检索结果-内蒙古大学图书馆

Translational relation embeddings for multi-hop knowledge base question answering

JOURNAL OF WEB SEMANTICS 2022年第0期74卷

作者： Li, Ziyan Wang, Haofen Zhang, Wenqiang Fudan Univ Acad Engn & Technol Shanghai Peoples R China Tongji Univ Coll Design & Innovat Shanghai Peoples R China

Multi-hop knowledge Base Question Answering (KBQA) aims to predict answers that require multi-hop reasoning from the topic entity in the question over the knowledge Base (KB). Relation extraction is a core step in KBQA, which extracts the relation path from the topic entity to the answer entity. Compared with single-hop questions, multi-hop ones have more complex syntactic structures to understand, and multi-hop relation paths lead to a larger search space, which makes it much more challenging to extract the correct relation paths. To tackle the above challenges, most existing relation extraction approaches focus on the semantic similarity between questions and relation paths. However, those approaches only consider the word semantics of the relation names but ignore the graph semantics inside the knowledge base. As a result, their generalization ability relying on the naming rules of the relations, making it more difficult to generalize over large knowledge bases. To address the current limitations and take advantage of the graph semantics of relations, we propose a novel translational embedding-based relation extractor that utilizes pretrained embeddings from TransE. In particular, we treat the multi-hop relation path as a translation from the first relation to the last one in the semantic space of TransE. Then we map the question into this space under the supervision of the path embeddings. To take full advantage of the pretrained graph semantics in TransE, we propose a KBQA framework that leverages pretrained relation semantics in relation extraction and pretrained entity semantics in answer selection. Our approach achieves state-of-the-art performance on two benchmark datasets, WebQuestionSP and MetaQA, demonstrating its effectiveness on the multi-hop KBQA task. (C) 2022 Elsevier B.V. All rights reserved.

关键词： knowledge base question answering knowledge graph embedding Multi-hop relation extraction

来源：评论

学校读者我要写书评

暂无评论

Multi-perspective knowledge graph completion with global and interaction features

引用

INFORMATION SCIENCES 2024年 666卷

作者： Li, Duantengchuan Shi, Fobo Wang, Xiaoguang Zheng, Chao Cai, Yuefeng Li, Bing Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China Cent China Normal Univ Natl Engn Res Ctr Elearning Wuhan 430079 Peoples R China Wuhan Univ Sch Informat Management Wuhan 430072 Peoples R China ZTE Corp Shenzhen 518057 Peoples R China Hubei Luojia Lab Wuhan 430079 Peoples R China

knowledge graphs are multi -relation heterogeneous graphs. Thus, the existence of numerous multi -relation entities imposes a tough challenge to the modelling of the knowledge graph. Some recent works represent the property of corresponding entities and relations by generating embeddings. They attempted to identify the missing entities by translation operations or semantic matching. However, the expressiveness of these approaches depends on the entity (relations) embedding. The heterogeneity of entities leads to the difficulty of balancing uniform embedding dimension settings on complex and sparse relational entities, as high -dimensional embedding leads to the overfitting of sparse relational entities, and low -dimensional embedding leads to the underfitting of complex relational entities. We introduce a multi -perspective knowledge graph embedding model with global and interaction features (MGIF) to alleviate these issues. This achieved knowledge transfer from complex relational entities to sparse relational entities through the multi -view features. In particular, to overcome the local limitations of convolution neural networks, the global features shared between entities (relations) and entities (relations) are incorporated in the MGIF. The performance of MGIF is experimentally evaluated on several datasets. The experimental effects demonstrate that MGIF can efficiently model complicated entities and accomplish state-of-the-art complex relationship prediction results on most evaluation metrics.

关键词： knowledge graph embedding Global feature Link prediction Complex relations Convolutional network Interaction feature

来源：评论

学校读者我要写书评

暂无评论

Causality-aware Enhanced Model for Multi-hop Question Answering over knowledge graphs

引用

knowledge-BASED SYSTEMS 2022年 250卷

作者： Sui, Yuan Feng, Shanshan Zhang, Huaxiang Cao, Jian Hu, Liang Zhu, Nengjun Shandong Normal Univ Sch Informat Sci & Engn Jinan Peoples R China Shandong JiaoTong Univ Jinan Peoples R China Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai Peoples R China Tongji Univ DeepBlue Acad Sci Sch Elect & Informat Engn Shanghai Peoples R China DeepBlue Acad Sci Shanghai Peoples R China Shanghai Univ Sch Comp Engn & Sci Shanghai Peoples R China

