检索结果-内蒙古大学图书馆

18th Extended Semantic Web Conference (ESWC)

作者： Werner, Simon Rettinger, Achim Halilaj, Lavdim Luttin, Jurgen Trier Univ Trier Germany Bosch Res Renningen Germany

ISBN: (纸本)9783030773854;9783030773847

knowledge graph embeddings (KGE) are vector representations that capture the global distributional semantics of each entity instance and relation type in a static knowledge graph (KG). While KGEs have the capability to embed information related to an entity into a single representation, they are not customizable to a specific context. This is fundamentally limiting for many applications, since the latent state of an entity can change depending on the current situation and the entity's history of related observations. Such context-specific roles an entity might play cannot be captured in global KGEs, since it requires to generate an embedding unique for each situation. This paper proposes a KG modeling template for temporally contextualized observations and introduces the Recurrent Transformer (RETRA), a neural encoder stack with a feedback loop and constrained multi-headed self-attention layers. RETRA enables to transform global KGEs into custom embeddings, given the situation-specific factors of the relation and the subjective history of the entity. This way, entity embeddings for down-stream knowledge graph Tasks (KGT) can be contextualized, like link prediction for location recommendation, event prediction, or driving-scene classification. Our experimental results demonstrate the performance gains standard KGEs can obtain, if they are customized according to the situational context.

关键词： knowledge graph embedding Contextualized embeddings Modeling temporal context

来源：评论

学校读者我要写书评

暂无评论

Integrating knowledge graph embeddings and Pre-trained Language Models in Hypercomplex Spaces 22nd

Integrating Knowledge Graph Embeddings and Pre-trained Langu...

引用

22nd International Semantic Web Conference (ISWC)

作者： Nayyeri, Mojtaba Wang, Zihao Akter, Mst. Mahfuja Alam, Mirza Mohtashim Rony, Md Rashad Al Hasan Lehmann, Jens Staab, Steffen Univ Stuttgart Stuttgart Germany Univ Bonn Bonn Germany Karlsruhe Inst Technol Karlsruhe Germany Tech Univ Dresden Amazon Dresden Germany Univ Southampton Southampton England

ISBN: (纸本)9783031472398;9783031472404

knowledge graphs comprise structural and textual information to represent knowledge. To predict new structural knowledge, current approaches learn representations using both types of information through knowledge graph embeddings and language models. These approaches commit to a single pre-trained language model. We hypothesize that heterogeneous language models may provide complementary information not exploited by current approaches. To investigate this hypothesis, we propose a unified framework that integrates multiple representations of structural knowledge and textual information. Our approach leverages hypercomplex algebra to model the interactions between (i) graph structural information and (ii) multiple text representations. Specifically, we utilize Dihedron models with 4*D dimensional hypercomplex numbers to integrate four different representations: structural knowledge graph embeddings, word-level representations (e.g., Word2vec and FastText), sentence-level representations (using a sentence transformer), and document-level representations (using FastText or Doc2vec). Our unified framework score the plausibility of labeled edges via Dihedron products, thus modeling pairwise interactions between the four representations. Extensive experimental evaluations on standard benchmark datasets confirm our hypothesis showing the superiority of our two new frameworks for link prediction tasks.

关键词： knowledge graph embedding Pre-trained Language Model Textual Information

来源：评论

学校读者我要写书评

暂无评论

Fantastic knowledge graph embeddings and How to Find the Right Space for Them 19th

Fantastic Knowledge Graph Embeddings and How to Find the Rig...

