检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

304 篇 期刊文献
261 篇 会议
1 篇 学位论文

馆藏范围

566 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

531 篇 工学
- 510 篇 计算机科学与技术...
- 103 篇 电气工程
- 66 篇 软件工程
- 39 篇 信息与通信工程
- 27 篇 控制科学与工程
- 4 篇 机械工程
- 4 篇 测绘科学与技术
- 3 篇 电子科学与技术（可...
- 3 篇 生物医学工程（可授...
- 3 篇 网络空间安全
- 2 篇 仪器科学与技术
- 2 篇 交通运输工程
51 篇 管理学
- 38 篇 管理科学与工程(可...
- 11 篇 图书情报与档案管...
- 3 篇 公共管理
45 篇 理学
- 18 篇 数学
- 13 篇 生物学
- 8 篇 物理学
- 6 篇 系统科学
- 4 篇 地理学
- 3 篇 化学
- 2 篇 地球物理学
24 篇 医学
- 14 篇 基础医学(可授医学...
- 4 篇 临床医学
- 4 篇 药学(可授医学、理...
- 2 篇 公共卫生与预防医...
6 篇 文学
- 5 篇 外国语言文学
3 篇 法学
- 2 篇 社会学
- 1 篇 法学
3 篇 农学
2 篇 教育学
- 2 篇 教育学

主题

566 篇 knowledge graph ...
142 篇 link prediction
90 篇 knowledge graph
63 篇 knowledge graph ...
34 篇 representation l...
29 篇 knowledge graphs
23 篇 semantics
20 篇 entity alignment
17 篇 task analysis
17 篇 attention mechan...
15 篇 graph neural net...
14 篇 deep learning
14 篇 predictive model...
12 篇 negative samplin...
12 篇 graph neural net...
12 篇 machine learning
12 篇 convolutional ne...
11 篇 computational mo...
10 篇 knowledge engine...
10 篇 recommender syst...

机构

17 篇 chinese acad sci...
12 篇 univ chinese aca...
12 篇 univ chinese aca...
10 篇 univ sci fac inf...
9 篇 wuhan univ sch c...
9 篇 vietnam natl uni...
7 篇 hefei univ techn...
7 篇 southeast univ s...
7 篇 univ mannheim da...
6 篇 zhejiang univ co...
5 篇 zhejiang univ pe...
5 篇 alibaba grp peop...
5 篇 peng cheng lab p...
5 篇 shanghai univ sc...
4 篇 univ queensland ...
4 篇 soochow univ sch...
4 篇 bosch ctr ai ren...
4 篇 beihang univ sch...
4 篇 harbin inst tech...
4 篇 huawei technol c...

作者

11 篇 zhang wen
9 篇 chen huajun
9 篇 jia yantao
8 篇 paulheim heiko
7 篇 cheng xueqi
7 篇 thanh le
7 篇 bac le
7 篇 wang yuanzhuo
7 篇 wang meng
6 篇 li zhifei
6 篇 wang ronggui
6 篇 li guanyu
6 篇 yang juan
6 篇 xue lixia
5 篇 liu jun
5 篇 wang tao
5 篇 zhang wensheng
5 篇 guo xiaobo
5 篇 sun zhengya
5 篇 wang bin

语言

559 篇 英文
7 篇 其他

检索条件"主题词=Knowledge Graph embedding"

共 566 条记录，以下是131-140 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Modeling IsA Relations via Box Structure for knowledge graph embedding 26th

Modeling IsA Relations via Box Structure for Knowledge Graph...

