检索结果-内蒙古大学图书馆

knowledge graph representation learning with simplifying hierarchical feature propagation

INFORMATION PROCESSING & MANAGEMENT 2023年第4期60卷

作者： Li, Zhifei Zhang, Qi Zhu, Fangfang Li, Duantengchuan Zheng, Chao Zhang, Yan Hubei Univ Sch Comp Sci & Informat Engn Wuhan 430062 Hubei Peoples R China Cent China Normal Univ Sch Informat Management Wuhan 430072 Hubei Peoples R China Cent China Normal Univ Fac Artificial Intelligence Educ Wuhan 430079 Hubei Peoples R China Wuhan Univ Sch Comp Sci Wuhan 430072 Hubei Peoples R China

graph neural networks (GNN) have emerged as a new state-of-the-art for learning knowledge graph representations. Although they have shown impressive performance in recent studies, how to efficiently and effectively aggregate neighboring features is not well designed. To tackle this challenge, we propose the simplifying heterogeneous graph neural network (SHGNet), a generic framework that discards the two standard operations in GNN, including the transformation matrix and nonlinear activation. SHGNet, in particular, adopts only the essential component of neighborhood aggregation in GNN and incorporates relation features into feature propaga-tion. Furthermore, to capture complex structures, SHGNet utilizes a hierarchical aggregation architecture, including node aggregation and relation weighting. Thus, the proposed model can treat each relation differently and selectively aggregate informative features. SHGNet has been evaluated for link prediction tasks on three real-world benchmark datasets. The experimental results show that SHGNet significantly promotes efficiency while maintaining superior performance, outperforming all the existing models in 3 out of 4 metrics on NELL-995 and in 4 out of 4 metrics on FB15k-237 dataset.

关键词： knowledge graphs Representation learning knowledge graph embedding Link prediction

来源：评论

学校读者我要写书评

暂无评论

A Novel Encoder-Decoder knowledge graph Completion Model for Robot Brain

引用

FRONTIERS IN NEUROROBOTICS 2021年 15卷 674428页

作者： Song, Yichen Li, Aiping Tu, Hongkui Chen, Kai Li, Chenchen Natl Univ Def Technol Coll Comp Changsha Peoples R China

With the rapid development of artificial intelligence, Cybernetics, and other High-tech subject technology, robots have been made and used in increasing fields. And studies on robots have attracted growing research interests from different communities. The knowledge graph can act as the brain of a robot and provide intelligence, to support the interaction between the robot and the human beings. Although the large-scale knowledge graphs contain a large amount of information, they are still incomplete compared with real-world knowledge. Most existing methods for knowledge graph completion focus on entity representation learning. However, the importance of relation representation learning is ignored, as well as the cross-interaction between entities and relations. In this paper, we propose an encoder-decoder model which embeds the interaction between entities and relations, and adds a gate mechanism to control the attention mechanism. Experimental results show that our method achieves better link prediction performance than state-of-the-art embedding models on two benchmark datasets, WN18RR and FB15k-237.

关键词： learning-based artificial intelligence robot intelligence human-robot interaction knowledge graph reasoning and completion knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

TAGAT: Type-Aware graph Attention neTworks for reasoning over knowledge graphs

引用

knowledge-BASED SYSTEMS 2021年 233卷 107500-107500页

作者： Wang, Yuzhuo Wang, Hongzhi He, Junwei Lu, Wenbo Gao, Shuolin Harbin Inst Technol Harbin Peoples R China Peng Cheng Lab Shenzhen Peoples R China

With the rapid development of knowledge graphs (KGs), various AI-related applications have been affected positively. However, even though some KGs are relatively large, they still suffer from incompleteness. This has mighty promoted the development of reasoning over KGs to complement them. However, most existing reasoning methods only focus on semantics in the KG, ignoring potential or valuable information hidden in it, the most typical ones are neighborhood information and type information. This limits not only the reasoning performance but also the interpretability of the embedding space. To this end, we propose a Type-Aware graph Attention neTworks (TAGAT) for the reasoning task over KGs. Except for combining type-related information during the embedding process, TAGAT further adopts a hierarchical attention mechanism to realize the perception of type and neighborhood information meticulously. For each entity, different attention levels respectively focus on considering the contribution of different relations, different types under each relation and different entity of each type under each relation. Moreover, the embedding space of TAGAT is constrained by the type information and naturally has better type-related interpretability, which greatly complements the defects of existing KGC models. Extensive experiments validate the high reasoning performance and the relatively ideal interpretability of our model. (c) 2021 Elsevier B.V. All rights reserved.