To improve the performance of knowledge graph-based question answering system (KGQA), several approaches have been developed to construct a semantic parser based on entity linking, relation identification and logical/numerical structure identification. However, existing methods arrive at answers only by maximizing the data likelihood only on the sparse or imbalanced explicit relations, ignoring the potentially large number of latent relations. It makes KGQA suffer from a high level of spurious entity relations and missing link challenge. In this paper, we propose a causal filter (CF) model for KGQA (CF-KGQA), which performs causal interference on the relation representation space to reduce the spurious relation representation in a data-driven manner, i.e., the goal of this work is to comprehensively discover disentangled latent factors to alleviate the spurious correlation problem in KGQA. The model comprises a causal pairwise aggregator (A(P)) and a disentangled latent factor aggregator (A(C)). The former filters out most spurious entity relations inconsistent to their dense groups' neighborhood, and generates a causal pairwise matrix among all the candidate relations. The latter learns the latent relation representation via an encoder-decoder on the causal pairwise matrix. It disconnects the latent factor and the causal confounder beneath the knowledge embedding space by causal intervention. To prove the effectiveness and efficiency of the proposed approach, we test CFKGQA and other state-of-the-art methods on four public real-world datasets. The experiments indicate that our approach outperforms the recent methods and is also less sensitive to the spurious correlation problem, thus demonstrating the robustness of CF-KGQA. (C) 2022 Published by Elsevier B.V.

关键词： knowledge graph-based question answering Causal representation learning Constraint pairwise-based clustering knowledge graph embedding Confounding bias

来源：评论

学校读者我要写书评

暂无评论

Relagraph: Improving embedding on small-scale sparse knowledge graphs by neighborhood relations

引用

INFORMATION PROCESSING & MANAGEMENT 2023年第5期60卷

作者： Shi, Bin Wang, Hao Li, Yueyan Deng, Sanhong Nanjing Univ Sch Informat Management Nanjing 210023 Peoples R China Jiangsu Key Lab Data Engn & Knowledge Serv Nanjing 210023 Peoples R China

Learning a continuous dense low-dimensional representation of knowledge graphs (KGs), known as knowledge graph embedding (KGE), has been viewed as the key to intelligent reasoning for deep learning (DL) and gained much attention in recent years. To address the problem that the current KGE models are generally ineffective on small-scale sparse datasets, we propose a novel method Relagraph to improve the representation of entities and relations in KGs by introducing neighborhood relations. Relagraph extends the neighborhood information during entity encoding, and adds the neighborhood relations to mine deeper level of graph structure information, so as to make up for the shortage of information in the generated subgraph. This method can well represent KG components in a vector space in a way that captures the structure of the graph, avoiding underlearning or overfitting. KGE based on Relagraph is evaluated on a small-scale sparse graph KMHEO, and the MRR reached 0.49, which is 34 percentage points higher than that of the SOTA methods, as well as it does on several other datasets. Additionally, the vectors learned by Relagraph is used to introduce DL into several KG-related downstream tasks, which achieved excellent results, verifying the superiority of KGE-based methods.

关键词： knowledge graph knowledge graph embedding Deep learning Stargraph

来源：评论

学校读者我要写书评

暂无评论

An radicals construction technique based on dual quaternions and hierarchical transformers

引用

NEUROCOMPUTING 2024年 604卷

作者： Zhang, Sensen Liang, Xun Renmin Univ China Sch Informat Beijing 100872 Peoples R China

At present, the exploration of knowledge graph embedding (KGE) mainly focuses on static KGE models. Due to the diversity and complexity of vertical domain data, it is difficult for existing KGE models to achieve excellent performance. Specific KGE models must be constructed for research on vertical domain knowledge graphs. This paper explores the relationships between the composition of Chinese characters and their sounds, meanings, and forms by constructing the Chinese Radical knowledge graph (CRKG). CRKG was constructed from a unique perspective according to the characteristics of Chinese radicals and knowledge graphs. The minor components of Chinese characters are separated and constructed into the fourth dimension of the knowledge graph. In this paper, we propose a new Chinese Radical knowledge graph embedding (CRKGE) model, RotAL, which introduces dual quaternions and hierarchical transformers into KGE. RotAL performs a translation-rotation operation on the head entity with the relation as a parameter, then does a translation operation on the head entity with the minor component as a parameter to be close to the tail entity. Finally, we feed the trained quaternions into hierarchical transformers to jointly learn entity-related composition and relational contextualization based on a head entity's neighborhood. We demonstrate that our method can model and infer various relational patterns of CRKG, such as symmetric/antisymmetric, reflexive, inversion, and multiple. The experimental results on four CRKG datasets demonstrate that the RotAL model achieves the highest Hit@1 score, outperforming existing KGE models in accurately identifying the target entity on the first attempt. Furthermore, the RotAL model consistently achieves superior performance across other evaluation metrics, substantiating its significant advantage over existing models.

