检索结果-内蒙古大学图书馆

39th International Conference on Machine Learning, ICML 2022

作者： Nguyen, Tam Nguyen, Tan M. Le, Dung D. Nguyen, Duy Khuong Tran, Viet-Anh Baraniuk, Richard G. Ho, Nhat Osher, Stanley J. FPT Software AI Center Ha Noi Viet Nam Department of Mathematics University of California Los Angeles United States College of Engineering and Computer Science VinUniversity Ha Noi Viet Nam Deezer Research France Department of Electrical and Computer Engineering Rice University Houston United States Department of Statistics and Data Sciences The University of Texas Austin United States

Multi-head attention is a driving force behind state-of-the-art transformers, which achieve remarkable performance across a variety of natural language processing (NLP) and computer vision tasks. It has been observed that for many applications, those attention heads learn redundant embedding, and most of them can be removed without degrading the performance of the model. Inspired by this observation, we propose Transformer with a Mixture of Gaussian Keys (Transformer-MGK), a novel transformer architecture that replaces redundant heads in transformers with a mixture of keys at each head. These mixtures of keys follow a Gaussian mixture model and allow each attention head to focus on different parts of the input sequence efficiently. Compared to its conventional transformer counterpart, Transformer-MGK accelerates training and inference, has fewer parameters, and requires fewer FLOPs to compute while achieving comparable or better accuracy across tasks. Transformer-MGK can also be easily extended to use with linear attention. We empirically demonstrate the advantage of Transformer-MGK in a range of practical applications, including language modeling and tasks that involve very long sequences. On the Wikitext-103 and Long Range Arena benchmark, Transformer-MGKs with 4 heads attain comparable or better performance to the baseline transformers with 8 heads. Copyright © 2022 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning dynamics of kernel-based deep neural networks in manifolds

引用

science China(Information sciences) 2021年第11期64卷 105-119页

作者： Wei WU Xiaoyuan JING Wencai DU Guoliang CHEN School of Computer Science Wuhan University Institute of Deep-sea Science and Engineering Chinese Academy of Sciences School of Computer Guangdong University of Petrochemical Technology Institute of Data Science City University of Macau College of Computer Science and Software Engineering Shenzhen University

Convolutional neural networks(CNNs) obtain promising results via layered kernel convolution and pooling operations, yet the learning dynamics of the kernel remain obscure. We propose a continuous form to describe kernel-based convolutions through integration in neural manifolds. The status of spatial expression is proposed to analyze the stability of kernel-based CNNs. We divide CNN dynamics into the three stages of unstable vibration, collaborative adjusting, and stabilized fluctuation. According to the system control matrix of the kernel, the kernel-based CNN training proceeds via the unstable and stable status and is verified by numerical experiments.

关键词： learning dynamics kernel-based convolution manifolds control model network stability

来源：评论

学校读者我要写书评

暂无评论

A Revocable Fast and Lightweight Parallel Encryption Scheme for IIoT

引用

IEEE Internet of Things Journal 2025年

作者： Lu, Junze Hu, Chunqiang Chen, Jiajun Xia, Hui Chongqing University Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education China Chongqing University School of Big Data and Software Engineering Chongqing 400030 China Ocean University of China College of Computer Science and Technology China

As the Industrial Internet of Things (IIoT) expands, the number of stakeholders increases. Many entities require significant amounts of data from industrial devices. These data streams improve information sharing and optimize the industrial chain. However, IIoT’s enormous data volumes pose challenges to traditional encryption methods, which are unable to meet efficiency and energy consumption requirements. Thus, a new, efficient encryption algorithm is essential for managing data flows among IIoT subscribers. In this paper, we propose a fast, low-energy, high-security encryption scheme to manage multi-entity data streams. First, we introduce a novel encryption scheme based on the Subset Sum Problem (SSP), which improves energy efficiency and speed. Second, to meet subscription requirements, we employ attribute-based encryption (ABE) for key forwarding. Finally, we handle subscription revocations with device key updates. The device owner utilizes their secret value to generate an identity proof with a key update request. © 2014 IEEE.

关键词： attribute based encryption data sharing Industrial Internet of Things Subset sum problem

来源：评论

学校读者我要写书评

暂无评论

Visitors Vis: Interactive Mining of Suspected Medical Insurance Fraud Groups 18th

Visitors Vis: Interactive Mining of Suspected Medical Insura...

