检索结果-内蒙古大学图书馆

Open-world knowledge graph completion for unseen entities and relations via attentive feature aggregation

INFORMATION SCIENCES 2022年 586卷 468-484页

作者： Oh, Byungkook Seo, Seungmin Hwang, Jimin Lee, Dongho Lee, Kyong-Ho Yonsei Univ Dept Comp Sci Seoul South Korea

Most of knowledge graph completion (KGC) models are designed for static KGs where entity and relation sets are fixed. These approaches are inherently transductive because they simply predict the plausibility of facts whose entities and relations had to previously appear in the training phase. However, since entities and relations are constantly added, removed, or changed over time, KGC models should be able to generalize to out-of-KG entities and relations in evolving KGs, which are more suited to real-world scenarios. Moreover, incorporating global graph-structured information into KGC models is another challenging issue. To overcome these issues, this paper proposes a novel Inductive KG embedding (IKGE) model for open-world KGC, which accommodates out-of-KG entities and relations. Unlike training individual unique embeddings, the proposed model fundamentally learns an embedding generator function to elaborately generate fact embeddings in an inductive manner. Specifically, the feature information of each fact is extracted as a vector from its entity-related and relation-related side information via an attention mechanism. Then, to score a given fact, our neighborhood feature aggregator hierarchically accumulates the feature information of multi-hop neighbors. Experimental results show that IKGE outperforms existing approaches in both transductive and inductive setups by successfully aggregating neighborhood features.(c) 2021 Elsevier Inc. All rights reserved.

关键词： knowledge graph embedding Link prediction graph-based learning graph convolutional networks Deep learning Attention model

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

Degree aware based adversarial graph convolutional networks for entity alignment in heterogeneous knowledge graph

引用

NEUROCOMPUTING 2022年第0期487卷 99-109页

作者： Wang, Hanchen Wang, Yining Li, Jianfeng Luo, Tao Beijing Univ Posts & Telecommun Beijing Lab Adv Informat Networks Beijing Key Lab Network Syst Architecture & Conve Beijing Peoples R China

Entity alignment, as the vital technique for knowledge graph construction and integration, aims to match entities that refer to the same real-world identity in different knowledge graphs (KGs). Recently, much effort has been devoted to embedding-based methods for entity alignment. For most of such methods, the entity with a high degree is hard to be aligned with its equivalent counterpart with a low degree. This degree difference between equivalent entities poses a great challenge for entity alignment. To solve this problem, a novel entity alignment framework that integrates a graph convolutional network (GCN) based embedding initializer and a degree aware generative adversarial network is proposed. In particular, the embedding initializer utilizes a GCN with highway gates to generate the preliminary embedding of entities based on their topological characteristics in the KGs. By alleviating the relevance between embeddings and degree features, the degree aware GAN mitigates the impact of degree difference and generates the final degree level irrelevant alignment result. To quantify the heterogeneity between the KGs, an evaluation metric called heterogeneity entropy of degree (HED) that represents the degree difference is defined in this paper. Based on HED, the impact of KG heterogeneity on the performance of the proposed DAGCN model is investigated based on WK3l-15k and DBP15k datasets. The experimental results show that the proposed degree aware adversarial graph convolutional network (DAGCN) outperforms other state-of-the-art methods over all metrics, especially when the HED is large. (C) 2022 Elsevier B.V. All rights reserved.

关键词： knowledge graph Entity alignment knowledge graph embedding graph convolutional network Generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

TOWARDS GEOSPATIAL knowledge graph INFUSED NEURO-SYMBOLIC AI FOR REMOTE SENSING SCENE UNDERSTANDING

TOWARDS GEOSPATIAL KNOWLEDGE GRAPH INFUSED NEURO-SYMBOLIC AI...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Potnis, Abhishek Lunga, Dalton Sorokine, Alexandre Dias, Philipe Yang, Lexie Arndt, Jacob Bowman, Jordan Wohlgemuth, Jason Oak Ridge Natl Lab Geospatial Sci & Human Secur Div Oak Ridge TN 37830 USA

