检索结果-内蒙古大学图书馆

Augmenting embedding Projection With Entity Descriptions for knowledge graph Completion

IEEE ACCESS 2021年 9卷 159955-159964页

作者： Chen, Junfan Xu, Jie Bo, Manhui Tang, Hongwu Beihang Univ Sch Comp Sci & Engn Beijing 100083 Peoples R China Univ Leeds Sch Comp Leeds LS2 9JT W Yorkshire England Travelsky Mobile Technol Ltd Beijing 100029 Peoples R China

Extra information, such as hierarchical entity types, entity descriptions or some text corpus are recently used to enhance knowledge graph Completion (KGC). A typical task in this setting is building entities' description information into some embedding models. Existing approaches under this task usually use simple embedding models, which have difficulty in handling the complex structures of the knowledge graphs. These models are also limited in the way where description representation is combined with structure representation, which requires an impractical large set of weight parameters increasing in proportion to the number of entities in the knowledge graph. This paper aims at developing more effective embedding models that jointly represent the structure information of the knowledge base with the description of entities and efficiently reduce the model parameters. We propose more principled approaches named Dimensional Attentive Combination (DAC) for the composition of structure representation and description representation with fixed-size parameters independent of entity amount, and the composition builds upon more powerful knowledge graph embedding models. The proposed model significantly reduces the weight parameters and can extend to KGs with a large set of entities or involving sparse data. Experimental comparison on link prediction and relation prediction shows that our approaches, even under a simple description-encoding model, improve upon the baselines by a significant margin.

关键词： Task analysis Electronic mail Predictive models Licenses Urban areas Solid modeling Probabilistic logic knowledge graph completion knowledge graph embedding text representation attention

来源：评论

学校读者我要写书评

暂无评论

EARR: Using rules to enhance the embedding of knowledge graph

引用

EXPERT SYSTEMS WITH APPLICATIONS 2023年第1期232卷

作者： Li, Jin Xiang, Jinpeng Cheng, Jianhua Harbin Engn Univ Coll Comp Sci & Technol Harbin Peoples R China Harbin Engn Univ Coll Intelligent Syst Sci & Engn Harbin Peoples R China

knowledge graphs have been receiving increasing attention from researchers. However, most of these graphs are incomplete, leading to the rise of knowledge graph completion as a prominent task. The goal of knowledge graph completion is to find missing relations in a knowledge graph. knowledge graph embedding represents the entities and relations in a low-dimensional embedding space, simplifying operations and allowing for integration with knowledge graph completion tasks. Several popular embedding models, such as TransE, TransH, TransR, TuckER, RotatE, and others have achieved impressive results on knowledge graph completion tasks. However, most of these methods do not incorporate background knowledge that could enhance the quality of knowledge embedding. Logic rules are adaptable and scalable, which can enrich background knowledge, and separating the attributes of entities can improve the relevance of relations and facilitate the accuracy of logic rule extraction. Thus, we propose a novel method, named Entity-Attribute-Relation-Rule (EARR), which separates attributes from entities and uses logic rules to extend the dataset, improving the accuracy of knowledge graph completion tasks. We define a total of six rules in this paper, including Rule 1-3, Rule 5, and Rule 6 for entities, and Rule 4 for entities and attributes. We evaluate our method based on the task of link prediction through two kinds of experiments. In the basic experiment, we compare our method with three benchmark models, namely, TransE, TransH, and TransR. In the experiment with different size datasets, FB24K and CoDEx, we evaluate our method on different size datasets with different models, including TransE, TuckER, and RotatE. The experimental results indicate that EARR can improve the quality of knowledge graph embedding.

关键词： knowledge graph knowledge graph embedding Rule extraction Rule enhanced knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

Regularized online tensor factorization for sparse knowledge graph embeddings

引用

NEURAL COMPUTING & APPLICATIONS 2023年第1期35卷 787-797页

作者： Zulaika, Unai Almeida, Aitor Lopez-de-Ipina, Diego Univ Deusto DeustoTech Fac Engn Avda Univ 2 Bilbao 48007 Bizkaia Spain

knowledge graphs represent real-world facts and are used in several applications;however, they are often incomplete and have many missing facts. Link prediction is the task of completing these missing facts from existing ones. embedding models based on Tensor Factorization attain state-of-the-art results in link prediction. Nevertheless, the embeddings they produce can not be easily interpreted. Inspired by previous work on word embeddings, we propose inducing sparsity in the bilinear tensor factorization model, RESCAL, to build interpretable knowledge graph embeddings. To overcome the difficulties that stochastic gradient descent has when producing sparse solutions, we add l(1) regularization to the learning objective by using the generalized Regularized Dual Averaging online optimization algorithm. The proposed method substantially improves the interpretability of the learned embeddings while maintaining competitive performance in the standard metrics.

