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

121 篇 会议
1 册 图书
1 篇 期刊文献

馆藏范围

123 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

93 篇 工学
- 88 篇 计算机科学与技术...
- 37 篇 软件工程
- 33 篇 电气工程
- 30 篇 信息与通信工程
- 11 篇 控制科学与工程
- 10 篇 生物工程
- 3 篇 动力工程及工程热...
- 3 篇 测绘科学与技术
- 2 篇 生物医学工程（可授...
- 1 篇 机械工程
- 1 篇 电子科学与技术（可...
- 1 篇 建筑学
- 1 篇 土木工程
- 1 篇 化学工程与技术
- 1 篇 交通运输工程
- 1 篇 船舶与海洋工程
- 1 篇 环境科学与工程（可...
23 篇 理学
- 12 篇 生物学
- 8 篇 数学
- 3 篇 系统科学
- 1 篇 物理学
- 1 篇 化学
- 1 篇 统计学（可授理学、...
11 篇 管理学
- 9 篇 管理科学与工程(可...
- 6 篇 工商管理
- 3 篇 图书情报与档案管...
2 篇 法学
- 2 篇 社会学
2 篇 教育学
- 2 篇 教育学
1 篇 经济学
- 1 篇 应用经济学
1 篇 医学
- 1 篇 基础医学(可授医学...

主题

9 篇 sensor systems
6 篇 edge computing
5 篇 iot
5 篇 distributed comp...
5 篇 federated learni...
4 篇 intelligent netw...
4 篇 protocols
3 篇 scalability
3 篇 resource managem...
3 篇 wireless sensor ...
3 篇 distributed syst...
3 篇 blockchain
3 篇 artificial intel...
3 篇 cloud computing
3 篇 computer network...
3 篇 data models
3 篇 distributed ledg...
2 篇 internet of thin...
2 篇 ethereum
2 篇 routing

机构

2 篇 college of compu...
2 篇 yangzhou power s...
2 篇 wuhan univ techn...
2 篇 sidroco holdings...
2 篇 univ jinan sch i...
2 篇 xiamen univ tech...
1 篇 information scie...
1 篇 oxford brookes u...
1 篇 chongqing key la...
1 篇 department of co...
1 篇 beijing jiaotong...
1 篇 department of co...
1 篇 anhui univ techn...
1 篇 southern methodi...
1 篇 school of artifi...
1 篇 univ jinan infor...
1 篇 school of comput...
1 篇 research team on...
1 篇 department of so...
1 篇 nearby comp sl b...

作者

2 篇 zhai xiaojun
2 篇 zhou xiaokang
2 篇 zhao yue
2 篇 liao yangzhe
2 篇 liu xin
2 篇 hu xiping
1 篇 batista fabrizio
1 篇 ouahbi ibrahim
1 篇 liu xiaoming
1 篇 li xi
1 篇 sari talip tolga
1 篇 biswas sujit
1 篇 mendiboure leo
1 篇 qu qianhui
1 篇 george c. polyzo...
1 篇 wen-lin chang
1 篇 khoi le quoc
1 篇 sylla tidiane
1 篇 irfan awan
1 篇 qi jin

语言

122 篇 英文
1 篇 其他

检索条件"任意字段=18th International Conference on Distributed Computing and Intelligent Technology, ICDCIT 2022"

共 123 条记录，以下是1-10 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：

18th international conference on distributed computing and intelligent technology, icdcit 2022

18th International Conference on Distributed Computing and I...

引用

18th international conference on distributed computing and intelligent technology, icdcit 2022

ISBN: (纸本)9783030948757

the proceedings contain 19 papers. the special focus in this conference is on distributed computing and intelligent technology. the topics include: An Introduction to Graph Neural Networks from a distributed computing Perspective;Towards Temporally Uncertain Explainable AI Planning;the Impact of Synchronization in Parallel Stochastic Gradient Descent;a distributed Algorithm for Constructing an Independent Dominating Set;An Approach to Cost Minimization with EC2 Spot Instances Using VM Based Migration Policy;transforming Medical Resource Utilization Process to Verifiable Timed Automata Models in Cyber-Physical Systems;An SDN Implemented Adaptive Load Balancing Scheme for Mobile Networks;rewriting Logic and Petri Nets: A Natural Model for Reconfigurable distributed Systems;preface;Modern AI/ML Methods for Healthcare: Opportunities and Challenges;MCDPS: An Improved Global Scheduling Algorithm for Multiprocessor Mixed-Criticality Systems;replication Based Fault Tolerance Approach for Cloud;A Comparative Study on MFCC and Fundamental Frequency Based Speech Emotion Classification;efficient Traffic Routing in Smart Cities to Minimize Evacuation Time During Disasters;early Detection of Parkinson’s Disease as a Pre-diagnosis Tool Using Various Classification Techniques on Vocal Features;extracting Emotion Quotient of Viral Information Over Twitter;a Novel Modified Harmonic Mean Combined with Cohesion Score for Multi-document Summarization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

distributed and Personalized Federated Learning in Wireless Ad Hoc Networks 18th

Distributed and Personalized Federated Learning in Wireless...