引用

18th CCF Conference on Computer Supported Cooperative Work and Social Computing, ChineseCSCW 2023

作者： Dong, Rixin Liu, Hanlin Guo, Xu Zhou, Jiantao College of Computer Science Inner Mongolia University Hohhot China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolia Hohhot China Engineering Research Center of Ecological Big Data Ministry of Education Hohhot China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Hohhot China Inner Mongolia Key Laboratory of Social Computing and Data Processing Hohhot China Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Hohhot China Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (纸本)9789819996360

As medical insurance continues to grow in size, the losses caused by medical insurance fraud cannot be underestimated. Current data mining and predictive techniques have been applied to analyze and explore the health insurance fraud population. However, previous studies only provide summary results and do not show the details of comparative analysis during the visit, resulting in the inability of auditors to quickly identify anomalous behavior. In this paper, we propose a visual analytics system for interactive medical insurance fraud detection to support the exploration and interpretation of different access processes. We propose a weighted MinDL to improve the accuracy of visit pattern classification in the time-series modeling process, and design a data analysis model and visual analysis view based on medical insurance fraud characteristics to reveal and explore the characteristics of medical insurance fraud groups. We collaborate with related organizations to design and implement an interactive visualization for medical insurance fraud group detection using real Medicare data and expert interviews The system is effective and practical in detecting and analyzing medical insurance fraud syndicates. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Health insurance

来源：评论

学校读者我要写书评

暂无评论

Using Rough Sets to Improve the High-dimensional data Anomaly Detection Method Based on Extended Isolation Forest

Using Rough Sets to Improve the High-dimensional Data Anomal...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Hanlin Liu Jiantao Zhou Hua Li College of Computer Science Inner Mongolia University Hohhot China Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Ministry of Education Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Hohhot China

Anomaly detection refers to the identification of data objects that deviate from the general data distribution. One of the important challenges in anomaly detection is handling high-dimensional data, especially when it contains a large number of redundant attributes. Although traditional Isolation Forest (iForest) and Extended Isolation Forest (EIF) have performed well in anomaly detection, the detection accuracy is still extremely influenced by redundant attributes. In this paper, we propose a two-tier architecture named RS-EIF, to alleviate the negative impact of redundant attributes. Specifically, the RS-EIF combines the rough set theory and EIF algorithm and provides an effective basis for the EIF-based anomaly detection method by removing redundant attributes with rough set theory. Experimental results show that the RS-EIF algorithm performs better than the iForest and EIF algorithms in terms of anomaly detection rate, and the results of the combination of rough set theory and EIF are more prominent compared to the other combination methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Graph Sequence Generator and Multi-head Self-attention Mechanism based Knowledge Graph Reasoning Architecture

A Graph Sequence Generator and Multi-head Self-attention Mec...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Yuejia Wu Jian-Tao Zhou College of Computer Science Inner Mongolia University National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Ministry of Education Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

Knowledge Graph (KG) is an essential research direction that involves storing and managing knowledge data, but its incompleteness and sparsity hinder its development in various applications. Knowledge Graph Reasoning (KGR) is an effective method to solve this limitation via reasoning missing knowledge based on existing knowledge. The graph Convolution Network (GCN) based method is one of the state-of-the-art approaches to this work. However, there are still some problems, such as the insufficient ability to perceive graph structure and the poor effect of learning data features which may limit the reasoning accuracy. This paper proposes a KGR architecture based on a graph sequence generator and multi-head self-attention mechanism, named GaM-KGR, to improve the above problems and enhance prediction accuracy. Specifically, the GaM-KGR first introduces the graph generation model into the field of KGR for graph representation learning to obtain the hidden features in the data so that enhancing the reasoning effect and then embeds the generated graph sequence into the multi-head self-attention mechanism for subsequent processing to improve the graph structure perception ability of the proposed architecture, so that it can process the graph structure data more appropriately. Extensive experimental results show that the GaM-KGR architecture can achieve the state-of-the-art prediction results of current GCN-based models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Multi-Cloud data Storage System Disaster Recovery

Blockchain-Based Multi-Cloud Data Storage System Disaster Re...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Feiyu Wang Jian-tao Zhou College of Computer Science Inner Mongolia University Hohhot Inner Mongolia China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Engineering Research Center of Ecological Big Data Ministry of Education National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian China

Cloud storage services have been used by most businesses and individual users. However, data loss, service interruptions and cyber attacks often lead to cloud storage services not being provided properly, and these incidents have caused financial losses to users. Second, traditional and single-cloud model disaster recovery services are no longer suitable for the current complex cloud storage systems. Therefore, a scheme to provide disaster recovery for cloud storage services in a multi-cloud storage environment is needed in real production. In this paper, we propose a disaster recovery scheme based on blockchain technology. The proposed scheme outlined in this study aims to address the issue of data availability within the cloud storage landscape. The proposed scheme achieves this goal by dividing data into hot and cold categories, verifying the integrity of copy data via blockchain technology, and utilizing blockchain networks to manage multi-cloud storage systems. Experimental findings demonstrate that the proposed scheme yields superior results in terms of computation and time overheads.