引用

26th Pacific-Asia Conference on knowledge Discovery and Data Mining (PAKDD)

作者： Dong, Yao Wang, Lei Xiang, Ji Liu, Kai Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China

ISBN: (纸本)9783031059360;9783031059353

knowledge graph completion (KGC) aims to predict missing connections by mining information already present in a knowledge graph (KG). Predicting such connections is heavily dependent on the inference patterns. IsA relations (i.e., instanceOf and subclassOf) play an essential part in inferencing the composition pattern. Some existing methods already exploit is A relations. However, most of them learn insufficient representations, which may limit the performance. To address this issue, we propose a box-based knowledge graph embedding model called IBKE, in which concepts are embedded as boxes, and instances are represented by vectors in the same semantic space. According to the relative positions of elements, IBKE can naturally formulate isA relations. In addition, we introduce a random update strategy (RUS) for optimizing training, which updates embeddings in a probability pattern. Experimental results on benchmark datasets show that IBKE outperforms most existing state-of-the-art methods, and demonstrate the effectiveness of RUS.

关键词： knowledge graph embedding Link prediction Box

来源：评论

学校读者我要写书评

暂无评论

Clustering-Enhanced knowledge graph embedding 1

引用

10th CCF Big Data Conference (BigData)

作者： Zhang, Fuwei Zhang, Zhao Zhuang, Fuzhen Gu, Jingjing Shi, Zhiping He, Qing Chinese Acad Sci Key Lab Intelligent Informat Proc Chinese Acad Sc Inst Comp Technol Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Chinese Acad Sci Inst Comp Technol Beijing 100190 Peoples R China Xiamen Inst Data Intelligence Xiamen Peoples R China Nanjing Univ Aeronaut & Astronaut Nanjing Peoples R China Capital Normal Univ Beijing 100048 Peoples R China

ISBN: (数字)9789811983313

ISBN: (纸本)9789811983306;9789811983313

knowledge graph embedding (KGE) is a task to transform the symbolic entities and relations in knowledge graphs (KGs) into low-dimensional vectors, which facilitates the use of KGs in downstream applications. However, most existing models ignore the semantic correlations among similar entities and relations. Indeed, we find there exist semantically similarities in entities or relations. To take advantage of these semantic correlations, we utilize the entity cluster and relation cluster information to enhance traditional KGE models. Particularly, we first use an unsupervised clustering algorithm to get the entity and relation clusters. Then we decompose the representation of the entities or relations into two parts, one is from the entities or relations themselves, and the other is from the cluster information. By this way, the entities or relations can make full use of both the common information of their similar entities or relations and the unique information from themselves. Extensive experiments on popular benchmarks demonstrate the effectiveness of the proposed models.

关键词： knowledge graph Clustering knowledge graph embedding nowledge representation

来源：评论

学校读者我要写书评

暂无评论

Course recommendation model based on knowledge graph embedding 16

Course recommendation model based on Knowledge Graph Embeddi...

引用

16th International Conference on Signal-Image Technology and Internet-Based Systems (SITIS)

作者： Chetoui, Ismail El Bachari, Essaid El Adnani, Mohamed Cadi Ayyad Univ Dept Comp Sci Marrakech Morocco

ISBN: (纸本)9781665464956

The use of graphs as a method of storing data has begun to rise significantly in recent years, due to the new way of representing data in graphs. This is leveraged by the structure of graphs that facilitate modeling interactions between real-world entities. With the rapid development of technologies such as machine learning and deep learning, the digitalization of education has entered the era with artificial intelligence as the main feature. As an important part of artificial intelligence technology, knowledge graph as a format of data storing provides possibilities for smart education and promotes the innovation and development of smart education. In this context, we present in this communication a model that we built to facilitate reaching the appropriate lesson for each learner among a large group of lessons in an eLearning graph, this model is practically divided into two parts, the first in which we sort the learners by defining the profile of each of them, which will facilitate their classification into groups, and in the second part, we connect each learner with his appropriate path to achieve the desired lesson, by building a nodal path through sequential prediction until reaching the target lesson, relying mainly on embedding graph models.

关键词： knowledge graph embedding Education Course Recommendation system

来源：评论

学校读者我要写书评

暂无评论

TransP: A New knowledge graph embedding Model by Translating on Positions 11

TransP: A New Knowledge Graph Embedding Model by Translating...