关键词： knowledge graph embedding Chinese radical knowledge graph Quaternions Hierarchical transformers

来源：评论

学校读者我要写书评

暂无评论

Hic-KGQA: Improving multi-hop question answering over knowledge graph via hypergraph and inference chain

引用

knowledge-BASED SYSTEMS 2023年第1期277卷

作者： Wang, Jingchao Li, Weimin Liu, Fangfang Sheng, Bin Liu, Wei Jin, Qun Shanghai Univ Sch Comp Engn & Sci Shanghai 200000 Peoples R China Waseda Univ Fac Human Sci Tokorozawa 3591192 Japan

Question answering over knowledge graph (KGQA) aims at answering natural language questions posed over knowledge graphs (KGs). Moreover, multi-hop KGQA requires reasoning across multiple triplets in KGs to get to the answer. Unfortunately, KGs often lack complete information and contain many missing links, which poses huge challenges for multi-hop KGQA. To address this, recent several approaches have introduced KG embedding techniques, which have shown good performance on the multi-hop KGQA task. However, these methods ignore the semantic correlations between paths and questions, and the reasoning process is not easily explained. Furthermore, traditional KG embedding methods consider only low-order pairwise relations and ignore the higher-order relations among entities, leading to a sub-optimal embedding result. To address these problems, we propose Hic-KGQA, a novel hypergraph and inference chain-based model for multi-hop KGQA. Specifically, Hic-KGQA first generates pre-trained entity embeddings with multiple semantics via a hypergraph-based KGC module (HKM). Then, an inference chain modeling module (ICMM) is designed to learn the importance of different inference chains for the question and encode the highest-ranked inference chain into an embedding representation. Finally, two scoring networks are used to evaluate the correlation between the candidate answers and the questions from the perspective of both the triplet facts and the reasoning process to obtain more accurate answers. Furthermore, the mutual information maximization (MIM) is innovatively implemented to capture richer common path features from similar cases to alleviate the missing path problem caused by KG incompleteness. Experiments show that Hic-KGQA significantly outperforms existing state-of-the-art methods and is explainable. & COPY;2023 Published by Elsevier B.V.

关键词： Question answering over knowledge graph knowledge graph embedding Hypergraph Mutual information

来源：评论

学校读者我要写书评

暂无评论

Towards assessing the quality of knowledge graphs via differential testing

引用

INFORMATION AND SOFTWARE TECHNOLOGY 2024年 174卷

作者： Tan, Jiajun Wang, Dong Sun, Jingyu Liu, Zixi Li, Xiaoruo Feng, Yang Nanjing Univ Nanjing Peoples R China Henan Univ Kaifeng Henan Peoples R China

knowledge graphs (KG) can aggregate data and make information resources easier to calculate and understand. With tremendous advancements in knowledge graphs, they have been incorporated into plenty of software systems to assist various tasks. However, while KGs determine the performance of downstream software systems, their quality is often measured by the accuracy of test data. Considering the limitation of accessible high-quality test data, an automated quality assessment technique could fundamentally improve the testing efficiency of KG-driven software systems and save plenty of manual labeling resources. In this paper, we propose an automated approach to quantify the quality of KGs via differential testing. It first constructs multiple knowledge graph embedding Models (KGEM) and conducts head prediction tasks on models. Then, it can produce a differential score that reflects the quality of KGs by comparing the proximity of output results. To validate the effectiveness of this approach, we experiment with four open-sourced knowledge graphs. The experiment results show that our approach is capable of accurately evaluating the quality of KGs and producing reliable results on different datasets. Moreover, we compared our method with existing methods and achieved certain advantages. The potential usefulness of our approach sheds light on the development of various KG-driven software systems.