关键词： knowledge graph embedding Sparse learning Interpretable embeddings

来源：评论

学校读者我要写书评

暂无评论

INK: knowledge graph embeddings for node classification

引用

DATA MINING AND knowledge DISCOVERY 2022年第2期36卷 620-667页

作者： Steenwinckel, Bram Vandewiele, Gilles Weyns, Michael Agozzino, Terencio De Turck, Filip Ongenae, Femke IDLab Technol Pk Zwijnaarde 126 B-9050 Ghent Belgium

Deep learning techniques are increasingly being applied to solve various machine learning tasks that use knowledge graphs as input data. However, these techniques typically learn a latent representation for the entities of interest internally, which is then used to make decisions. This latent representation is often not comprehensible to humans, which is why deep learning techniques are often considered to be black boxes. In this paper, we present INK: Instance Neighbouring by using knowledge, a novel technique to learn binary feature-based representations, which are comprehensible to humans, for nodes of interest in a knowledge graph. We demonstrate the predictive power of the node representations obtained through INK by feeding them to classical machine learning techniques and comparing their predictive performances for the node classification task to the current state of the art: graph Convolutional Networks (R-GCN) and RDF2Vec. We perform this comparison both on benchmark datasets and using a real-world use case.

关键词： knowledge graph representation knowledge graph embedding Node classification Semantic data mining

来源：评论

学校读者我要写书评

暂无评论

Schema-Aware Hyper-Relational knowledge graph embeddings for Link Prediction

引用

IEEE TRANSACTIONS ON knowledge AND DATA ENGINEERING 2024年第6期36卷 2614-2628页

作者： Lu, Yuhuan Yang, Dingqi Wang, Pengyang Rosso, Paolo Cudre-Mauroux, Philippe Univ Macau State Key Lab Internet Things Smart City Taipa Macao Peoples R China Univ Macau Dept Comp & Informat Sci Taipa Macao Peoples R China Univ Fribourg Fribourg Switzerland

knowledge graph (KG) embeddings have become a powerful paradigm to resolve link prediction tasks for KG completion. The widely adopted triple-based representation, where each triplet (h, r, t) links two entities h and t through a relation r, oversimplifies the complex nature of the data stored in a KG, in particular for hyper-relational facts, where each fact contains not only a base triplet (h, r, t), but also the associated key-value pairs (k, v). Even though a few recent techniques tried to learn from such data by transforming a hyper-relational fact into an n-ary representation (i.e., a set of key-value pairs only without triplets), they result in suboptimal models as they are unaware of the triplet structure, which serves as the fundamental data structure in modern KGs and preserves the essential information for link prediction. Moreover, as the KG schema information has been shown to be useful for resolving link prediction tasks, it is thus essential to incorporate the corresponding hyper-relational schema in KG embeddings. Against this background, we propose sHINGE, a schema-aware hyper-relational KG embedding model, which learns from hyper-relational facts directly (without the transformation to the n-ary representation) and their corresponding hyper-relational schema in a KG. Our extensive evaluation shows the superiority of sHINGE on various link prediction tasks over KGs. In particular, compared to a sizeable collection of 21 baselines, sHINGE consistently outperforms the best-performing triple-based KG embedding method, hyper-relational KG embedding method, and schema-aware KG embedding method by 19.1%, 1.8%, and 12.9%, respectively.