引用

11th IEEE International Conference on knowledge graph (IEEE ICKG)

作者： Ren, Feiliang Li, Jucheng Zhang, Huihui Yang, Xiaochun Northeastern Univ Sch Comp Sci & Engn Shenyang Peoples R China

ISBN: (纸本)9781728181561

embedding knowledge graph into continuous space(s) is attracting more and more research attention, and lots of novel methods have been proposed. Among them, translation based methods achieved state-of-the-art experimental results. However, most of existing work ignore following two facts. First, once a relation is fixed, its linked head and tail entities will be fixed to a certain extent. Second, in a triplet, if one of its entities and the relation are fixed, the other entity's candidates will also be fixed to a certain extent. Taking these two facts into consideration, we propose a new knowledge graph embedding model named TransP, which defines a head entity space and a tail entity space for each relation. During embedding, TransP first projects entities into these two position spaces. Then the entities in these two position spaces are further projected into a common transformation space, in which the relation is converted into two transformation matrices. A symmetrical score function is designed to connect a correct triplet's head and tail entity in the common space. The basic idea behind this score function is that if a correct triplet holds, its head (tail) entity should be able to be converted into its tail (head) entity when taking the relation's transformation matrix as an intermediate bridge. Viewing the transformation matrices as decoders, this process is just like a common translation process. We evaluate TransP on triplet classification task and link prediction task. Extensive experiments show that TransP achieves much better performance than other baseline models.

关键词： knowledge graph embedding translation based KGE triplet classification link prediction

来源：评论

学校读者我要写书评

暂无评论

MDNCaching: A Strategy to Generate Quality Negatives for knowledge graph embedding 35th

MDNCaching: A Strategy to Generate Quality Negatives for Kno...

引用

35th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems (IEA/AIE)

作者： Madushanka, Tiroshan Ichise, Ryutaro SOKENIAI Grad Univ Adv Studies Chiyoda Ku 2-1-2 Hitotsubashi Tokyo Japan Natl Inst Informat Chiyoda Ku 2-1-2 Hitotsubashi Tokyo Japan Univ Kelaniya Kelaniya Sri Lanka

ISBN: (纸本)9783031085307;9783031085291

knowledge graph embedding (KGE) has become an integral part of AI as it enables knowledge construction and exploring missing information. KGE encodes the entities and relations (elements) in a knowledge graph into a low-dimensional vector space. The conventional KGE models are trained using positive and negative examples by discriminating the positives from the negatives. However, the existing knowledge graphs contain only the positives. Hence, it is required to generate negatives to train KGE models. This remains a key challenge in KGE due to various reasons. Among them, the quality of the negatives is a critical factor for KGE models to produce accurate embeddings of the observed facts. Therefore, researchers have introduced various strategies such as Bernoulli negative sampling to generate quality negatives that are hard to distinguish from positives. However, fixed negative sampling strategies are suffering from vanishing gradients and false negatives. Later, the dynamic negative sampling techniques were introduced to overcome the vanishing gradient, but the false negatives still remain as a challenge to the research community. The present research introduces a new strategy called MDNCaching (Matrix Decomposed Negative Caching), which generates negatives considering the dynamics of the embedding space while exploring the quality negatives with large similarity scores. Matrix decomposition is used to eliminate false negatives, and hence, the MDNCaching ensures the quality of the generated negatives. The performance of MDNCaching was compared with the existing state-of-art negative sampling strategies, and the results reflect that the proposed negative sampling strategy can produce a notable improvement in existing KGE models.

关键词： Negative sampling knowledge graph embedding Matrix decomposition

来源：评论

学校读者我要写书评

暂无评论

HRS: Hybrid Recommendation System based on Attention Mechanism and knowledge graph embedding

HRS: Hybrid Recommendation System based on Attention Mechani...

