检索结果-内蒙古大学图书馆

Optimisation of sparse deep autoencoders for dynamic network embedding

CAAI Transactions on Intelligence technology 2024年第6期9卷 1361-1376页

作者： Huimei Tang Yutao Zhang Lijia Ma Qiuzhen Lin Liping Huang Jianqiang Li Maoguo Gong College of Computer Science and Software Engineering Shenzhen UniversityShenzhenChina Institute for Infocomm Research Agency for Science Technology and ResearchSingaporeSingapore Key Laboratory of Collaborative Intelligence Systems Ministry of EducationXidian UniversityXi'anChina

Network embedding(NE)tries to learn the potential properties of complex networks represented in a low-dimensional feature ***,the existing deep learningbased NE methods are time-consuming as they need to train a dense architecture for deep neural networks with extensive unknown weight parameters.A sparse deep autoencoder(called SPDNE)for dynamic NE is proposed,aiming to learn the network structures while preserving the node evolution with a low computational *** tries to use an optimal sparse architecture to replace the fully connected architecture in the deep autoencoder while maintaining the performance of these models in the dynamic ***,an adaptive simulated algorithm to find the optimal sparse architecture for the deep autoencoder is *** performance of SPDNE over three dynamical NE models(*** architecture-based deep autoencoder method,DynGEM,and ElvDNE)is evaluated on three well-known benchmark networks and five real-world *** experimental results demonstrate that SPDNE can reduce about 70%of weight parameters of the architecture for the deep autoencoder during the training process while preserving the performance of these dynamical NE *** results also show that SPDNE achieves the highest accuracy on 72 out of 96 edge prediction and network reconstruction tasks compared with the state-of-the-art dynamical NE algorithms.

关键词： deep autoencoder dynamic networks low-dimensional feature space network embedding sparse structure

来源：评论

学校读者我要写书评

暂无评论

Credit assignment for trained neural networks based on Koopman operator theory

引用

Frontiers of computer Science 2024年第1期18卷 251-253页

作者： Zhen LIANG Changyuan ZHAO Wanwei LIU Bai XUE Wenjing YANG Zhengbin PANG Institute for Quantum Information&State Key Laboratory of High Performance Computing National University of Defense TechnologyChangsha 410000China Institute of Software Chinese Academy of SciencesBeijing 100190China College of Computer Science and Technology National University of Defense TechnologyChangsha 410000China

1 Introduction Artificial neural networks(ANNs,also NNs)have recently emerged as leading candidate models for deep learning,popularly used in various areas[1–3].Behind the enormous success,ANNs are generally with complicated structures,there being an intricate data flow through multiple linear or nonlinear components between the input layer and the output ***,it is pressing to evaluate how much a specific component contributes to the final output,termed the Credit Assignment Problem(CAP)[4]in this paper.

关键词： layer assignment operator

来源：评论

学校读者我要写书评

暂无评论

SAT-based Formal Verification of Fault Injection Countermeasures for Cryptographic Circuits∗

IACR Transactions on Cryptographic Hardware and Embedded Sys...

引用

IACR Transactions on Cryptographic Hardware and Embedded Systems 2024年第4期2024卷 1-39页

作者： Tan, Huiyu Gao, Pengfei Song, Fu Chen, Taolue Wu, Zhilin ShanghaiTech University Shanghai201210 China Wingsemi Technology Co. Ltd. Shanghai201203 China Bytedance Beijing100098 China Key Laboratory of System Software Chinese Academy of Sciences and State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing100190 China Nanjing Institute of Software Technology Nanjing211135 China Birkbeck University of London WC1E 7HX United Kingdom

Fault injection attacks represent a type of active, physical attack against cryptographic circuits. Various countermeasures have been proposed to thwart such attacks, however, the design and implementation of which are intricate, error-prone, and laborious. The current formal fault-resistance verification approaches are limited in efficiency and scalability. In this paper, we formalize the fault-resistance verification problem and show that it is coNP-complete. We then devise a novel approach for encoding the fault-resistance verification problem as the Boolean satisfiability (SAT) problem so that modern off-the-shelf SAT solvers can be utilized. The approach is implemented in an open-source tool FIRMER which is evaluated extensively on realistic cryptographic circuit benchmarks. The experimental results show that FIRMER is able to verify fault-resistance of almost all (72/76) benchmarks in 3 minutes (the other three are verified in 35 minutes and the hardest one is verified in 4 hours). In contrast, the prior approach fails on 31 fault-resistance verification tasks even after 24 hours (per task). © 2024, Ruhr-University of Bochum. All rights reserved.

