li, Lijie Wang, Hui Li, Jiahang Xu, Xiaodi Wang, Ye Ren, Tao Harbin Engn Univ Harbin Heilongjiang Peoples R China Chinese Acad Sci State Key Lab Intelligent Game Inst Software Beijing Peoples R China

ISBN: (纸本)9798400704369

Different from traditional knowledge graphs, where facts are usually represented as (subject, relation, object), hyper-relational knowledge graphs (HKGs) allow facts to be associated with additional relation-entity pairs to constrain the validity of facts. HKGs contain a substantial amount of textual information, which plays a crucial role in enriching representations. However, existing HKG embedding methods mainly rely on structural information but overlook textual information in HKGs, which are less effective in representing entities with limited structural information. To address this issue, the paper proposes HIST (hyper-relational knowledge graph Encoder Integrating Structure and Text), which incorporates textual information and structural information in HKGs to enhance representations of entities and relations. HIST adopts the graph convolutional network to extract structural information and utilizes it to generate the Structure Soft Prompt. During the Structure Soft Prompt Tuning process, the textual information and structural information are fully integrated to generate more comprehensive representations. Additionally, an effective contrastive learning method for HKG embedding is formulated to improve the efficiency of negative sampling. Experimental results show that HIST achieves state-of-the-art performance on several public datasets. Our code is available at https://***/QieFangBaiLuQingYaJian/HIST.

关键词： hyper-relational knowledge graph hyper-relational knowledge graph Embedding Soft Prompt

来源：评论

学校读者我要写书评

暂无评论

Improvement on message passing of hyper-relational knowledge graph 22

Improvement on message passing of hyper-relational knowledge...

引用

Proceedings of the 2022 5th International Conference on E-Business, Information Management and Computer Science

作者： Zhaokun Wang Bei Hui Xue Zhou Yanping Wu University of Electronic Science and Technology of China China

ISBN: (纸本)9781450397827

Unlike traditional knowledge graphs (KGs), which represent real-world facts as entity-relationship-entity triples, hyper-relational knowledge graphs allow triples of traditional entities with additional relation-entity pairs (also known as qualifiers) to establish connections to deliver more complicated messages. Modelling triplet-qualifier relationships effectively for hyper-relational knowledge graphs to accomplishing prediction tasks is an existing challenge. In this paper, an improved hyper-relational knowledge graph completion method, STARE, is proposed by introducing two new methods: (1) Reconstructing the graph neural network module in the original STARE; (2) Introducing centralization and scaling to the model-the idea of shrinking to avoid over-smoothing. In our experiments on four benchmark datasets, the proposed method is always better than STARE, improving the prediction ability of the completion of HKGs.

关键词： graph neural network hyper-relational knowledge graph knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Dual-view embedding for hyper-relational knowledge graphs with hierarchical structure

引用

JOURNAL OF INTELLIGENT INFORMATION SYSTEMS 2025年 1-18页

作者： Liu, Shuang Xu, Liangyang Liu, Yiying Kolmanic, Simon Dalian Minzu Univ Sch Comp Sci & Engn 31 Jinshi Rd Dalian 116600 Peoples R China Univ Maribor Fac Elect Engn & Comp Sci Koroska Cesta 46 Maribor 2000 Slovenia

This study proposes a dual-view hyper-relational knowledge graph embedding model aimed at addressing the challenges of embedding complex relationships in knowledge graphs. Traditional methods primarily handle simple triplet relations and struggle with the complexity of hyper-relations. By integrating instance view and ontology view, our model, DVHE, captures hierarchical structural information between entities and is applied to link prediction tasks. Experimental results show that DVHE significantly outperforms existing single-view and dual-view models across multiple benchmark datasets, particularly in handling complex hyper-relations and hierarchical information. Ablation studies further validate the effectiveness of the model's components, providing new insights for the development of knowledge graph embeddings.

