检索结果-内蒙古大学图书馆

19th CCF conference on Computer Supported Cooperative Work and Social Computing, ChineseCSCW 2024

作者： Liang, Yuting Cai, Weixin Guo, Kun College of Computer and Data Science Fuzhou University Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350108 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China

ISBN: (纸本)9789819623723

Graphs widely exist in real-world, and Graph neural networks (GNNs) have exhibited exceptional efficacy in graph learning in diverse fields. With the strengthening of data privacy protection worldwide in recent years, Federated graph neural networks (FedGNNs) have gained increasing attention in academia and industry owing to their ability to train the model in a collaborative manner while complying with the privacy protection regulations. However, in federated learning, the non-independent and identically distributed (non-IID) problem of local data possessed by multiple participants can significantly undermine model accuracy. We propose a new Decentralized Federated Graph Normalized AutoEncoder (D-FGNAE). First, the model is designed as a decentralized federated learning framework with dynamically assigned tripartite roles. This design eliminates the fixed server role found in traditional federated learning, enhances system fault tolerance, avoids single points of failure, and protects model privacy. Second, the splitting and correcting of calculation by layer in the model, along with the special design of the normalization layer, effectively tackle the non-IID problem in both the structural and attribute aspects. Experimental results on real-world networks demonstrate the effectiveness of D-FGNAE, which can achieve nearly the same accuracy as the centralized model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

BGElasor: Elastic-Scaling Framework for distributed Streaming processing with Deep neural network 16th

BGElasor: Elastic-Scaling Framework for Distributed Streamin...

引用

16th IFIP WG 10.3 International conference on network and Parallel Computing, NPC 2019

作者： Mu, Weimin Jin, Zongze Wang, Junwei Zhu, Weilin Wang, Weiping Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783030307080

In face of constant fluctuations and sudden bursts of data stream, elasticity of distributed stream processing system has become increasingly important. The proactive policy offers a powerful means to realize the effective elastic scaling. The existing methods lack the latent features of data stream, it leads the poor prediction. Furthermore, the poor prediction results in the high cost of adaptation and the instability. To address these issues, we propose the framework named BGElasor, which is a proactive and low-cost elastic-scaling framework based on the accurate prediction using deep neural networks. It can capture the potentially-complicated pattern to enhance the accuracy of prediction, reduce the cost of adaptation and avoid adaptation bumps. The experimental results show that BGElasor not only improves the prediction accuracy with three kinds of typical loads, but also ensure the end-to-end latency on QoS with low cost. © 2019, IFIP International Federation for Information processing.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

LEARNING IN PARALLEL distributed-processing networkS - COMPUTATIONAL-COMPLEXITY AND INFORMATION-CONTENT

引用

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS 1991年第2期21卷 359-367页

作者： KOLEN, JF GOEL, AK GEORGIA INST TECHNOL COLL COMPSCH INFORMAT & COMP SCIARTIFICIAL INTELLIGENCE & COGNIT SCI GRPATLANTAGA 30332

neural networks offer an intriguing set of techniques for learning based on the adjustment of weights of connections between processing units. However, the power and limitations of connectionist methods for learning, such as the method of back propagation in parallel distributed processing networks, are not yet entirely clear. A set of experiments that more precisely identify the power and limitations of the method of back propagation is reported on. The experiment on learning to compute the exclusive-or function suggests that the computational efficiency of learning by the method of back propagation depends on the initial weights in the network. The experiment on learning to play tic-tac-toe suggests that the information content of what is learned by the back propagation method is dependent on the initial abstractions in the network. It also suggests that these abstractions are a major source of power for learning in parallel distributed processing networks. In addition, it is shown that the learning task addressed by connectionist methods, including the back propagation method, is computationally intractable. These experimental and theoretical results strongly indicate that current connectionist methods may be too limited for the complex task of learning they seek to solve. It is proposed that the power of neural networks may be enhanced by developing task-specific connectionist methods.