关键词： Formal verification

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cervical Segmentation via Alternate Diverse Teaching in Semi-Supervised Learning 22

Enhancing Cervical Segmentation via Alternate Diverse Teachi...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Yu, Jiawei College of Computer Science National University of Defense Technology Changsha China State Key Laboratory of Complex & Critical Software Environment Changsha China

ISBN: (纸本)9798331520526

In clinical practice, the cervical structure plays a critical role in predicting preterm birth, thus making accurate segmentation of this structure in ultrasound images of paramount importance. However, the performance of existing deep learning methods is limited by the high cost of labeling ultrasound images. In this context, semi-supervised medical image segmentation techniques have emerged as promising solutions, particularly recent teacher-student frameworks that have demonstrated notable efficacy. Despite their success, these methods are often subject to confirmation bias, which undermines their reliability. To address this issue, we introduce a novel approach, Alternate Diverse Teaching (AD-MT), for the semi-supervised segmentation of cervical ultrasound images. AD-MT enhances model performance by alternately updating two teacher models, offering diverse perspectives during learning. Furthermore, a conftict-combating module is incorporated to ensure that the model learns from the discrepancies between teacher predictions. This methodology effectively harnesses both labeled and unlabeled data for segmentation tasks. Experimental results demonstrate that AD-MT achieves competitive segmentation performance, as evidenced by its strong showing in the ISBI 2025 Fetal Ultrasound Grand Challenge. © 2025 IEEE.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Multi-scale convolutional fusion network embedded with improved attention mechanism for polarimetric synthetic aperture radar image classification

引用

Journal of Applied Remote Sensing 2025年第1期19卷

作者： Li, Jiewen Zhu, Yanan Ai, Jiaqiu Zhao, Zhicheng Shi, Jun Hefei University of Technology School of Computer Science and Information Engineering Hefei China Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province Hefei China Hefei University of Technology School of Artificial Intelligence Hefei China Hefei University of Technology School of Software Hefei China

Convolutional neural networks (CNNs) have been widely applied in the field of polarimetric synthetic aperture radar (PolSAR) image classification and have achieved good classification results. However, due to the complexity of polarimetric information, traditional CNN structures are difficult to fully extract and integrate information from multiple polarimetric channels, resulting in insufficient feature diversity, which limits further improvement in classification accuracy. To this problem, this article proposes a multi-scale convolutional fusion network (MCF-Net). MCF-Net employs convolutional kernels of various sizes to perform parallel convolutions, extracting multi-scale features and optimally fusing them, thereby greatly enhancing the diversity and completeness of feature representation. In addition, to enhance the network's focus on important features and suppress irrelevant information, this article proposes an improved squeeze-and-excitation (SE) module, guided by mean, entropy, and Z-score (MEZ-SE), to weigh the importance of feature maps. By embedding the MEZ-SE module into MCF-Net, MEZ-MCF-Net significantly improves the completeness of feature representation and enhances the ability to distinguish different land cover categories. On the Flevoland, San Francisco, and Oberfaffenhofen PolSAR datasets, the overall accuracy of MEZ-MCF-Net exceeds that of the second-best method by 3.04%, 2.09%, and 1.99%, respectively. There is no doubt that MEZ-MCF-Net is an effective method for PolSAR image classification. © 2025 Society of Photo-Optical Instrumentation Engineers (SPIE).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based conditional privacy-preserving authentication scheme for vehicular ad hoc networks

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第5期14卷 6273-6286页

作者： Gong, Cheng Xiong, Ling He, Xingyu Niu, Xianhua College of Computer and Software Engineering Xihua University Sichuan Chengdu610099 China National Key Laboratory of Science and Technology Communications University of Electronic Science and Technology of China Sichuan Chengdu611731 China

Security and privacy are two challenging issues in Vehicular Ad-hoc Networks (VANETs), which have attracted widespread concern from industry and academia. However, the existing security schemes for VANETs environment have various problems, such as the unlinkability and the cross region communication,etc. To overcome these weaknesses, this paper designs a blockchain-based conditional privacy-preserving authentication scheme (BCPAS) for VANETs. The proposed scheme has the following two advantages: (1) Pseudonym ID is employed in authentication phase to ensure the real identity of vehicle is unlinkable. (2) Blockchain technology is adopted to make cross-region authentication more efficient. Compared with the most recent scheme, the computational efficiency of our scheme has improved 50% with 3 service management nodes, and 87% with 15 service management nodes in the Authentication and Member Secrets Generate Phase. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

FedHPM: Online Federated Learning via Heterogeneous Prediction Model 22

FedHPM: Online Federated Learning via Heterogeneous Predicti...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Zhang, Zhi Zhang, Shiwen Chen, Shuang Liang, Wei Hunan University of Science and Technology College of Computer Science and Technology Xiangtan China Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology School of Computer Science and Engineering Xiangtan411201 China

ISBN: (纸本)9798331509712

In the era of big data and growing privacy concerns, Federated Learning (FL) has emerged as a promising solution for collaborative model training while preserving user data privacy. However, FL faces challenges such as inconsistent data quality and frequent client dropouts, which hinder its performance. To address these challenges, we propose FedHPM, a novel framework that leverages the predictive capabilities of Long Short-Term Memory (LSTM) networks. FedHPM incorporates an intelligent client selection mechanism that utilizes LSTM-based analysis of historical data to forecast clients' potential data quality and dropout likelihood. This mechanism enables efficient selection of the top best-performing clients for participation in each round of global model training. By mitigating the impact of dropouts and optimizing the composition of participating clients, FedHPM significantly improves both the convergence speed and final performance of the global model. Through extensive empirical evaluations, we demonstrate the superior performance of FedHPM in enhancing FL stability, accelerating the convergence rate, and maintaining model accuracy. The results highlight the effectiveness of our framework in addressing the challenges associated with data quality and dropouts, thereby advancing the field of federated learning. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Constraint-aware and multi-objective optimization for micro-service composition in mobile edge computing

Constraint-aware and multi-objective optimization for micro-...