关键词： hyper-relational knowledge graph Dual-view embedding Link prediction graph neural network

来源：评论

学校读者我要写书评

暂无评论

Symbolic knowledge Reasoning on hyper-relational knowledge graphs

引用

IEEE TRANSACTIONS ON BIG DATA 2025年第2期11卷 578-590页

作者： Wang, Zikang Li, Linjing Zeng, Daniel Dajun Chinese Acad Sci Inst Automat State Key Lab Multimodal Artificial Intelligence S Beijing 100190 Peoples R China

knowledge reasoning has been widely researched in knowledge graphs (KGs), but there has been relatively less research on hyper-relational KGs, which also plays an important role in downstream tasks. Existing reasoning methods on hyper-relational KGs are based on representation learning. Though this approach is effective, it lacks interpretability and ignores the graph structure information. In this paper, we make the first attempt at symbolic reasoning on hyper-relational KGs. We introduce rule extraction methods based on both individual facts and paths, and propose a rule-based symbolic reasoning approach, hyperPath. This approach is simple and interpretable, it can serve as a baseline model for symbolic reasoning in hyper-relational KGs. We provide experimental results on almost all datasets, including five large-scale datasets and seven sub-datasets of them. Experiments show that the expressive power of the proposed model is similar to simple neural networks like convolutional networks, but not as advanced as more complex networks such as Transformer and graph convolutional networks, which is consistent with the performance of symbolic methods on KGs. Furthermore, we also analyze the impact of rule length and hyperparameters on the model's performance, which can provide insights for future research in hypergraph symbolic reasoning.

关键词： Cognition Representation learning Tensors Spread spectrum communication knowledge graphs Big Data Transformers hyper-relational knowledge graph knowledge reasoning multi-hop reasoning

来源：评论

学校读者我要写书评

暂无评论

Research on Predicting Super-relational Data Links for Mine Hoists Within hyper-relational knowledge graphs

引用

INFORMATION 2025年第1期16卷 3-3页

作者： Dang, Xiaochao Shu, Xiaoling Li, Fenfang Dong, Xiaohui Northwest Normal Univ Coll Comp Sci & Engn Lanzhou 730070 Gansu Peoples R China

hyper-relational knowledge graphs can enhance the intelligence, efficiency, and reliability of industrial production by enabling equipment collaboration and optimizing supply chains. However, the construction of knowledge graphs in industrial fields faces significant challenges due to the complexity of hyper-relational data, the sparsity of industrial datasets, and limitations in existing link prediction methods, which struggle to capture the nuanced relationships and qualifiers often present in industrial scenarios. This paper proposes the HyLinker model, designed to improve the representation of entities and relations through modular components, including an entity neighbor aggregator, a relation qualifier aggregator, MoE-LSTM (Mixture of Experts Long Short-Term Memory), and a convolutional bidirectional interaction module. Experimental results demonstrate that the proposed method performs well on both public datasets and a self-constructed hoisting machine dataset. In the Mine Hoist Super-Relationship Dataset (MHSD-100), HyLinker outperforms the latest models, with improvements of 0.142 in MRR (Mean Reciprocal Rank) and 0.156 in Hit@1 (Hit Rate at Rank 1), effectively addressing the knowledge graph completion problem for hoisting machines and providing more accurate information for equipment maintenance and fault prediction. These results demonstrate the potential of HyLinker in overcoming current challenges and advancing the application of hyper-relational knowledge graphs in industrial contexts.

关键词： industrial intelligence hyper-relational knowledge graph link prediction HyLinker equipment maintenance

来源：评论

学校读者我要写书评

暂无评论

MHRE: Multivariate link prediction method for medical hyper-relational facts

引用

APPLIED INTELLIGENCE 2024年第2期54卷 1311-1334页

作者： Wang, Weiguang Zhang, Xuanyi Zhang, Juan Cai, Wei Zhao, Haiyan Zhang, Xia Northeastern Univ Sch Comp Sci & Engn Shenyang 110819 Liaoning Peoples R China Neusoft Res Intelligent Healthcare Technol Co Ltd Shenyang 110167 Liaoning Peoples R China Shanghai Univ Engn Sci Sch Elect & Elect Engn Shanghai 201620 Peoples R China Peking Univ Sch Comp Sci Beijing 100871 Peoples R China Minist Educ Key Lab High Confidence Software Technol PKU Beijing 100871 Peoples R China

