检索结果-内蒙古大学图书馆

Uncertain knowledge graph embedding Using Auxiliary Information

IEEE ACCESS 2024年 12卷 138351-138361页

作者： Bahaj, Adil Ghogho, Mounir Int Univ Rabat TICLab Rabat 11103 Morocco Univ Leeds Fac Engn Leeds LS2 9JT England

Uncertain knowledge graphs (UKGs) offer a more realistic representation of knowledge by capturing the uncertainty associated with facts. However, existing UKG embedding methods primarily rely on structural information for confidence score prediction, neglecting other sources of uncertainty. This paper investigates the effectiveness of incorporating auxiliary information into UKG embeddings. We propose two approaches: Text-BEUrRE, which leverages textual information, and UCompGCN, which utilizes topological information. Our extensive experiments demonstrate that both methods successfully integrate these auxiliary data sources. Notably, Text-BEUrRE and UCompGCN outperform state-of-the-art baselines on most metrics in the confidence prediction task. On the CN15K dataset, Text-BEUrRE achieves a 7.39% improvement in Mean Squared Error (MSE) compared to the best existing model, while UCompGCN achieves an 8.27% improvement in Mean Absolute Error (MAE).

关键词： Semantics knowledge graphs Task analysis Uncertainty Training Computational modeling Adaptation models Predictive models Uncertain knowledge graphs knowledge graph embedding box embedding confidence prediction

来源：评论

学校读者我要写书评

暂无评论

A probabilistic ensemble approach for knowledge graph embedding

引用

NEUROCOMPUTING 2022年第0期500卷 1041-1051页

作者： Wang, Yinquan Chen, Yao Zhang, Zhe Wang, Tian Chinese Acad Sci Acad Math & Syst Sci Key Lab Syst & Control Beijing Peoples R China Univ Chinese Acad Sci Sch Math Sci Beijing Peoples R China Southwestern Univ Finance & Econ Dept Comp Sci Chengdu Peoples R China Beihang Univ Inst Artificial Intelligence Beijing Peoples R China

knowledge graph embedding (KGE) is a technique for embedding entities and relations of knowledge graphs (KGs) into continuous vector spaces while maintaining the inherent structure of KGs, in this way link prediction can be facilitated by scoring candidate triples. Existing KGE models only capture specific features of a KG, however, link prediction capacity heavily relies on comprehensive features of a KG. In this work, we propose an ensemble approach for KGE by incorporating the features captured by different KGE models. As a key step, we propose a probabilistic scoring index for characterizing the link prediction performance of a given KGE model. Based on this we established a theoretical framework to calculate the optimal parameters for the ensemble model and predict its corresponding link prediction rate. In particular, we proved that our ensemble approach can always improve link prediction performance under some assumptions. The Upper Confidence Bound Algorithm is then used to adjust the parameters. Experimental results on two widely used KGs show that the proposed ensemble approach achieves the state-of-the-art link prediction rate.

关键词： knowledge graph embedding Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Pykg2vec: A Python Library for knowledge graph embedding

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2021年第1期22卷 1-6页

作者： Yu, Shih-Yuan Chhetri, Sujit Rokka Canedo, Arquimedes Goyal, Palash Al Faruque, Mohammad Abdullah Univ Calif Irvine Dept Elect Engn & Comp Sci Irvine CA 92697 USA Siemens Corp Technol Princeton NJ USA Univ Southern Calif Dept Comp Sci Los Angeles CA 90007 USA

Pykg2vec is a Python library for learning the representations of the entities and relations in knowledge graphs. Pykg2vec's flexible and modular software architecture currently implements 25 state-of-the-art knowledge graph embedding algorithms, and is designed to easily incorporate new algorithms. The goal of pykg2vec is to provide a practical and educational platform to accelerate research in knowledge graph representation learning. Pykg2vec is built on top of PyTorch and Python's multiprocessing framework and provides modules for batch generation, Bayesian hyperparameter optimization, evaluation of KGE tasks, embedding, and result visualization. Pykg2vec is released under the MIT License and is also available in the Python Package Index (PyPI). The source code of pykg2vec is available at https://***/Sujit-0/pykg2vec(dagger).