引用

19th International Semantic Web Conference (ISWC)

作者： Nayyeri, Mojtaba Xu, Chengjin Vahdati, Sahar Vassilyeva, Nadezhda Sallinger, Emanuel Yazdi, Hamed Shariat Lehmann, Jens Univ Bonn Smart Data Analyt Grp SDA Bonn Germany InfAI Dresden Lab Dresden Germany Univ Oxford Oxford England TU Wien Vienna Austria Fraunhofer IAIS Dresden Lab Dresden Germany

ISBN: (纸本)9783030624194;9783030624187

During the last few years, several knowledge graph embedding models have been devised in order to handle machine learning problems for knowledge graphs. Some of the models which were proven to be capable of inferring relational patterns, such as symmetry or transitivity, show lower performance in practice than those not allowing to infer those patterns. It is often unknown what factors contribute to such performance differences among KGE models in the inference of particular patterns. We develop the concept of a solution space as a factor that has a direct influence on the practical performance of knowledge graph embedding models as well as their capability to infer relational patterns. We showcase the effect of solution space on a newly proposed model dubbed SpacEss. We describe the theoretical considerations behind the solution space and evaluate our model against state-of-the-art models on a set of standard benchmarks namely WordNet and FreeBase.

关键词： Link prediction knowledge graph embedding Relation pattern Solution space knowledge completion

来源：评论

学校读者我要写书评

暂无评论

Leveraging knowledge graph embeddings for Natural Language Question Answering 24th

Leveraging Knowledge Graph Embeddings for Natural Language Q...

引用

24th International Conference on Database Systems for Advanced Applications (DASFAA)

作者： Wang, Ruijie Wang, Meng Liu, Jun Chen, Weitong Cochez, Michael Decker, Stefan Xi An Jiao Tong Univ Natl Engn Lab Big Data Analyt 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 Univ Queensland Sch Informat Technol & Elect Engn Brisbane Qld Australia Fraunhofer FIT D-53754 St Augustin Germany Rhein Westfal TH Aachen Informat 5 Aachen Germany Univ Jyvaskyla Fac Informat Technol Jyvaskyla Finland

ISBN: (纸本)9783030185763;9783030185756

A promising pathway for natural language question answering over knowledge graphs (KG-QA) is to translate natural language questions into graph-structured queries. During the translation, a vital process is to map entity/relation phrases of natural language questions to the vertices/edges of underlying knowledge graphs which can be used to construct target graph-structured queries. However, due to linguistic flexibility and ambiguity of natural language, the mapping process is challenging and has been a bottleneck of KG-QA models. In this paper, we propose a novel framework, called KemQA, which stands on recent advances in relation phrase dictionaries and knowledge graph embedding techniques to address the mapping problem and construct graph-structured queries of natural language questions. Extensive experiments were conducted on question answering benchmark datasets. The results demonstrate that our framework outperforms state-of-the-art baseline models in terms of effectiveness and efficiency.

关键词： knowledge graph Natural language question answering knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

Biomedical knowledge graph embeddings for Personalized Medicine 1

引用

20th EPIA Conference on Artificial Intelligence (EPIA)

作者： Vilela, Joana Asif, Muhammad Marques, Ana Rita Santos, Joao Xavier Rasga, Celia Vicente, Astrid Martiniano, Hugo Inst Nacl Saude Doutor Ricardo Jorge Lisbon Portugal BioISI Biosyst & Integrat Sci Inst Lisbon Portugal

ISBN: (数字)9783030862305

ISBN: (纸本)9783030862305;9783030862299

Personalized medicine promises to revolutionize healthcare in the coming years. However significant challenges remain, namely in regard to integrating the vast amount of biomedical knowledge generated in the last few years. Here we describe an approach that uses knowledge graph embedding (KGE) methods on a biomedical knowledge graph as a path to reasoning over the wealth of information stored in publicly accessible databases. We use curated databases such as Ensembl, DisGeNET and Gene Ontology as data sources to build a knowledge graph containing relationships between genes, diseases and other biological entities and explore the potential of KGE methods to derive medically relevant insights from this KG. To showcase the method's usefulness we describe two use cases: a) prediction of gene-disease associations and b) clustering of disease embeddings. We show that the top gene-disease associations predicted by this approach can be confirmed in external databases or have already been identified in the literature. An analysis of clusters of diseases, with a focus on Autism Spectrum Disorder (ASD), affords novel insights into the biology of this paradigmatic complex disorder and the overlap of its genetic background with other diseases.