As hyper-relational facts continue to proliferate within knowledge graphs, link prediction on binary relations has become inadequate, while link prediction on hyper-relations has emerged as a research hotspot. Existing methods typically employ n-ary tuples, primary triple with auxiliary descriptions, or hypergraphs to represent hyper-relational facts and conduct link prediction. However, medical hyper-relational facts are more intricate and frequently lack multiple components, which presents challenges for current methods in conveying their structure, semantics, and predicting multiple missing elements simultaneously. To address these issues, in this paper, we introduce MHRE, the pioneering link prediction method specifically designed for medical hyper-relational facts. Initially, we represent medical hyper-relational facts as a heterogeneous multi-relational directed graph with hyper-relations at its core to depict both its structure and implicit semantics. Next, we develop a role-aware graph attention mechanism network to acquire distributed vector representations of entities and relations within the graph. Importantly, it fine-tunes the semantic weights of different components within hyper-relational facts by incorporating neighboring nodes and role information through learning. Lastly, we devise a prediction module based on self-attention mechanisms, enabling the simultaneous prediction of multiple missing elements within a medical hyper-relational fact. We conduct experiments using publicly available datasets, such as JF17K, WikiPeople, and their adapted versions, alongside a proprietary medical dataset. We compare MHRE with state-of-the-art baselines and further conduct ablation studies and parameter analysis. The experimental results confirm the efficacy and superiority of MHRE. In a range of benchmark tests involving hyper-relational facts, MHRE consistently outperforms current state-of-the-art methods.

关键词： hyper-relational knowledge graph Medical knowledge graph Link prediction knowledge graph completion knowledge representation learning

来源：评论

学校读者我要写书评

暂无评论

hyper²: hyperbolic embedding for hyper-relational link prediction

引用

NEUROCOMPUTING 2022年 492卷 440-451页

作者： Yan, Shiyao Zhang, Zequn Sun, Xian Xu, Guangluan Jin, Li Li, Shuchao Chinese Acad Sci Aerosp Informat Res Inst Beijing 100190 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Key Lab Network Informat Syst Technol NIST Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100190 Peoples R China

knowledge graphs (KGs) Embedding has been broadly studied in recent years. However, less light is shed on the ubiquitous hyper-relational KGs. Most existing hyper-relational KG embedding methods decompose n-ary facts into smaller tuples, undermining the structure of n-ary facts. Moreover, these models always suffer from low expressiveness and high complexity. In this work, to tackle the indecomposability issue, we represent n-ary fact as a hyperedge, keeping the integrity of fact and maintaining the vital role that primary triple plays. To address the expressiveness and complexity issue, we propose hyper2 where we generalize hyperbolic Poincare embedding from binary to arbitrary arity data, and we design an information aggregation module to capture the interaction between entities within and beyond triple. Extensive experiments demonstrate hyper2 is superior to its translational and deep analogues, improving MRR and other metrics by a large margin with relatively few dimensions. Moreover, we study the side effect of literals, and we theoretically and experimentally compare the computational complexity of hyper2 against several best-performing baselines. hyper2 is much quicker than its counterparts. (C) 2022 Published by Elsevier B.V.

关键词： Link prediction knowledge graph embedding hyperbolic space hyper-relational knowledge graph hyper-relational link prediction

来源：评论

学校读者我要写书评

暂无评论

hyper-relational knowledge Representation Learning with Multi-hypergraph Disentanglement 25

Hyper-Relational Knowledge Representation Learning with Mult...

引用

34th ACM Web Conference, WWW 2025

作者： Li, Jiecheng Luo, Xudong Lu, Guangquan Zhang, Shichao School of Computer Science and Engineering Key Lab of Education Blockchain and Intelligent Technology of the Ministry of Education Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin China

ISBN: (纸本)9798400712746

hyper-relational knowledge graphs (HKGs) extend the traditional triplet-based knowledge graph by adding qualifiers to the relationships, making HKGs particularly useful for tasks that require more profound understanding and inference from relationships between entities. However, existing hyper-relational knowledge representation learning methods (HKRL) focus on direct neighbourhood information of entities only by neglecting the relational similarity of the main triple in hyper-relational facts and the attribute details in the qualifiers. In addition, few works extract common and private information across multiple views to minimize noise and interference. This paper proposes a multi-hypergraph disentanglement method for HKRL to address the above issues. Specifically, we first construct four hypergraphs to mine and utilise the inherent structure information of HKGs, and then propose to extract common representations among hypergraphs and private representations within individual hypergraphs to mine the semantic information and the task-relevant information, respectively. Experiment results on four real datasets demonstrate the effectiveness of the proposed method compared to SOTA methods in link prediction tasks on HKGs. © 2025 Copyright held by the owner/author(s).

关键词： hyper-relational knowledge graph

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：