关键词： distributed processing Electric Power Source back propagation Learning complexity classes Computational efficiency Energy sources network weighted network

来源：评论

学校读者我要写书评

暂无评论

New Results on Exponential Convergence for Cellular neural networks with Continuously distributed Leakage Delays

引用

neural processing LETTERS 2015年第3期41卷 421-433页

作者： Zhang, Aiping Hunan Univ Technol Sch Sci Zhuzhou 412000 Hunan Peoples R China

This paper discusses the issue of a class of cellular neural networks with continuously distributed delays in the leakage terms. By applying Lyapunov functional method and differential inequality techniques, without assuming the boundedness conditions on the activation functions, a new delay dependent sufficient condition is derived to ensure that all solutions of the networks converge exponentially to the zero point, which corrects some recent results of Xiong and Meng (Electron J Qual Theory Differ Equ, (10):1-12, ***://***/ejqtde/).

关键词： Cellular neural network Exponential convergence Continuously distributed delay Leakage term

来源：评论

学校读者我要写书评

暂无评论

Selection of Deep neural network Models for IoT Anomaly Detection Experiments 29

Selection of Deep Neural Network Models for IoT Anomaly Dete...

引用

29th Euromicro International conference on Parallel, distributed and network-Based processing (PDP)

作者： Gaifulina, Diana Kotenko, Igor Russian Acad Sci Russian Acad Sci SPC RAS St Petersburg Inst Informat & Automat St Petersburg Fed Res Ctr 14th Liniya St Petersburg Russia

ISBN: (纸本)9781665414555

This research is about selection of deep neural network models for anomaly detection in Internet of Things network traffic. We are experimentally evaluating deep neural network models using the same software, hardware and the same subsets of the UNSW-NB 15 dataset for training and testing. The assessment results are quality metrics of anomaly detection and the time spent on training models.

关键词： deepp learning deep neural networks anomaly detection Internet of Things information security

来源：评论

学校读者我要写书评

暂无评论

Implementation of Bayesian inference in distributed neural networks 26

Implementation of Bayesian inference in distributed neural n...

引用

26th Euromicro International conference on Parallel, distributed, and network-Based processing (PDP)

作者： Yu, Zhaofei Hang, Tiejun Liu, Jian K. Peking Univ Sch Elect Engn & Comp Sci Beijing Peoples R China Graz Univ Technol Inst Theoret Comp Sci Graz Austria

ISBN: (纸本)9781538649756

Numerous neuroscience experiments have suggested that the cognitive process of human brain is realized as probability reasoning and further modeled as Bayesian inference. It is still unclear how Bayesian inference could be implemented by neural underpinnings in the brain. Here we present a novel Bayesian inference algorithm based on importance sampling. By distributed sampling through a deep tree structure with simple and stackable basic motifs for any given neural circuit, one can perform local inference while guaranteeing the accuracy of global inference. We show that these task-independent motifs can be used in parallel for fast inference without iteration and scale-limitation. Furthermore, experimental simulations with a small-scale neural network demonstrate that our distributed sampling-based algorithm, consisting with our theoretical analysis, can approximate Bayesian inference. Taken all together, we provide a proof-of-principle to use distributed neural networks to implement Bayesian inference, which gives a road-map for large-scale Bayesian network implementation based on spiking neural networks with computer hardwares, including neuromorphic chips.

关键词： Bayesian inference distributed neural network importance sampling neural implementation

来源：评论

学校读者我要写书评

暂无评论

distributed LARGE neural network WITH CENTRALIZED EQUIVALENCE

DISTRIBUTED LARGE NEURAL NETWORK WITH CENTRALIZED EQUIVALENC...

引用

IEEE International conference on Acoustics, Speech and Signal processing (ICASSP)

作者： Liang, Xinyue Javid, Alireza M. Skoglund, Mikael Chatterjee, Saikat KTH Royal Inst Technol Sch Elect Engn Dept Informat Sci & Engn Stockholm Sweden

ISBN: (纸本)9781538646588

In this article, we develop a distributed algorithm for learning a large neural network that is deep and wide. We consider a scenario where the training dataset is not available in a single processing node, but distributed among several nodes. We show that a recently proposed large neural network architecture called progressive learning network (PLN) can be trained in a distributed setup with centralized equivalence. That means we would get the same result if the data be available in a single node. Using a distributed convex optimization method called alternating-direction-method-of-multipliers (ADMM), we perform training of PLN in the distributed setup.