引用

作者： Wu, Jintao Zhang, Jingyi Zhang, Yiwen Wen, Yiping School of Software Nanjing University of Information Science and Technology Nanjing China School of Computer Science and Technology Anhui University Anhui China Hunan Key Laboratory for Service Computing and Novel Software Technology Hunan University of Science and Technology Hunan China

As a new paradigm of distributed computing, mobile edge computing (MEC) has gained increasing attention due to its ability to expand the capabilities of centralized cloud computing. In MEC environments, a software application typically consists of multiple micro-services, which can be composed together in a flexible manner to achieve various user requests. However, the composition of micro-services in MEC is still a challenging research issue arising from three aspects. Firstly, composite micro-services constructed by ignoring the processing capabilities of different micro-services may cause waste of edge resources. Secondly, edge servers' limitations in terms of computational power can easily cause service occupancy between composite micro-services, severely affecting the user experience. Thirdly, in dynamic and unstable mobile environments, different edge users have different sensitivities to request latency, which increases the complexity of micro-service composition. In order to improve edge resource utilization and user experience on micro-service invocations, in this paper, we comprehensively consider the above three factors, and we first model the micro-services composition problem in MEC as a constrained multi-objective optimization problem. Then, a micro-service composition optimization method M3C combining graph search and branch-and-bound strategy is proposed to find a composition solution set with low energy consumption and high success rate for multiple edge users. Finally, we perform a series of experiments on two widely used datasets. Experimental results show that our proposed approach significantly outperforms the four competing baseline approaches, and that it is sufficiently efficient for practical deployment. © 2023 John Wiley & Sons Ltd.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

RandoMix: a mixed sample data augmentation method with multiple mixed modes

引用

Multimedia Tools and Applications 2025年第8期84卷 4343-4359页

作者： Liu, Xiaoliang Shen, Furao Zhao, Jian Nie, Changhai National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China School of Artificial Intelligence Nanjing University Nanjing China School of Electronic Science and Engineering Nanjing University Nanjing China

Data augmentation plays a crucial role in enhancing the robustness and performance of machine learning models across various domains. In this study, we introduce a novel mixed-sample data augmentation method called RandoMix. RandoMix is specifically designed to simultaneously address robustness and diversity challenges. It leverages a combination of linear and mask mixed modes, introducing flexibility in candidate selection and weight adjustments. We evaluate the effectiveness of RandoMix on diverse datasets, including CIFAR-10/100, Tiny-ImageNet, ImageNet, and Google Speech Commands. Our results demonstrate its superior erformance compared to existing techniques such as Mixup, CutMix, Fmix, and ResizeMix. Notably, RandoMix excels in enhancing model robustness against adversarial noise, natural noise, and sample occlusion. The comprehensive experimental results and insights into parameter tuning underscore the potential of RandoMix as a versatile and effective data augmentation method. Moreover, it seamlessly integrates into the training pipeline. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Data augmentation Diversity Mixed-sample RandoMix Robustness

来源：评论

学校读者我要写书评

暂无评论

Unsupervised image-to-image translation by semantics consistency and self-attention

引用

Optoelectronics Letters 2022年第3期18卷 175-180页

作者： ZHANG Zhibin XUE Wanli FU Guokai The Key Laboratory of Computer Vision and System of Ministry of Education Tianjin Key Laboratory of Intelligence Computing and Novel Software TechnologyTianjin University of TechnologyTianjin 300384China

Unsupervised image-to-image translation is a challenging task for computer vision. The goal of image translation is to learn a mapping between two domains, without corresponding image pairs. Many previous works only focused on image-level translation but ignored image features processing, which led to a certain semantics loss, such as the changes of the background of the generated image, partial transformation, and so on. In this work, we propose a method of image-to-image translation based on generative adversarial nets(GANs). We use autoencoder structure to extract image features in the generator and add semantic consistency loss on extracted features to maintain the semantic consistency of the generated image. Self-attention mechanism at the end of generator is used to obtain long-distance dependency in image. At the same time, as expanding the convolution receptive field, the quality of the generated image is enhanced. Quantitative experiment shows that our method significantly outperforms previous works. Especially on images with obvious foreground, our model shows an impressive improvement.

关键词： translation features semantic

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：