关键词： knowledge graph embedding Personalized medicine Gene-disease associations

来源：评论

学校读者我要写书评

暂无评论

Multimodal knowledge graph embeddings via Lorentz-based Contrastive Learning

Multimodal Knowledge Graph Embeddings via Lorentz-based Cont...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Liu, Ruizhou Cao, Zongsheng Wu, Zhe Xu, Qianqian Huang, Qingming Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing Peoples R China Pengcheng Lab Dept Networked Intelligence Shenzhen Peoples R China Chinese Acad Sci Key Lab Intelligent Informat Proc Inst Comp Technol Beijing Peoples R China Chinese Acad Sci Inst Informat Engn Beijing Peoples R China

ISBN: (纸本)9798350390155;9798350390162

Multimodal knowledge graph embeddings (MKGE) have recently garnered significant attention. Unlike traditional unimodal knowledge graph embeddings, MKGE integrates both structural and multimodal knowledge to represent entities within a unified framework. However, real-world entities exhibit heterogeneity, often resulting in semantic inconsistencies where structurally similar embeddings may diverge significantly in their multimodal representations. Previous approaches primarily focus on directly fusing structural and multimodal embeddings, thus overlooking the issue of semantic-embedding inconsistency. To tackle this issue, we propose a new multimodal knowledge graph embedding method via Lorentz-based contrastive learning (LCKGE). we firstly introduce a well-designed nearest-neighbor fusion module via contrastive learning for multimodal fusion. Then, an attention-based Lorentz transformation is proposed for capturing more complex geometric information in MKGs. Furthermore, a series of comprehensive experiments are conducted to demonstrate the effectiveness of our model. We provide the code and appendix of LCKGE in https://***/RuizhouLiu/ LCKGE

关键词： multimodal knowledge graph knowledge graph embedding lorentz transformations

来源：评论

学校读者我要写书评

暂无评论

An Evaluation of Hubness Reduction Methods for Entity Alignment with knowledge graph embeddings 13

An Evaluation of Hubness Reduction Methods for Entity Alignm...

引用

13th International Joint Conference on knowledge Discovery, knowledge Engineering and knowledge Management (IC3K) / 13th International Conference on knowledge Engineering and Ontology Development (KEOD)

作者： Obraczka, Daniel Rahm, Erhard Univ Leipzig ScaDSAI Database Grp Leipzig Germany

ISBN: (纸本)9789897585333

The heterogeneity of knowledge graphs is problematic for conventional data integration frameworks. A possible solution to this issue is using knowledge graph embeddings (KGEs) to encode entities into a lower-dimensional embedding space. However, recent findings suggest that KGEs suffer from the so-called hubness phenomenon. A dataset that suffers from hubness has a few popular entities that are nearest neighbors of a highly disproportionate amount of other entities. Because the calculation of nearest neighbors is an integral part of entity alignment with KGEs, hubness reduces the accuracy of the matching result. We therefore investigate a variety of hubness reduction techniques and utilize approximate nearest neighbor (ANN) approaches to offset the increase in time complexity stemming from the hubness reduction. Our results suggest, that hubness reduction in combination with ANN techniques improves the quality of nearest neighbor results significantly compared to using no hubness reduction and exact nearest neighbor approaches. Furthermore, this advantage comes without losing the speed advantage of ANNs on large datasets.

关键词： Hubness Reduction Nearest Neighbor Search knowledge graph embedding Entity Alignment

来源：评论

学校读者我要写书评

暂无评论

Towards Understanding the Impact of graph Structure on knowledge graph embeddings 18th

Towards Understanding the Impact of Graph Structure on Knowl...

引用

18th International Conference on Neural-Symbolic Learning and Reasoning (NeSy)

作者： Dave, Brandon Christou, Antrea Shimizu, Cogan Wright State Univ Dayton OH 45435 USA

ISBN: (纸本)9783031711695;9783031711701

knowledge graphs (KGs) are an established paradigm for integrating heterogeneous data and representing knowledge. As such, there are many different methodologies for producing KGs, which span notions of expressivity, and are tailored for different use-cases and domains. Now, as neurosymbolic methods rise in prominence, it is important to understand how the development of KGs according to these methodologies impact downstream tasks, such as link prediction using KG embeddings (KGE). In this paper, we modify FB15k-237 in several ways (e.g., by increasingly including semantic metadata). This significantly changes the graph structure (e.g., centrality). We assess how these changes impact the link prediction task, using six KGE models.