关键词： knowledge reasoning knowledge graph embedding Type-aware graph attention network Hierarchical attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Zero-shot text classification with knowledge resources under label-fully-unseen setting

引用

NEUROCOMPUTING 2024年 610卷

作者： Wang, Yuqi Wang, Wei Chen, Qi Huang, Kaizhu Nguyen, Anh De, Suparna Xian Jiaotong Liverpool Univ Sch Adv Technol 111 Renai Rd Suzhou 215123 Jiangsu Peoples R China Xian Jiaotong Liverpool Univ Sch AI & Adv Comp 111 Renai Rd Suzhou 215123 Jiangsu Peoples R China Duke Kunshan Univ Data Sci Res Ctr 8 Duke Ave Kunshan 215316 Jiangsu Peoples R China Univ Liverpool Dept Comp Sci Liverpool L69 3BX England Univ Surrey Dept Comp Sci Guildford GU2 7XH Surrey England

Classification techniques are at the heart of many real-world applications, e.g. sentiment analysis, recommender systems and automatic text annotation, to process and analyse large-scale textual data in multiple fields. However, the effectiveness of natural language processing models can only be confirmed when a large amount of up-to-date training data is available. An unprecedented amount of data is continuously created, and new topics are introduced, making it less likely or even infeasible to collect labelled samples covering all topics for training models. We attempt to study the extreme case: there is no labelled data for model training, and the model, without being adapted to any specific dataset, will be directly applied to the testing samples. We propose a transformer-based framework to encode sentences in a contextualised way and leverage the existing knowledge resources, i.e. ConceptNet and WordNet, to integrate both descriptive and structural knowledge for better performance. To enhance the robustness of the model, we design an adversarial example generator based on relations from external knowledge bases. The framework is evaluated on both general and specific domain text classification datasets. Results show that the proposed framework can outperform the existing competitive state-of-the-art baselines, delivering new benchmark results.

关键词： Zero-shot learning knowledge graph embedding Natural language processing Textual analysis Multi-class classification

来源：评论

学校读者我要写书评

暂无评论

An attention-based representation learning model for multiple relational knowledge graph

引用

EXPERT SYSTEMS 2023年第6期40卷 e13234-e13234页

作者： Han, Zhongming Chen, Fuyu Zhang, Hui Yang, Zhiyu Liu, Wenwen Shen, Zequan Xiong, Haitao Beijing Technol & Business Univ Sch Int Econ & Management Beijing Peoples R China Beijing Technol & Business Univ Coll Comp Sci & Engn Beijing Peoples R China Bohai Bank Co Ltd Beijing Branch Informat Management Dept Beijing Peoples R China Beijing Sport Univ Sch Phys Engn Beijing Peoples R China

knowledge graph embedding models are used to learn low-dimensional representations of entities and relations in knowledge graphs. In this paper, we propose Multi-RAttE, an attention-based learning method for multiple relational knowledge graph embedding representation, which divides the information transfer in the knowledge graph into cross-relational information transfer and relation-specific information transfer, and divides the embedding of knowledge graph entities into structural embedding and multi-relational embedding for joint learning. To objectively analyse the performance of the Multi-RAttE model, we select two typical datasets and different representative baseline models for experimental evaluation on several tasks such as link prediction, multi-relation prediction and node classification. The experimental results show that the Multi-RAttE model improves 8% over the state-of-the-art model Composition-based Multi-Relational graph Convolutional Networks (CompGCN) in terms of Hits@1 metric on the link prediction task on FB15k-237 dataset;on the multi-relation prediction task, the accuracy improves by 1.8% and 3.7% in the auc metric and F1 metric, respectively. The experimental results have proved that the Multi-RAttE model can effectively perform the representation of multiple relations.