关键词： knowledge graph embedding Representation Learning

来源：评论

学校读者我要写书评

暂无评论

knowledge graph embedding with inverse function representation for link prediction

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年第PartA期127卷

作者： Zhang, Qianjin Xu, Yandan Huzhou Vocat & Tech Coll Huzhou 313000 Peoples R China

knowledge graphs, which contains billions of facts, have become a useful resource for many AI-related downstream tasks, such as knowledge inference, personalized search. However, although existing knowledge graphs contain billions of facts, most knowledge graphs are still incomplete due to the inability to manually access all the facts in the world. In order to automatically predict missing triples, researchers have proposed many knowledge graph embedding models for link prediction task. However, most existing models have flaws in handling symmetric relations, as they will get the same constant |r| = 1 or r = 0 for any symmetric relations. In order to address such flaws, we propose a novel model called InversEF, which can get different representations for symmetric relations by learning inverse function representation of triples. In InversEF, for the complex relations, we explicitly capture the structured information of each entity by using the interaction between entities , relations. Due to the symmetry between the function and its corresponding inverse function, InverseEF can work well on the symmetric and inverse relations. Experimental results show that, InversEF achieves new state-of-the-art performance.

关键词： Inverse function representation knowledge graph embedding Link prediction

来源：评论

学校读者我要写书评

暂无评论

knowledge graph embedding by relational rotation and complex convolution for link prediction

引用

EXPERT SYSTEMS WITH APPLICATIONS 2023年 214卷

作者： Thanh Le Nam Le Bac Le Univ Sci Fac Informat Technol Ho Chi Minh City Vietnam Vietnam Natl Univ Ho Chi Minh City Vietnam

knowledge graphs are organized as triplets to represent facts from the real world and play an important role in various intelligent information systems. Because knowledge graphs are frequently constructed using manual or semi-automatic methods, they often miss connections between entities. Link prediction was created to solve this problem. Many recent state-of-the-art studies, such as those introducing the RotatE and RotatHS models, have advocated for rotation transformations with entity and relation embeddings in complex vector spaces. However, using only rotation planes means that these models do not have the expressive power of models based on neural networks, such as the ConvE and the ConvR models. As a result, link prediction performance suffers. To address these shortcomings, this paper proposes the ConvRot model, which integrates a 2D convolution. Specifically, we perform convolution on embeddings of entities and relations to obtain support vector embeddings. These vectors are then integrated into an element-wise rotation from the head entity to the tail entity using the Hadamard product, enabling the model to capture local interactions among entities and relations through the neural network while still ensuring intuitiveness through a roto-transformation in the link prediction. In addition, we present two strategies for designing the complex convolution module and show their effects on model perfor-mance. The proposed method is evaluated on standard benchmark datasets and achieves significantly improved results on MRR and Hits@K (K = 1, 3, 10). Overall, our model's link prediction performance is superior by approximately 5-7 %. Moreover, the ConvRot model is also considered separately on many relation types, such as one-to-one, one-to-many, many-to-one, and many-to-many. Finally, we prove that type constraints can help increase the model's overall performance, especially on complex and large datasets.

关键词： knowledge graph embedding Link prediction Complex convolution Rotation transformation

来源：评论

学校读者我要写书评

暂无评论

Structural context-based knowledge graph embedding for link prediction

引用

NEUROCOMPUTING 2022年第0期470卷 109-120页

作者： Zhang, Qianjin Wang, Ronggui Yang, Juan Xue, Lixia Hefei Univ Technol Sch Comp & Informat Hefei 230601 Peoples R China