关键词： knowledge graph knowledge graph embedding FB15k-237

来源：评论

学校读者我要写书评

暂无评论

Swift and Sure: Hardness-aware Contrastive Learning for Low-dimensional knowledge graph embeddings 22

Swift and Sure: Hardness-aware Contrastive Learning for Low-...

引用

31st ACM Web Conference (WWW)

作者： Wang, Kai Liu, Yu Sheng, Quan Z. Dalian Univ Technol Sch Software Key Lab Ubiquitous Network & Serv Software Liaoni Dalian Liaoning Peoples R China Macquarie Univ Sch Comp Intelligent Comp Lab Sydney NSW Australia

ISBN: (纸本)9781450390965

knowledge graph embedding (KGE) has shown great potential in automatic knowledge graph (KG) completion and knowledge-driven tasks. However, recent KGE models suffer from high training cost and large storage space, thus limiting their practicality in real-world applications. To address this challenge, based on the latest findings in the field of Contrastive Learning, we propose a novel KGE training framework called Hardness-aware Low-dimensional embedding (HaLE). Instead of the traditional Negative Sampling, we design a new loss function based on query sampling that can balance two important training targets, Alignment and Uniformity. Furthermore, we analyze the hardness-aware ability of recent low-dimensional hyperbolic models and propose a lightweight hardnessaware activation mechanism, which can help the KGE models focus on hard instances and speed up convergence. The experimental results show that in the limited training time, HaLE can effectively improve the performance and training speed of KGE models on five commonly-used datasets. After training just a few minutes, the HaLE-trained models are competitive compared to the state-of-the-art models in both low- and high-dimensional conditions.

关键词： knowledge graph embedding Contrastive Learning Link Prediction knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Machine learning estimated probability of relapse in early-stage non-small-cell lung cancer patients with aneuploidy imputation scores and knowledge graph embeddings

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年 235卷

作者： Buosi, Samuele Timilsina, Mohan Janik, Adrianna Costabello, Luca Torrente, Maria Provencio, Mariano Fey, Dirk Novacek, Vit Univ Galway Data Sci Inst Univ Rd Galway H91 TK33 Co Galway Ireland Masaryk Univ Fac Informat Botanicka 68a Brno 60200 Czech Republic Masaryk Mem Canc Inst Zluty Kopec 7 Brno 65653 Czech Republic Accenture Labs Grand Canal Dock D02 YN32 Co Dublin Ireland Hosp Univ Puerta de Hierro Majadahonda Med Oncol Dept C Joaquin Rodrigo 1 Majadahonda 28222 Madrid Spain Univ Coll Dublin Syst Biol Ireland Dublin Co Dublin Ireland

Motivation: Low-stage lung cancer is known to recur unpredictably, and patients receiving various treatment methods like radiation, chemotherapy, and immunotherapies have been seen to respond very differently. Identifying a priori if a patient is going to relapse or not could make a difference in terms of saving lives and personalized care offered. In this work, we provide an answer to the following research question: Is it possible to enhance the machine learning (ML) of the estimated probability of relapse in early-stage non-small-cell lung cancer (NSCLC) patients with aneuploidy imputation scores?Results: To predict recurrence in 1,348 early-stage (I-II) NSCLC patients, we train graph ML models utilizing the Spanish pulmonary cancer group knowledge graph enriched with triples from pathway imputation. ML models trained on knowledge graph data enriched with triples from pathway score imputation present an 82% Precision and 91% Specificity in predicting relapse over 200 patients from a held-out test set. ML models trained using graphs data could prove useful supplemental tool in the TNM classification systems and improve a lung cancer patient's prognosis.

关键词： Non-small-cell lung cancer Tumor recurrence prediction knowledge graph embedding Machine learning Link prediction

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：