引用

IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT)

作者： Dong, Chunfang Ju, Xuchan Ma, Yue Zhengzhou Univ Zhengzhou Key Lab Big Data Anal & Applicat Henan Acad Big Data Zhengzhou Peoples R China Shenzhen Univ Coll Math & Stat Shenzhen Peoples R China

ISBN: (纸本)9781450391870

Traditional recommendation methods often have sparsity and cold start problems in real applications. Researchers found that introducing knowledge graphs into recommender systems as a kind of auxiliary information can alleviate these problems and improve the performance of the recommender systems. This paper put forward a Hybrid Recommendation System based on Attention Mechanism and knowledge graph embedding (HRS). It uses cross&compress unit and preference propagation respectively to enrich the features of items and users. In this process, we use the attention mechanism and knowledge graph embedding to enhance the recommender system. After obtaining the user vector representation and the item vector representation, we can predict the probability of the user clicking on the item. The experiments on three datasets derived from the actual scenes demonstrate the competitiveness of HRS, compared with several state-of-the-art baselines in the recommendation.

关键词： recommender systems knowledge graph attention mechanism knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

Scaling knowledge graph embedding Models for Link Prediction 2

Scaling Knowledge Graph Embedding Models for Link Prediction

引用

2nd European Workshop on Machine Learning and Systems (EuroMLSys)

作者： Sheikh, Nasrullah Qin, Xiao Reinwald, Berthold Lei, Chuan IBM Res Almaden San Jose CA 95120 USA Instacart San Francisco CA USA

ISBN: (纸本)9781450392549

Developing scalable solutions for training graph Neural Networks (GNNs) for link prediction tasks is challenging due to the inherent data dependencies which entail high computational costs and a huge memory footprint. We propose a new method for scaling training of knowledge graph embedding models for link prediction to address these challenges. Towards this end, we propose the following algorithmic strategies: self-sufficient partitions, constraint-based negative sampling, and edge mini-batch training. The experimental evaluation shows that our scaling solution for GNN-based knowledge graph embedding models achieves a 16x speed up on benchmark datasets while maintaining a comparable model performance to non-distributed methods on standard metrics.

关键词： knowledge graph embedding graph Neural Networks Distributed Data Parallel Training

来源：评论

学校读者我要写书评

暂无评论

Confidence-aware Self-Semantic Distillation on knowledge graph embedding 24

Confidence-aware Self-Semantic Distillation on Knowledge Gra...

引用

33rd ACM International Conference on Information and knowledge Management (CIKM)

作者： Liu, Yichen Chen, Jiawei Chen, Defang Zhou, Zhehui Feng, Yan Wang, Can Zhejiang Univ Coll Comp Sci Hangzhou Peoples R China Zhejiang Univ State Key Lab Blockchain & Data Secur Hangzhou Peoples R China China & Hangzhou High Tech Zone Binjiang Inst Blo Hangzhou Peoples R China

ISBN: (纸本)9798400704369

knowledge graph embedding (KGE), which projects entities and relations into continuous vector spaces, has garnered significant attention. Although high-dimensional KGE methods offer better performance, they come at the expense of significant computation and memory overheads. Decreasing embedding dimensions significantly deteriorates model performance. While several recent efforts utilize knowledge distillation or non-Euclidean representation learning to augment the effectiveness of low-dimensional KGE, they either necessitate a pre-trained high-dimensional teacher model or involve complex non-Euclidean operations, thereby incurring considerable additional computational costs. To address this, this work proposes Confidence-aware Self-knowledge Distillation (CSD) that learns from the model itself to enhance KGE in a low-dimensional space. Specifically, CSD extracts knowledge from embeddings in previous iterations, which would be utilized to supervise the learning of the model in the next iterations. Moreover, a specific semantic module is developed to filter reliable knowledge by estimating the confidence of previously learned embeddings. This straightforward strategy bypasses the need for time-consuming pre-training of teacher models and can be integrated into various KGE methods to improve their performance. Our comprehensive experiments on six KGE backbones and four datasets underscore the effectiveness of the proposed CSD.