关键词： attention GNN knowledge graph embedding representation learning

来源：评论

学校读者我要写书评

暂无评论

Relation-oriented few-shot knowledge graph prototype networks

引用

NEUROCOMPUTING 2024年 575卷

作者： Xue, Yingying Song, Aibo Jin, Jiahui Peng, Hui Qiu, Jingyi Fang, Xiaolin Zhai, Xiaorui Southeast Univ Dept Comp Sci & Engn Nanjing Jiangsu Peoples R China Southeast Univ Key Lab Comp Network & Informat Integrat Minist Educ Nanjing Peoples R China NARI Grp Nanjing Jiangsu Peoples R China State Grid Elect Power Res Inst Nanjing Jiangsu Peoples R China

knowledge graph (KG) embedding has been widely researched, but it suffers from some problems in the few -shot scenarios. The topological and semantic connection among entities cannot satisfy the assumption of samples' independent identically distribution. Additionally, these relations between entity pairs are various and complex. But most of the previous methods are node -oriented, which is weak in modeling complex relations. In order to solve the above problems, we propose a few -shot relation prototype network (FRPN). In our method, each relation is regarded as a learning object, instead of just entity pairs' concatenation. A relation -oriented two -channel embedding mechanism is designed to achieve multi -scale information aggregation at the entity level and the relation level respectively. For the entity level, it aggregates information at different scales according to the relation type and the neighbors under each relation. For the relation level, our model obtains each kind of relation's prototype from the ontology and the entity layer. The multi -scale aggregation contributes to KG embedding in the few -shot scenario. Compared with existing models, our model has significantly improved the performance on both the link prediction and triple classification tasks in two few -shot datasets.

关键词： knowledge graph embedding Ontology Prototype network Relation-oriented

来源：评论

学校读者我要写书评

暂无评论

TAP with ease: a generic recommendation system for trigger-action programming based on multi-modal representation learning

引用

APPLIED SOFT COMPUTING 2024年 166卷

作者： Wu, Gang Wang, Ming Wang, Feng Jilin Univ Coll Comp Sci & Technol Changchun 130012 Jilin Peoples R China

The escalating popularity of smart devices has given rise to an increasing trend wherein users leverage customized trigger-action programming (TAP) rules within the Internet of Things (IoT) to automate various aspects of their lives. This article addresses the challenge of effectively combining functions provided by many smart devices and online services by introducing a novel multi-modal representation learning model called TAP-TAG. This model integrates both textual and graph structures inherent in TAP rules, offering a holistic method to rule recommendation. TAP-TAG comprises two branches: the knowledge graph embedding model, which projects triplets extracted from the TAP dataset into embeddings, and convolution neural networks that extract semantic features from the textual content of TAP rules. Extensive experiments are conducted on real- world TAP datasets to evaluate our model's ability to recommend relevant rules based on user preferences. The experimental results show that TAP-TAG can outperform the state-of-the-art method by 5% in Precision@5, indicating that TAP-TAG is highly effective in providing accurate and diverse recommendations for TAP rules.

关键词： Trigger-action programming knowledge graph embedding Natural language processing Multi-modal representation learning

来源：评论

学校读者我要写书评

暂无评论

knowledge-enhanced attentive learning for answer selection in community question answering systems

引用

knowledge-BASED SYSTEMS 2022年第0期250卷

作者： Jing, Fengshi Ren, Hao Cheng, Weibin Wang, Xin Zhang, Qingpeng Guangdong Second Prov Gen Hosp Inst Healthcare Artificial Intelligence Guangzhou 510317 Peoples R China City Univ Hong Kong Sch Data Sci Hong Kong Peoples R China Univ North Carolina Chapel Hill Sch Med UNC Project China UNC Global China NC USA Tianjin Univ Coll Intelligence & Comp Sch Artificial Intelligence Tianjin Peoples R China Tianjin Key Lab Cognit Comp & Applicat Tianjin Peoples R China

In a community question-answering (CQA) system, the answer selection task is used to identify the best answer for a specific question. This plays a key role in improving service quality by recommending appropriate answers to new questions. Recent advances in CQA answer selection have focused on enhancing performance by incorporating community information, and particularly the expertise (previous answers) and authority (position in the social network) of a respondent. However, existing approaches to incorporating this information are limited, as they (a) consider either the expertise or the authority, but not both;(b) ignore domain knowledge that could differentiate between the topics of previous answers;or (c) simply use authority information to adjust the similarity score, rather than fully integrating it into the process of measuring the similarity between the question and answer segments. We propose a new approach called the knowledge-enhanced attentive answer selection (KAAS) model, which enhances performance by (a) considering both the expertise and the authority of the answerer;(b) utilizing human-labeled tags, a taxonomy of tags, and votes as domain knowledge to infer the expertise of the respondent;(c) using a matrix decomposition of the social network (based on 'following' relationships) to infer the authority of the respondent and incorporating this information into the process of evaluating the similarity between segments. In addition, we incorporate an external knowledge graph to capture more professional information for CQA systems for vertical communities. We also adopt an attention mechanism to integrate our analysis of both questions and answers texts and the aforementioned community information. Experiments with both vertical and general CQA sites demonstrate the superior performance of the proposed KAAS model. (c) 2022 Elsevier B.V. All rights reserved.