关键词： knowledge graph embedding Differential testing Quality evaluation

来源：评论

学校读者我要写书评

暂无评论

knowledge graph fact prediction via knowledge-enriched tensor factorization

引用

JOURNAL OF WEB SEMANTICS 2019年 59卷 100497-100497页

作者： Padia, Ankur Kalpakis, Kostantinos Ferraro, Francis Finin, Tim Univ Maryland Baltimore Cty Baltimore MD 21228 USA

We present a family of novel methods for embedding knowledge graphs into real-valued tensors. These tensor-based embeddings capture the ordered relations that are typical in the knowledge graphs represented by semantic web languages like RDF. Unlike many previous models, our methods can easily use prior background knowledge provided by users or extracted automatically from existing knowledge graphs. In addition to providing more robust methods for knowledge graph embedding, we provide a provably-convergent, linear tensor factorization algorithm. We demonstrate the efficacy of our models for the task of predicting new facts across eight different knowledge graphs, achieving between 5% and 50% relative improvement over existing state-of-the-art knowledge graph embedding techniques. Our empirical evaluation shows that all of the tensor decomposition models perform well when the average degree of an entity in a graph is high, with constraint-based models doing better on graphs with a small number of highly similar relations and regularization-based models dominating for graphs with relations of varying degrees of similarity. (C) 2019 Elsevier B.V. All rights reserved.

关键词： knowledge graph knowledge graph embedding Tensor decomposition Tensor factorization Representation learning Fact prediction

来源：评论

学校读者我要写书评

暂无评论

Representation learning for dynamic graphs: a survey

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2020年第1期21卷 2648-2720页

作者： Seyed Mehran Kazemi Rishab Goel Kshitij Jain Ivan Kobyzev Akshay Sethi Peter Forsyth Pascal Poupart Borealis AI Montreal QC Canada Borealis AI Waterloo ON Canada

graphs arise naturally in many real-world applications including social networks, recommender systems, ontologies, biology, and computational finance. Traditionally, machine learning models for graphs have been mostly designed for static graphs. However, many applications involve evolving graphs. This introduces important challenges for learning and inference since nodes, attributes, and edges change over time. In this survey, we review the recent advances in representation learning for dynamic graphs, including dynamic knowledge graphs. We describe existing models from an encoder-decoder perspective, categorize these encoders and decoders based on the techniques they employ, and analyze the approaches in each category. We also review several prominent applications and widely used datasets and highlight directions for future research.

关键词： graph representation learning dynamic graphs knowledge graph embedding heterogeneous information networks

来源：评论

学校读者我要写书评

暂无评论

Decentralized Federated Learning-Enabled Relation Aggregation for Anomaly Detection

引用

INFORMATION 2023年第12期14卷 647-647页

作者： Shuai, Siyue Hu, Zehao Zhang, Bin Liaqat, Hannan Bin Kong, Xiangjie Zhejiang Univ Technol Coll Comp Sci & Technol Hangzhou 310023 Peoples R China Zhejiang Yuexiu Univ Foreign Language Coll Digital Commerce Shaoxing 312000 Peoples R China Univ Educ IT Dept Informat Sci Div Sci & Technol Township Campus Lahore 54000 Pakistan

Anomaly detection plays a crucial role in data security and risk management across various domains, such as financial insurance security, medical image recognition, and Internet of Things (IoT) device management. Researchers rely on machine learning to address potential threats in order to enhance data security. In the financial insurance industry, enterprises tend to leverage the relation mining capabilities of knowledge graph embedding (KGE) for anomaly detection. However, auto insurance fraud labeling strongly relies on manual labeling by experts. The efficiency and cost issues of labeling make auto insurance fraud detection still a small-sample detection challenge. Existing schemes, such as migration learning and data augmentation methods, are susceptible to local characteristics, leading to their poor generalization performance. To improve its generalization, the recently emerging Decentralized Federated Learning (DFL) framework provides new ideas for mining more frauds through the joint cooperation of companies. Based on DFL, we propose a federated framework named DFLR for relation embedding aggregation. This framework trains the private KGE of auto insurance companies on the client locally and dynamically selects servers for relation aggregation with the aim of privacy protection. Finally, we validate the effectiveness of our proposed DFLR on a real auto insurance dataset. And the results show that the cooperative approach provided by DFLR improves the client's ability to detect auto insurance fraud compared to single client training.

关键词： Decentralized Federated Learning knowledge graph embedding anomaly detection relation aggregation

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：