关键词： knowledge graph embedding knowledge Distillation Confidence Self-distillation

来源：评论

学校读者我要写书评

暂无评论

A Lightweight knowledge graph embedding Framework for Efficient Inference and Storage 21

A Lightweight Knowledge Graph Embedding Framework for Effici...

引用

30th ACM International Conference on Information and knowledge Management (CIKM)

作者： Wang, Haoyu Wang, Yaqing Lian, Defu Gao, Jing Purdue Univ W Lafayette IN 47907 USA Univ Sci & Technol China Hefei Peoples R China Yangtze River Delta Informat Intelligence Innovat Wuhu Peoples R China

ISBN: (纸本)9781450384469

knowledge graphs, which consist of entities and their relations, have become a popular way to store structured knowledge. knowledge graph embedding (KGE), which derives a representation for each entity and relation, has been widely used to capture the semantics of the information in the knowledge graphs, and has demonstrated great success in many downstream applications, such as the extraction of similar entities in response to a query entity. However, existing KGE methods cannot work well on emerging knowledge graphs that are large-scale due to the constraints in storage and inference efficiency. In this paper, we propose a lightweight KGE model, LightKG, which significantly reduces storage as well as running time needed for inference. Instead of storing a continuous vector for every entity, LightKG only needs to store a few codebooks, each of which contains some codewords that correspond to the representatives among the embeddings, and the indices that correspond to the codeword selections for entities. Hence LightKG can achieve highly efficient storage. The efficiency of the downstream querying process can be significantly boosted too with the proposed LightKG model as the relevance score between the query and an entity can be efficiently calculated via a quick look-up in a table that contains the scores between the query and codewords. The storage and inference efficiency of LightKG is achieved by its novel design. LightKG is an end-to-end framework that automatically infers codebooks and codewords and generates an approximated embedding for each entity. A residual module is included in LightKG to induce the diversity among codebooks, and a continuous function is adopted to approximate codeword selection, which is non-differential. In addition, to further improve the performance of KGE, we propose a novel dynamic negative sampling method based on quantization, which can be applied to the proposed LightKG or other KGE methods. We conduct extensive experiments on

关键词： knowledge graph embedding quantization

来源：评论

学校读者我要写书评

暂无评论

Learning Dynamic knowledge graph embedding in Evolving Service Ecosystems via Meta-Learning

Learning Dynamic Knowledge Graph Embedding in Evolving Servi...

引用

IEEE International Conference on Web Services (IEEE ICWS)

作者： Sun, Hongliang Liu, Jinlan Wang, Can Sui, Dianbo Tu, Zhiying Xu, Xiaofei Harbin Inst Technol Fac Comp Weihai Peoples R China

ISBN: (纸本)9798350368567;9798350368550

In the context of dynamic service ecosystems, the inability of conventional knowledge graph embedding (KGE) methods to efficiently update incremental knowledge poses a significant challenge for the effectiveness of intelligent web applications. To address the continuous updating challenges of service knowledge, this paper introduces MetaHG, a meta-learning strategy for KGE. Unlike existing meta-learning KGE studies that focus solely on local entity information, MetaHG incorporates both local and potential global structural information from current snapshot's seen knowledge graphs (KGs) to mitigate issues such as spatial deformation and enhance the representation of unseen entities. Our approach initializes entity embeddings using 'in' and 'out' relationship matrices and refines them through a hybrid graph neural network (GNN) framework, which includes a GNN layer for local information and a hypergraph neural network (HGNN) layer for potential global information. The meta-learning strategy embedded in MetaHG effectively transfers meta-knowledge for the accurate representation of emerging entities. Extensive experiments are conducted on a self-collected clothing industry service dataset and two publicly available open-source KG datasets. By comparing with several baselines, experiment results demonstrate the superior performance of MetaHG in generating high-quality embeddings for emerging entities and dynamically updating service knowledge.

关键词： dynamic service ecosystem knowledge graph embedding incremental knowledge update meta-learning graph neural networks

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共57页 << < 10 11 12 13 14 15 16 17 18 19 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：