关键词： distributed learning neural networks data parallelism convex optimization

来源：评论

学校读者我要写书评

暂无评论

Analysis of Effective E-Commerce Coordination Big Data processing Strategies under Infinite Deep neural network Topology

Analysis of Effective E-Commerce Coordination Big Data Proce...

引用

Asia-Pacific conference on Communications Technology and Computer Science (ACCTCS)

作者： Zhang, Ailing Yao, Fuxiao Shandong Vocat & Tech Univ Int Studies Rizhao 276800 Shandong Peoples R China

ISBN: (纸本)9781728176499

This paper researches and analyses the effective e-commerce coordination big data processing strategy through the infinite-depth neural network topology. This paper firstly proposes a neural network training model neural network-Storm (NN-S) based on Storm streaming distributed architecture, which decomposes the neural network training task into multiple computing units by data-parallel method, the parameters are updated synchronously after the training of a single batch of data is completed. In the Storm architecture, a Zookeeper network is used for multi-server distributed deployment. The training results show that the NN-S model can significantly improve the training speed of neural networks. At the same time, the NN-S architecture can quickly recover from node failures and network resource scheduling abnormalities with strong robustness. In this paper, we investigate the streaming-based distributed neural network training and design a Storm-based distributed neural network training model and optimized training algorithms, which are of reference significance for distributed neural network training.

关键词： infinite depth neural network topology effective e-conunerce coordination big data processing strategy analysis

来源：评论

学校读者我要写书评

暂无评论

Performance and Scalability of GPU-based Convolutional neural networks

Performance and Scalability of GPU-based Convolutional Neura...

引用

18th Euromicro International conference on Parallel, distributed and network-Based processing (PDP)

作者： Strigl, Daniel Kofler, Klaus Podlipnig, Stefan Univ Innsbruck Inst Comp Sci Distributed & Parallel Syst Grp Technikerstr 21a A-6020 Innsbruck Austria

ISBN: (纸本)9780769539393

In this paper we present the implementation of a framework for accelerating training and classification of arbitrary Convolutional neural networks (CNNs) on the GPU. CNNs are a derivative of standard Multilayer Perceptron (MLP) neural networks optimized for two-dimensional pattern recognition problems such as Optical Character Recognition (OCR) or face detection. We describe the basic parts of a CNN and demonstrate the performance and scalability improvement that can be achieved by shifting the computation-intensive tasks of a CNN to the GPU. Depending on the network topology training and classification on the GPU performs 2 to 24 times faster than on the CPU. Furthermore, the GPU version scales much better than the CPU implementation with respect to the network size.

关键词： machine learning convolutional neural networks GPGPU CUDA performance scalability

来源：评论

学校读者我要写书评

暂无评论

Reducing Feed-Forward neural network processing Time Utilizing Matrix Multiplication Algorithms on Heterogeneous distributed Systems

Reducing Feed-Forward Neural Network Processing Time Utilizi...

引用

International conference on Computational Intelligence, Communication Systems and networks, CICSYN

作者： Ali Kattan Rosni Abdullah Rosalina Abdul Salam School of Computer Science Universiti Sains Islam Malaysia Penang Malaysia School of Computer Science Universiti Sains Malaysia Penang Malaysia

This paper presents a work in progress that aims to reduce the overall training and processing time of feed-forward multi-layer neural networks. If the network is large processing is expensive in terms of both; time and space. In this paper, we suggest a cost-effective and presumably a faster processing technique by utilizing a heterogeneous distributed system composed of a set of commodity computers connected by a local area network. neural network computations can be viewed as a set of matrix multiplication processes. These can be adapted to utilize the existing matrix multiplication algorithms tailored for such systems. With Java technology as an implementation means, we discuss the different factors that should be considered in order to achieve this goal highlighting some issues that might affect such a proposed implementation.

关键词： Feedforward systems neural networks Feedforward neural networks Artificial neural networks Hardware Computer networks Parallel processing distributed computing Computational modeling Computational intelligence

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：