ISBN: (纸本)9798350320107

Deep learning has proven its effectiveness in numerous tasks for remote sensing scene understanding. However there is an increasing interest to explore fusion of domain-specific background information to the deep neural network to further improve its performance. Remote sensing researchers are also working towards developing models that generalize and adapt to multiple applications. Generalization challenges coupled with the scarcity of large corpora of high-quality noise-free labelled data, have together fueled an interest for leveraging background information. knowledge graphs serve as excellent choice to represent domain-specific information in a structured, standardized and extensible manner. Integrating symbolic knowledge representations in the form of knowledge graph embedding (KGE) to perform neuro-symbolic reasoning is an emerging research direction promising significant impacts. This vision paper seeks to position ideas and provoke early thoughts toward advancing neuro-symbolic artificial intelligence in the context of geospatial challenges. Specifically, it conceptualizes and elaborates on an architecture for infusing geospatial knowledge from knowledge graph in a deep neural network pipeline. As guiding case studies - land-use land-cover classification, object detection and instance segmentation can benefit from infusing spatio-contextual information with remote sensing imagery. The discussion further reflects on and articulates the challenges and explainable AI opportunities anticipated when scaling and maintaining large-scale geospatial knowledge graphs.

关键词： geospatial knowledge graphs neuro-symbolic knowledge-infused learning remote sensing scene understanding deep learning representation learning knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

knowledge-embedded Prompt Learning for Zero-shot Social Media Text Classification 9

Knowledge-embedded Prompt Learning for Zero-shot Social Medi...

引用

IEEE International Conference on Smart Computing (SMARTCOMP)

作者： Li, Jingyi Chen, Qi Wang, Wei Wu, Fangyu Xian Jiaotong Liverpool Univ Sch AI & Adv Comp Suzhou Peoples R China Xian Jiaotong Liverpool Univ Dept Comp Suzhou Peoples R China Xian Jiaotong Liverpool Univ Dept Intelligent Sci Suzhou Peoples R China

ISBN: (纸本)9798350322811

Social media plays an irreplaceable role in shaping the way information is created shared and consumed. While it provides access to a vast amount of data, extracting and analyzing useful insights from complex and dynamic social media data can be challenging. Deep learning models have shown promise in social media analysis tasks, but such models require a massive amount of labelled data which is usually unavailable in real-world settings. Additionally, these models lack common-sense knowledge which can limit their ability to generate comprehensive results. To address these challenges, we propose a knowledge-embedded prompt learning model for zero-shot social media text classification. Our experimental results on four social media datasets demonstrate that our proposed approach outperforms other well-known baselines.

关键词： Zero-shot text classification prompt learning knowledge graph embedding social media data analysis

来源：评论

学校读者我要写书评

暂无评论

Learning with cone-based geometric models and orthologics

引用

ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE 2022年第11-12期90卷 1159-1195页

作者： Leemhuis, Mena Oezcep, Ozgur L. Wolter, Diedrich Univ Lubeck Lubeck Germany Univ Bamberg Bamberg Germany

Recent approaches for knowledge-graph embeddings aim at connecting quantitative data structures used in machine learning to the qualitative structures of logics. Such embeddings are of a hybrid nature, they are data models that also exhibit conceptual structures inherent to logics. One motivation to investigate embeddings is to design conceptually adequate machine learning (ML) algorithms that learn or incorporate ontologies expressed in some logic. This paper investigates a new approach to embedding ontologies into geometric models that interpret concepts by geometrical structures based on convex cones. The ontologies are assumed to be represented in an orthologic, a logic with a full (ortho)negation. As a proof of concept this cone-based embedding was implemented within two ML algorithms for weak supervised multi-label learning. Both algorithms rely on cones but the first addresses ontologies expressed in classical propositional logic whereas the second addresses a weaker propositional logic, namely a weak orthologic that does not fulfil distributivity. The algorithms were evaluated and showed promising results that call for investigating other (sub)classes of cones and developing fine-tuned algorithms based on them.

关键词： Concept learning knowledge graph embedding Support-vector machine Multi-label learning Orthologic

来源：评论

学校读者我要写书评

暂无评论

Can Ensemble Calibrated Learning Enhance Link Prediction? A Study on Commonsense knowledge 15th

Can Ensemble Calibrated Learning Enhance Link Prediction? A ...