knowledge graph embedding, which aims to address the limitation of symbolic representation of knowledge, has become an effective method for many AI downstream tasks, such as relation extraction, question answering. Existing knowledge graph embedding models mainly consider triples individually, and ignore the structural information connected with other entities. However, the connectivity between entities not only provides explicit structural information represented in triples, but also embodies a lot of implicit structure information. In this paper, a new knowledge graph embedding model is proposed, which can capture both the information of relational structure-context and edge structure-context by two-interaction. In addition, in order to model complex relations, we define different score function for different relation types. Moreover, the four relation connectivity types in knowledge graph (i.e. symmetry/antisymmetry, inversion, and composition) also can be modeled and inferred by StructurE. We evaluate our StructurE for knowledge graph link prediction task. Benefiting from the structural context and the relation-type-specific score function, compared with conventional geometric transformation based knowledge graph embedding models StructurE achieves state-of-the-art results for link prediction. Moreover, compared with GCN-based models StructurE also achieves state-of-the-art results on more challenging dataset WN18RR which contains more symmetric relations. (c) 2021 Elsevier B.V. All rights reserved.

关键词： knowledge graph embedding Link prediction Relational structure-context Edge structure-context

来源：评论

学校读者我要写书评

暂无评论

knowledge graph embedding: A Locally and Temporally Adaptive Translation-Based Approach

引用

ACM TRANSACTIONS ON THE WEB 2018年第2期12卷 8-8页

作者： Jia, Yantao Wang, Yuanzhuo Jin, Xiaolong Lin, Hailun Cheng, Xueqi Chinese Acad Sci Inst Comp Technol CAS Key Lab Network Data Sci & Technol Beijing 100190 Peoples R China Chinese Acad Sci Inst Informat Engn Beijing 100193 Peoples R China

A knowledge graph is a graph with entities of different types as nodes and various relations among them as edges. The construction of knowledge graphs in the past decades facilitates many applications, such as link prediction, web search analysis, question answering, and so on. knowledge graph embedding aims to represent entities and relations in a large-scale knowledge graph as elements in a continuous vector space. Existing methods, for example, TransE, TransH, and TransR, learn the embedding representation by defining a global margin-based loss function over the data. However, the loss function is determined during experiments whose parameters are examined among a closed set of candidates. Moreover, embeddings over two knowledge graphs with different entities and relations share the same set of candidates, ignoring the locality of both graphs. This leads to the limited performance of embedding related applications. In this article, a locally adaptive translation method for knowledge graph embedding, called TransA, is proposed to find the loss function by adaptively determining its margin over different knowledge graphs. Then the convergence of TransA is verified from the aspect of its uniform stability. To make the embedding methods up-to-date when new vertices and edges are added into the knowledge graph, the incremental algorithm for TransA, called iTransA, is proposed by adaptively adjusting the optimal margin over time. Experiments on four benchmark data sets demonstrate the superiority of the proposed method, as compared to the state-of-the-art ones.

关键词： Locally and temporally adaptive translation knowledge graph embedding optimal margin convergence

来源：评论

学校读者我要写书评

暂无评论

knowledge graph embedding with the special orthogonal group in quaternion space for link prediction

引用

knowledge-BASED SYSTEMS 2023年第1期266卷

作者： Le, Thanh Tran, Huy Le, Bac Univ Sci Fac Informat Technol Ho Chi Minh City Vietnam Vietnam Natl Univ Ho Chi Minh City Vietnam

graph embedding is an important technique for improving the quality of link prediction models on knowledge graphs. Although embedding based on neural networks can capture latent features with high expressive power, geometric embedding has other advantages, such as intuitiveness, interpretability, and few parameters. Several recent works have used rotation in quaternion space to enhance performance, yet these rotations have been limited to 3D representations. This paper proposes Rotate4D, a novel model that performs 4D rotations in quaternion space using a special orthogonal group. Specifically, Rotate4D begins by embedding entities in quaternion space, then rotates the head embedding to the tail embedding in two different ways (isoclinic and double rotation). The group structure helps decompose the relation into unit vectors to perform 4D rotations in quaternion space. In addition, quaternion scaling is applied to solve hierarchical relations. With this approach, the proposed model improved link prediction performance compared with state-of-the-art models on standard datasets, especially for the Hits@1 metric (an improvement of 2.72% to 3.49%). In addition to these experiments, we also theoretically prove that Rotate4D can model all relational patterns, including symmetry, anti-symmetry, inversion, and composition.(c) 2023 Elsevier B.V. All rights reserved.