关键词： Hyper-relation knowledge graph embedding link prediction schema

来源：评论

学校读者我要写书评

暂无评论

Recommender systems based on neuro-symbolic knowledge graph embeddings encoding first-order logic rules

引用

USER MODELING AND USER-ADAPTED INTERACTION 2024年第5期34卷 2039-2083页

作者： Spillo, Giuseppe Musto, Cataldo de Gemmis, Marco Lops, Pasquale Semeraro, Giovanni Univ Bari Aldo Moro Dipartimento Informat Via Edoardo Orabona 4 I-70125 Bari Italy

In this paper, we present a knowledge-aware recommendation model based on neuro-symbolic graph embeddings that encode first-order logic rules. Our approach is based on the intuition that is the basis of neuro-symbolic AI systems: to combine deep learning and symbolic reasoning in one single model, in order to take the best out of both the paradigms. To this end, we start from a knowledge graph (KG) encoding information about users, ratings, and descriptive properties of the items and we design a model that combines background knowledge encoded in logical rules mined from the KG with explicit knowledge encoded in the triples of the KG itself to obtain a more precise representation of users and items. Specifically, our model is based on the combination of: (i) a rule learner that extracts first-order logic rules based on the information encoded in the knowledge graph;(ii) a graph embedding module, that jointly learns a vector space representation of users and items based on the triples encoded in the knowledge graph and the rules previously extracted;(iii) a recommendation module that uses the embeddings to feed a deep learning architecture that provides users with top-k recommendations. In the experimental section, we evaluate the effectiveness of our strategy on three datasets, and the results show that the combination of knowledge graph embeddings and first-order logic rules led to an improvement in the predictive accuracy and in the novelty of the recommendations. Moreover, our approach overcomes several competitive baselines, thus confirming the validity of our intuitions.

关键词： Recommender systems Neuro-symbolic AI knowledge-aware recommender systems knowledge graph knowledge graph embedding First-order logic First-order logic rules

来源：评论

学校读者我要写书评

暂无评论

QuatSE: Spherical Linear Interpolation of Quaternion for knowledge graph embeddings 11th

QuatSE: Spherical Linear Interpolation of Quaternion for Kno...

引用

11th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC)

作者： Li, Jiang Su, Xiangdong Ma, Xinlan Gao, Guanglai Inner Mongolia Univ Coll Comp Sci Hohhot Peoples R China Natl & Local Joint Engn Res Ctr Intelligent Infor Hohhot Peoples R China Inner Mongolia Key Lab Mongolian Informat Proc Te Hohhot Peoples R China

ISBN: (纸本)9783031171208;9783031171192

knowledge graph embedding aims to learn representations of entities and relations in a knowledge graph. Recently, QuatE has introduced the graph embeddings into the quaternion space. However, there are still challenges in dealing with complex patterns, including 1-N, N1, and multiple-relations between two entities. Since the learned entity embeddings tend to overlap with each other in the first two cases, and the learned relation embeddings tend to overlap with each other in the last case. To deal with these issues, we propose QuatSE, a novel knowledge embedding model that adjusts graph embeddings via spherical linear interpolation (Slerp) of entities and relations. For a triple (head entity, relation, tail entity), QuatSE calculates Slerp between each entity and its relation, and adds the normalized interpolation to the corresponding entity. The operation avoids the problem of embedding overlap and ensures the information of original entity is not missed. We further compare the effect of interpolation using different normalization strategies (L1 or L2) for Slerp. Several experiments suggest that QuatSE works well in 1-N, N-1 and multiple-relations pattern. QuatSE outperforms the existing quaternion-based models.

关键词： knowledge graph embedding Spherical linear interpolation Quaternion

来源：评论

学校读者我要写书评

暂无评论

knowledge graph embeddings for dealing with concept drift in machine learning

引用

JOURNAL OF WEB SEMANTICS 2021年 67卷 100625-100625页

作者： Chen, Jiaoyan Lecue, Freddy Pan, Jeff Z. Deng, Shumin Chen, Huajun Univ Oxford Dept Comp Sci Oxford England INRIA Le Chesnay Rocquencourt France Thales CortAIx Montreal PQ Canada Univ Aberdeen Dept Comp Sci Aberdeen Scotland Huawei Knowledge Graph Lab Reading Berks England Zhejiang Univ Coll Comp Sci & Technol Hangzhou Peoples R China ZJU Alibaba Joint Lab Knowledge Engine Hangzhou Peoples R China