引用

15th Asian Conference on Intelligent Information and Database Systems (ACIIDS)

作者： Racharak, Teeradaj Jearanaiwongkul, Watanee Thwe, Khine Myat Japan Adv Inst Sci & Technol Sch Informat Sci Nomi Japan Asian Inst Technol Khlong Luang Thailand

ISBN: (纸本)9789819958368;9789819958375

Numerous prior works have shown how we can use knowledge graph embedding (KGE) models for ranking unseen facts that are likely to be true. Though these KGE models have been shown to make good performance on the ranking task with standard benchmark datasets, in practice only a subset of the top-k ranked list is indeed correct. This is due to the fact that most knowledge graphs are built under the open world assumption, while state-of-the-art KGE exploit the closed world assumption to build negative samples for training. In this paper, we show to address this problem by ensembling calibrated learning, following the principle that multiple calibrated models can make a stronger one. In experiments on the ConceptNet of commonsense knowledge base, we show significant improvement over each individual baseline model. This suggests that ensembling calibrated learning is a promising technique to improve link prediction with KGEs.

关键词： Link prediction knowledge graph embedding Ensemble learning Commonsense knowledge base ConceptNet

来源：评论

学校读者我要写书评

暂无评论

Next-Generation Security Entity Linkage: Harnessing the Power of knowledge graphs and Large Language Models 23

Next-Generation Security Entity Linkage: Harnessing the Powe...

引用

16th ACM International Systems and Storage Conference (SYSTOR)

作者： Alfasi, Daniel Shapira, Tal Bremler-Barr, Anat Reichman Univ Dept Comp Sci Herzliyya Israel Tel Aviv Univ Dept Comp Sci Tel Aviv Israel

ISBN: (纸本)9781450399623

With the continuous increase in reported Common Vulnerabilities and Exposures (CVEs), security teams are overwhelmed by vast amounts of data, which are often analyzed manually, leading to a slow and inefficient process. To address cybersecurity threats effectively, it is essential to establish connections across multiple security entity databases, including CVEs, Common Weakness Enumeration (CWEs), and Common Attack Pattern Enumeration and Classification (CAPECs). In this study, we introduce a new approach that leverages the RotatE [4] knowledge graph embedding model, initialized with embeddings from Ada language model developed by OpenAI [3]. Additionally, we extend this approach by initializing the embeddings for the relations.

关键词： CVE CWE CAPEC knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

An End-to-End knowledge graph Based Question Answering Approach for COVID-19 8th

An End-to-End Knowledge Graph Based Question Answering Appro...

引用

8th Annual China Conference on Health Information Processing (CHIP)

作者： Qiao, Yinbo Yang, Zhihao Lin, Hongfei Wang, Jian Dalian Univ Technol Dalian 116024 Peoples R China

ISBN: (纸本)9789811998645;9789811998652

Question Answering based on knowledge graph (KG) has emerged as a popular research area in general domain. However, few works focus on the COVID-19 kg-based question answering, which is very valuable for biomedical domain. In addition, existing question answering methods rely on knowledge embedding models to represent knowledge (i.e., entities and questions), but the relations between entities are neglected. In this paper, we construct a COVID-19 knowledge graph and propose an end-to-end knowledge graph question answering approach that can utilize relation information to improve the performance. Experimental result shows that the effectiveness of our approach on the COVID-19 knowledge graph question answering. Our code and data are available at https:// ***/CHNcreater/COVID-19-KGQA.

关键词： COVID-19 knowledge graph knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

knowledge graph Representation Learning via Generated Descriptions 28th

Knowledge Graph Representation Learning via Generated Descri...

引用

28th International Conference on Applications of Natural Language to Information Systems (NLDB)

作者： Hu, Miao Lin, Zhiwei Marshall, Adele Queens Univ Belfast Sch Math & Phys Belfast Antrim North Ireland

ISBN: (纸本)9783031353192;9783031353208

knowledge graph representation learning (KGRL) aims to project the entities and relations into a continuous low-dimensional knowledge graph space to be used for knowledge graph completion and detecting new triples. Using textual descriptions for entity representation learning has been a key topic. However, the current work has two major constraints: (1) some entities do not have any associated descriptions;(2) the associated descriptions are usually phrases, and they do not contain enough information. This paper presents a novel KGRL method for learning effective embeddings by generating meaningful descriptive sentences from entities' connections. The experiments using four public datasets and a new proposed dataset show that the New Description-Embodied knowledge graph embedding (NDKGE for short) approach introduced in this paper outperforms most of the existing work in the task of link prediction. The code and datasets of this paper can be obtained from GitHub (https://***/MiaoHu-Pro/NDKGE.)

关键词： knowledge graph embedding Entity description Constructing new descriptions 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：