关键词： knowledge discovery Answer selection Recommender systems Community question answering knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

RDF-star2Vec: RDF-star graph embeddings for Data Mining

引用

IEEE ACCESS 2023年 11卷 142030-142042页

作者： Egami, Shusaku Ugai, Takanori Oota, Masateru Matsushita, Kyoumoto Kawamura, Takahiro Kozaki, Kouji Fukuda, Ken Natl Inst Adv Ind Sci & Technol Koto Tokyo 1350064 Japan Fujitsu Ltd Kawasaki Kanagawa 1057123 Japan Natl Agr & Food Res Org Tsukuba Ibaraki 3050856 Japan Osaka Electrocommun Univ Fac Informat & Commun Engn Dept Engn Informat Neyagawa Osaka 5720833 Japan

knowledge graphs (KGs) such as Resource Description Framework (RDF) data represent relationships between various entities through the structure of triples ( $ $ ). knowledge graph embedding (KGE) is crucial in machine... 详细信息

knowledge graphs (KGs) such as Resource Description Framework (RDF) data represent relationships between various entities through the structure of triples ( $ < subject$ , $predicate$ , $object>$ ). knowledge graph embedding (KGE) is crucial in machine learning applications, specifically in node classification and link prediction tasks. KGE remains a vital research topic within the semantic web community. RDF-star introduces the concept of a quoted triple (QT), a specific form of triple employed either as the subject or object within another triple. Moreover, RDF-star permits a QT to act as compositional entities within another QT, thereby enabling the representation of recursive, hyper-relational KGs with nested structures. However, existing KGE models fail to adequately learn the semantics of QTs and entities, primarily because they do not account for RDF-star graphs containing multi-leveled nested QTs and QT-QT relationships. This study introduces RDF-star2Vec, a novel KGE model specifically designed for RDF-star graphs. RDF-star2Vec introduces graph walk techniques that enable probabilistic transitions between a QT and its compositional entities. Feature vectors for QTs, entities, and relations are derived from generated sequences through the structured skip-gram model. Additionally, we provide a dataset and a benchmarking framework for data mining tasks focused on complex RDF-star graphs. Evaluative experiments demonstrated that RDF-star2Vec yielded superior performance compared to recent extensions of RDF2Vec in various tasks including classification, clustering, entity relatedness, and QT similarity.

关键词： Resource description framework Task analysis Benchmark testing Data mining knowledge graphs Semantics knowledge graph embedding RDF2Vec RDF-star hyper-relational knowledge graphs N-ary relation graph walk

来源：评论

学校读者我要写书评

暂无评论

Three birds, one stone: A novel translation based framework for joint entity and relation extraction

引用

knowledge-BASED SYSTEMS 2022年第0期236卷 107677-107677页

作者： Huang, Heyan Shang, Yu-Ming Sun, Xin Wei, Wei Mao, Xianling Beijing Inst Technol Sch Comp Sci & Technol Beijing 100081 Peoples R China Beijing Engn Res Ctr High Volume Language Informa Beijing 100081 Peoples R China Huazhong Univ Sci & Technol Sch Comp Sci Wuhan 430074 Peoples R China

Joint entity and relation extraction is an important task in natural language processing and knowledge graph construction. Existing studies mainly focus on three issues: redundant predictions, overlapping triples and relation connections. However, as far as we know, none of them is able to solve the three problems simultaneously in a unified architecture. To address this issue, in this paper, we propose a novel translation based unified framework. Specifically, the proposed framework contains two components: an entity tagger and a relation extractor. The former is used to recognize all candidate head entities and tail entities respectively. The latter predicts relations for every entity pair dynamically through ranking with translation mechanism. To show the superiority of the proposed framework, we instantiate it through the simplest binary entity tagger and TransE algorithm. Extensive experiments over two widely used datasets demonstrate that, even with the simplest components, the proposed framework can still achieve competitive performance with most previous baselines. Moreover, the framework is flexible. It enjoys further performance boost when employing more powerful entity tagger and knowledge graph embedding algorithm. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Entity and relation extraction Overlapping triples Redundant predictions Relation connections knowledge graph embedding

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：