引用

18th international conference on Wireless Artificial intelligent computing Systems and Applications, WASA 2024

作者： Huang, Baogui Wang, Bei Li, Xiangqian Ma, Chunmei Li, Guangshun Lai, Qingliang School of Computer Science Qufu Normal University Shandong Rizhao276826 China Huilian Zhongchuang Intelligent Technology Research Institute Shandong Rizhao276826 China

ISBN: (纸本)9783031714665

this paper studies the difficult task of designing federated learning algorithms tailored for wireless ad hoc networks. Federated learning in such networks presents numerous challenges, including signal interference, decentralized infrastructure, dynamic changes in network topology, heterogeneous devices, and diverse data statistics. In response to these challenges, this paper proposes a fully distributed and personalized federated learning algorithm specifically designed for wireless ad hoc networks, named ADDPFed. ADDPFed tackles the issue of wireless interference by leveraging non-orthogonal multiple access technology and successive interference cancellation for enhancing overall communication efficiency. Another key strength of ADDPFed lies in its ability to enable direct local model exchanges among neighboring clients, eliminating the need for central server coordination for model aggregation. For the model aggregation, ADDPFed first calculates the distance between local models using the Tonimoto coefficient, and then assigns suited aggregation weights to these models. this approach emphasizes the contribution of similar models to the global model, effectively tackling the issue of data statistical heterogeneity. Extensive experiments validate the effectiveness of ADDPFed, paving the way for enhanced collaborative and distributed learning paradigms in wireless ad hoc networks. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework 25

引用

18th ACM international conference on Web Search and Data Mining, WSDM 2025

作者： Qiao, Yiran Ao, Xiang Liu, Yang Xu, Jiarong Sun, Xiaoqian He, Qing Institute of Computing Technology CAS Beijing China Key Lab of AI Safety Chinese Academy of Sciences Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences CAS Beijing China School of Management Fudan University Shanghai China Institute of Intelligent Computing Technology Suzhou China

ISBN: (纸本)9798400713293

Recent prevailing works on graph machine learning typically follow a similar methodology that involves designing advanced variants of graph neural networks (GNNs) to maintain the superior performance of GNNs on different graphs. In this paper, we aim to streamline the GNN design process and leverage the advantages of Large Language Models (LLMs) to improve the performance of GNNs on downstream tasks. We formulate a new paradigm, coined "LLMs-as-Consultants", which integrates LLMs with GNNs in an interactive manner. A framework named LOGIN (LLM cOnsulted GNN traINing) is instantiated, empowering the interactive utilization of LLMs within the GNN training process. First, we attentively craft concise prompts for spotted nodes, carrying comprehensive semantic and topological information, and serving as input to LLMs. Second, we refine GNNs by devising a complementary coping mechanism that utilizes the responses from LLMs, depending on their correctness. We empirically evaluate the effectiveness of LOGIN on node classification tasks across both homophilic and heterophilic graphs. the results illustrate that even basic GNN architectures, when employed within the proposed LLMs-as-Consultants paradigm, can achieve comparable performance to advanced GNNs with intricate designs. Our code is available at https://***/QiaoYRan/LOGIN. © 2025 Copyright held by the owner/author(s).

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

DS-TFP: A distributed and Secure Traffic Flow Prediction Framework Based on Federated Graph Learning 18th

DS-TFP: A Distributed and Secure Traffic Flow Prediction Fr...

引用

18th international conference on Wireless Artificial intelligent computing Systems and Applications, WASA 2024

作者： Fu, Yu Sun, Lijun Ma, Zhihui Gao, Haoxiang Yan, Chaoying Qingdao University of Science and Technology Qingdao266061 China