关键词：

来源：评论

学校读者我要写书评

暂无评论

VMeta: A QoS dataset for Metaverse Services 6th

VMeta: A QoS Dataset for Metaverse Services

引用

6th International Conference on Blockchain and Trustworthy Systems, BlockSys 2024

作者： Ge, Zhiyuan Jin, Huiying Dong, Hai Ji, Shunhui Li, Jiajia Yang, Shuhan Wang, Qi Zhang, Pengcheng Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing210000 China College of Computer Science and Software Engineering Hohai University Nanjing210000 China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210000 China School of Computing Technologies RMIT University Melbourne3000 Australia

ISBN: (纸本)9789819614134

The metaverse is undergoing repaid evolution with metaverse services emerging as a significant focal point of research across virtual reality, augmented reality, and metaverse social networking. However, a key challenge lies in the scarcity of datasets that accurately represent metaverse services, impeding the advancement of metaverse service technologies and applications. To address this challenge, we have categorized metaverse services into virtual scene services and meta-services. Subsequently, we introduced a metaverse service dataset called "VMeta". VMeta encompasses comprehensive information about virtual scene services and meta-services, including essential QoS (Quality of Service) data. This dataset serves as a valuable resource for researchers exploring various aspects of metaverse services, with the ultimate goal of enhancing user satisfaction in the metaverse. We have conducted evaluations and tests on VMeta to optimize metaverse QoS. The results demonstrate its substantial value for metaverse service research. Our datasets are available at https://***/Gelieziman/VMeta. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

An Uncovered Neurons Information-Based Fuzzing Method for DNN

An Uncovered Neurons Information-Based Fuzzing Method for DN...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Kecheng Tang Jian-Tao Zhou Xu Guo College of Computer Science Inner Mongolia University Hohhot China National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China Engineering Research Center of Ecological Big Data Ministry of Education Hohhot China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Hohhot China Inner Mongolia Key Laboratory of Social Computing and Data Processing Hohhot China Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Hohhot China Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Fuzzing is increasingly being utilized as a method to test the reliability of Deep Learning (DL) systems. In order to detect more errors in DL systems, exploring the internal logic of more DNNs has become the main objective of fuzzing. Despite advancements in the seed selection aspect of fuzzing, considerable opportunities still exist for improving testing efficiency. Current research has issues with the repeated consideration of neurons in the model that will be covered in the future by other seeds, leading to redundant seeds and lower testing efficiency. Additionally, there is a lack of a method to measure the potential of seeds to increase coverage, making it difficult to select the most worthy seeds for mutation in each iteration. We propose an uncovered neurons information based (UNIB) fuzzing method for DNN. UNIB uses clustering methods to organize the seed queue based on initial seed data, aiming to enhance the coverage rate improved in each iteration. It also integrates coverage information from the testing phase to identify the seeds with the greatest potential. The experimental results show that UNIB achieved a higher NC than the second-best method by 1.1% and 3% in LetNet-4 and LetNet-5, respectively. UNIB consistently required the fewest number of iterations to reach the same NC as other methods. For both LetNet-4 and LetNet-5, the adversarial test case sets generated by UNIB exhibited the highest diversity.

关键词： Deep learning Federated learning Current measurement Neurons Neural networks Fuzzing software

来源：评论

学校读者我要写书评

暂无评论

BMDP:Blockchain-Based Multi-Cloud Storage data Provenance

BMDP:Blockchain-Based Multi-Cloud Storage Data Provenance

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Feiyu Wang Jian-Tao Zhou Xu Guo College of Computer Science Inner Mongolia University Hohhot Inner Mongolia China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Engineering Research Center of Ecological Big Data Ministry of Education National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Engineering Laboratory for Big Data Analysis Technology China

In a multi-cloud storage system, provenance data records all operations and ownership during its lifecycle, which is critical for data security and audibility. However, recording provenance data also poses some challenging security and storage issues. In this paper, we present a secure and efficient multi-cloud storage data source scheme, BMDP. We use blockchain technology to ensure the secure storage of provenance data and design a smart contract to utilize the provenance data to ensure the proper operation of the multi-cloud storage system. Finally, we analyze the scheme’s safety and do simulation experiments to show that the scheme has practicality.

关键词：

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：