关键词： knowledge graph knowledge graph embedding Link prediction Quaternion Special orthogonal group

来源：评论

学校读者我要写书评

暂无评论

knowledge graph embedding model with attention-based high-low level features interaction convolutional network

引用

INFORMATION PROCESSING & MANAGEMENT 2023年第4期60卷

作者： Wang, Jingxiong Zhang, Qi Shi, Fobo Li, Duantengchuan Cai, Yuefeng Wang, Jian Li, Bing Wang, Xiaoguang Zhang, Zhen Zheng, Chao Wuhan Univ Sch Comp Sci Wuhan Peoples R China Cent China Normal Univ Sch Informat Management Wuhan Peoples R China Cent China Normal Univ Natl Engn Res Ctr E Learning Wuhan Peoples R China ZTE Corp Wuhan 430223 Peoples R China Wuhan Univ Sch Informat Management Wuhan Peoples R China Wuhan Sports Univ Sch Sports Engn & Informat Technol Wuhan Peoples R China

knowledge graphs are sizeable graph-structured knowledge with both abstract and concrete concepts in the form of entities and relations. Recently, convolutional neural networks have achieved outstanding results for more expressive representations of knowledge graphs. However, existing deep learning-based models exploit semantic information from single-level feature interaction, potentially limiting expressiveness. We propose a knowledge graph embedding model with an attention-based high-low level features interaction convolutional network called ConvHLE to alleviate this issue. This model effectively harvests richer semantic information and generates more expressive representations. Concretely, the multilayer convolutional neural network is utilized to fuse high-low level features. Then, features in fused feature maps interact with other informative neighbors through the criss-cross attention mechanism, which expands the receptive fields and boosts the quality of interactions. Finally, a plausibility score function is proposed for the evaluation of our model. The performance of ConvHLE is experimentally investigated on six benchmark datasets with individual characteristics. Extensive experimental results prove that ConvHLE learns more expressive and discriminative feature representations and has outperformed other state-of-the-art baselines over most metrics when addressing link prediction tasks. Comparing MRR and Hits@1 on FB15K-237, our model outperforms the baseline ConvE by 13.5% and 16.0%, respectively.

关键词： Link prediction knowledge graph embedding Convolutional neural network Criss-cross attention mechanism High-low level features interaction

来源：评论

学校读者我要写书评

暂无评论

knowledge graph embedding by reflection transformation

引用

knowledge-BASED SYSTEMS 2022年 238卷 1页

作者： Zhang, Qianjin Wang, Ronggui Yang, Juan Xue, Lixia Hefei Univ Technol Sch Comp & Informat Hefei 230601 Peoples R China

Due to the incompleteness of knowledge graph, knowledge graph embedding(KGE) has become a key technique for automatically predict missing facts in knowledge graph. KGE aims to learn low dimensional representations for both relations and entities. Despite existing KGE models achieved state-of-the-art(SOTA) performances, modeling and inferring relation connectivity(such as symmetry/antisymmetry, inversion, and composition), as well as complex relations prediction(such as M-to-1, 1-to-M and M-to-M) still have great challenges. In this paper, we propose a new KGE model called ReflectE, which regards each relation as a normal vector of a relation-specific reflection hyperplane. Specifically, ReflectE regards the tail entity(or head entity) in a triple as the reflection of the head entity(or tail entity) on a relation-specific hyperplane. Therefore it can model symmetric and inverse relations by reflection transformation naturally. Furthermore, ReflectE models complex relations by learning a relation-specific dynamic reflection hyperplane. In order to evaluate the effectiveness of our proposed model ReflectE, we choose previous SOTA models as baselines and conduct link prediction task on three popular datasets. Experimental results show that, compared with conventional distance-based KGE models, ReflectE achieves SOTA results for link prediction.(c) 2021 Elsevier B.V. All rights reserved.

关键词： knowledge graph embedding Reflection transformation 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：