ISBN: (纸本)9783031714665

Traffic flow prediction (TFP) plays a crucial role in intelligent transportation systems. Due to the need to collect data during the prediction process, TFP can face the risk of data leakage. Federated Graph Learning (FGL) is a novel method for protecting graph data privacy, but there are lower performance and Byzantine attacks challenges when applying FGL to TFP. In order to address these challenges, this paper proposes a distributed and secure traffic flow prediction (DS-TFP) framework based on federated graph learning, which includes three methods. Firstly, a New Spatial-Temporal Graph (NSTG) model is applied for the dynamic changes of temporal and spatial and simplifies the encoding procedures. Secondly, graph models are combined with federated method to ensure the protection of local data privacy. thirdly, the resist Byzantine attacks method which utilizes clients dynamic cross-validation and a voting-based aggregation algorithm, is designed to enhance system security. Finally, extensive experiments are conducted on two datasets. the results show that compared with the baselines, the Fed-NSTG model improved accuracy by an average of 8.15%. the DS-TFP framework can maintain an average prediction accuracy of 87.57% even under the Byzantine attacks. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Merging Framework for Homogeneous and Heterogeneous Blockchain Systems 18th

A Novel Merging Framework for Homogeneous and Heterogeneou...

引用

18th international conference on Wireless Artificial intelligent computing Systems and Applications, WASA 2024

作者： Zhu, Liehuang Bukhari, Sadaf Sharif, Kashif Li, Fan Fardous, Shumaila Biswas, Sujit Beijing Institute of Technology Beijing China CITY University of London London United Kingdom

ISBN: (纸本)9783031714665

this paper presents two solutions for merging diverse blockchain systems: Homogeneous Chain Consolidation (HCC) and Heterogeneous Multi-chain Integration Architecture (HMIA). As blockchain networks expand, integrating these disparate ledgers becomes crucial. HCC merges similar chains using common genesis blocks, enhancing efficiency by pooling validator resources. HMIA integrates different chains through meta-blocks, balancing compatibility and autonomy. We evaluate these approaches using consensus times, block sizes, and ledger growth. HCC improves throughput and efficiency, while HMIA prioritizes decentralized attributes. Use case-based evaluation shows that the proposed work can be seamlessly integrated with existing solutions, while the performance of implementation proves the low cost of resources in merged networks. Our frameworks offer insights into merging blockchains, addressing critical challenges in interconnected decentralized networks. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： distributed ledger

来源：评论

学校读者我要写书评

暂无评论

Enhancing Scalability: A Complete Tree Sharding Architecture Towards IoT 18th

Enhancing Scalability: A Complete Tree Sharding Architecture...

引用

18th international conference on Wireless Artificial intelligent computing Systems and Applications, WASA 2024

作者： Zhang, Luyi Wang, Yujue Ding, Yong Liang, Hai Yang, Changsong Zheng, Haibin Guangxi Key Laboratory of Cryptography and Information Security School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China Hangzhou Innovation Institute of Beihang University Hangzhou310052 China Institute of Cyberspace Technology HKCT Institute for Higher Education Hong Kong Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Shenzhen518055 China Guangxi Engineering Research Center of Industrial Internet Security and Blockchain Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9783031714665

With the rapid proliferation of integration of blockchain and IoT, traditional centralized architectures and single-node processing have been effectively solved, but scalability of blockchain have become inadequate to meet the demands of high-load environments. Sharded blockchain brings an innovative approach to tackle the scalability of blockchain and has the potential to greatly enhance the performance of IoT based on blockchain. this paper introduces CTS towards IoT – complete tree sharding that overlaps shards to enable a little shards to retain records of other shards, facilitating the validation of cross-shard transactions as intra-shard transactions. A tree sharding consensus mechanism that relies on the complete tree architecture is proposed to ensure consistency among interconnected shards during the execution of cross-shard transactions. A prototype for CTS towards IoT is simulated and the findings demonstrate that CTS can enhance transaction throughput by a factor of 1.3 when compared to state of the art layered sharding systems observed in a system consisting of 15 shards and 1500 nodes. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： distributed ledger

来源：评论

学校读者我要写书评

暂无评论

FedDCT: A Dynamic Cross-Tier Federated Learning Framework in Wireless Networks 18th

FedDCT: A Dynamic Cross-Tier Federated Learning Framework in...

引用

18th international conference on Wireless Artificial intelligent computing Systems and Applications, WASA 2024

作者： Xian, Youquan Gan, Xiaoyun Yao, Chuanjian Li, Dongcheng Wang, Peng Liu, Peng Zhao, Ying Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin54104 China School of Computer Science and Engineering Guangxi Normal University Guilin54104 China School of Business Guilin University of Electronic Technology Guilin54104 China

ISBN: (纸本)9783031714634

Federated Learning (FL), as a privacy-preserving machine learning paradigm, trains a global model across devices without exposing local data. However, resource heterogeneity and inevitable stragglers in wireless networks severely impact the efficiency and accuracy of FL training. In this paper, we propose a novel Dynamic Cross-Tier Federated Learning framework (FedDCT). Firstly, we design a dynamic tiering strategy that dynamically partitions devices into different tiers based on their response times and assigns specific timeout thresholds to each tier to reduce single-round training time. then, we propose a cross-tier device selection algorithm that selects devices that respond quickly and are conducive to model convergence to improve convergence efficiency and accuracy. Experimental results demonstrate that the proposed approach under wireless networks outperforms the baseline approach, with an average reduction of 54.7% in convergence time and an average improvement of 1.83% in convergence accuracy. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Communication-Efficient Secure Neural Network via Key-Reduced distributed Comparison Function 18th

Communication-Efficient Secure Neural Network via Key-Reduce...