Data stream learning has been largely studied for extracting knowledge structures from continuous and rapid data records. As data is evolving on a temporal basis, its underlying knowledge is subject to many challenges. Concept drift,1 as one of core challenge from the stream learning community, is described as changes of statistical properties of the data over time, causing most of machine learning models to be less accurate as changes over time are in unforeseen ways. This is particularly problematic as the evolution of data could derive to dramatic change in knowledge. We address this problem by studying the semantic representation of data streams in the Semantic Web, i.e., ontology streams. Such streams are ordered sequences of data annotated with ontological vocabulary. In particular we exploit three levels of knowledge encoded in ontology streams to deal with concept drifts: i) existence of novel knowledge gained from stream dynamics, ii) significance of knowledge change and evolution, and iii) (in)consistency of knowledge evolution. Such knowledge is encoded as knowledge graph embeddings through a combination of novel representations: entailment vectors, entailment weights, and a consistency vector. We illustrate our approach on classification tasks of supervised learning. Key contributions of the study include: (i) an effective knowledge graph embedding approach for stream ontologies, and (ii) a generic consistent prediction framework with integrated knowledge graph embeddings for dealing with concept drifts. The experiments have shown that our approach provides accurate predictions towards air quality in Beijing and bus delay in Dublin with real world ontology streams. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Ontology knowledge graph embedding Stream learning Concept drift

来源：评论

学校读者我要写书评

暂无评论

The DLCC Node Classification Benchmark for Analyzing knowledge graph embeddings 21st

The DLCC Node Classification Benchmark for Analyzing Knowled...

引用

21st International Semantic Web Conference (ISWC)

作者： Portisch, Jan Paulheim, Heiko SAP SE Walldorf Germany Univ Mannheim Data & Web Sci Grp Mannheim Germany

ISBN: (纸本)9783031194320;9783031194337

knowledge graph embedding is a representation learning technique that projects entities and relations in a knowledge graph to continuous vector spaces. embeddings have gained a lot of uptake and have been heavily used in link prediction and other downstream prediction tasks. Most approaches are evaluated on a single task or a single group of tasks to determine their overall performance. The evaluation is then assessed in terms of how well the embedding approach performs on the task at hand. Still, it is hardly evaluated (and often not even deeply understood) what information the embedding approaches are actually learning to represent. To fill this gap, we present the DLCC (Description Logic Class Constructors) benchmark, a resource to analyze embedding approaches in terms of which kinds of classes they can represent. Two gold standards are presented, one based on the real-world knowledge graph DBpedia and one synthetic gold standard. In addition, an evaluation framework is provided that implements an experiment protocol so that researchers can directly use the gold standard. To demonstrate the use of DLCC, we compare multiple embedding approaches using the gold standards. We find that many DL constructors on DBpedia are actually learned by recognizing different correlated patterns rather than those defined in the gold standard;we further find that specific DL constructors, such as cardinality constraints, are particularly hard to be learned for most embedding approaches.

关键词： knowledge graph embedding Node classification Description logics Benchmark Evaluation framework

来源：评论

学校读者我要写书评

暂无评论

Demographic Aware Probabilistic Medical knowledge graph embeddings of Electronic Medical Records 19th

Demographic Aware Probabilistic Medical Knowledge Graph Embe...

引用

19th International Conference on Artificial Intelligence in Medicine (AIME)

作者： Guluzade, Aynur Kacupaj, Endri Maleshkova, Maria Univ Bonn Bonn Germany

ISBN: (纸本)9783030772109;9783030772116

Medical knowledge graphs (KGs) constructed from Electronic Medical Records (EMR) contain abundant information about patients and medical entities. The utilization of KG embedding models on these data has proven to be efficient for different medical tasks. However, existing models do not properly incorporate patient demographics and most of them ignore the probabilistic features of the medical KG. In this paper, we propose DARLING (Demographic Aware pRobabiListic medIcal knowledge embedding), a demographic-aware medical KG embedding framework that explicitly incorporates demographics in the medical entities space by associating patient demographics with a corresponding hyperplane. Our framework leverages the probabilistic features within the medical entities for learning their representations through demographic guidance. We evaluate DARLING through link prediction for treatments and medicines, on a medical KG constructed from EMR data, and illustrate its superior performance compared to existing KG embedding models.

关键词： Demographics Probabilistic medical knowledge graph knowledge graph embedding Electronic medical records

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：