引用

18th international conference on Provable and Practical Security

作者： Yang, Peng Jiang, Zoe Lin Gao, Shiqi Wang, Hongxiao Zhou, Jun Jin, Yangyiye Yiu, Siu-Ming Fang, Junbin Harbin Inst Technol Shenzhen Peoples R China Univ Hong Kong Hong Kong Peoples R China Shanghai Pudong Dev Bank Shanghai Peoples R China Jinan Univ Guangzhou Peoples R China

ISBN: (纸本)9789819609567;9789819609574

In privacy-preserving neural network, the high communication costs of securely computing non-linear functions is the primary performance bottleneck. For commonly used non-linear functions, such as ReLU, existing methods adopt an offline-online computation paradigm and utilizes distributed comparison function (DCF) to reduce communication costs. Specifically, these methods prepare DCF keys in the offline phase and perform secure non-linear function computation using these keys in the online phase. However, the practicality of these methods is limited due to the substantial size of DCF keys and the heavy reliance on a trusted third party during the offline phase. In this work, we introduce FssNN, a communication-efficient secure two-party neural network framework, which features a key-reduced DCF scheme without a trusted third party to enable practical secure training and inference. Firstly, by analyzing the correlations between DCF keys to eliminate redundant parameters, we propose a key-reduced DCF scheme with a compact additive construction, decreasing the size of DCF keys by about 17.9% and offline communication costs by approximately 28.0%. Secondly, leveraging an MPC-friendly pseudorandom number generator, we propose a secure two-party distributed key generation protocol for our key-reduced DCF, eliminating the need for a trusted third party. Finally, we utilize the key-reduced DCF and additive secret sharing to compute non-linear and linear functions, and design secure computation protocols with constant online communication rounds for neural network operations, reducing online communication costs by 28.9%-43.4%. We provide formal security proofs and evaluate the performance of FssNN on various models and datasets. Experimental results show that compared to the state-of-the-art framework AriaNN, our framework reduces the total communication costs of secure training and inference by approximately 25.4% and 26.4% respectively.

关键词： Privacy-preserving neural network Secure multi-party computation distributed comparison function Additive secret sharing

来源：评论

学校读者我要写书评

暂无评论

An Introduction to Graph Neural Networks from a distributed computing Perspective 18th

An Introduction to Graph Neural Networks from a Distributed ...

引用

18th international conference on distributed computing and intelligent technology (icdcit)

作者： Papp, Pal Andras Wattenhofer, Roger Swiss Fed Inst Technol Zurich Switzerland

ISBN: (纸本)9783030948764;9783030948757

the paper provides an introduction into the theoretical expressiveness of graph neural networks. We discuss the basic properties and main applications of standard GNN models, and we show how these constructions are both upper and lower bounded in expressive power by the Weisfeiler-Lehman test. We then outline a wide variety of approaches to increase the expressiveness of GNNs above this theoretical limit, and discuss the strengths and weaknesses of these methods.

关键词： Graph Neural Network distributed computing Weisfeiler-Lehman test Expressive power

来源：评论

学校读者我要写书评

暂无评论

Rewriting Logic and Petri Nets: A Natural Model for Reconfigurable distributed Systems 18th

Rewriting Logic and Petri Nets: A Natural Model for Reconfig...

引用

18th international conference on distributed computing and intelligent technology (icdcit)

作者： Capra, Lorenzo Univ Milan Dipartimento Informat Milan Italy

ISBN: (纸本)9783030948764;9783030948757

Petri Nets (PN) are a central model for concurrent or distributed systems, but not expressive enough to represent dynamically reconfigurable systems. On the other side, Rewriting Logic has proved to be a natural framework for several formal models of distributed systems. We propose an efficient Maude formalization of dynamically reconfigurable PT nets (with inhibitor arcs), using as a running example a fault-tolerant manufacturing system. We discuss the advantages of such a hybrid approach, as well as some concerns that are raised.

关键词： Maude PT nets Reconfigurable distributed systems

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13页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：