检索结果-内蒙古大学图书馆

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Ma, Wenqiang Hau, Yaqing Yu, Hua Tong, Xiangrong Zhu, Zexuan Zhang, Qiang School of Computer Science and Technology Dalian University of Technology Dalian116024 China School of Computer and Control Engineering Yantai University Yantai264005 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

ISBN: (纸本)9798350308365

Deep neural networks are powerful and popular learning models;however, recent studies have shown that deep neural network-based policies are susceptible to deception by adversarial attacks. A minimalistic attack is a specialized form of adversarial attack that aims to accomplish successful attacks at the lowest possible cost. Recently, transfer optimization algorithms have been applied to deceive previously trained policies by acquiring knowledge from previously solved tasks. Experiments indicate that the transfer optimization algorithms perform well compared to traditional optimization algorithms. However, current transfer algorithms for addressing minimalistic attacks not only select a single source task for knowledge transfer but also tend to overly rely on identified appropriate source tasks. To address this issue, this paper introduces a similar locality based transfer evolutionary optimization algorithm. It can adaptively select multiple source tasks and extract valuable knowledge from these source tasks. Moreover, by leveraging the concept of similar locality, the algorithm alleviates its excessive dependence on familiar tasks, thereby providing fresh knowledge for the optimization of the target task. On this basis, the algorithm can mine more valuable knowledge from the large source task space to achieve a successful attack in a shorter period. The algorithm is tested on three Atari games-BeamRider, Qbert, and Seaquest-demonstrating its ability and potential to outperform other transfer optimization algorithms currently available in solving this problem. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-Optimiser Training for GANs Based on Evolutionary Computation 13

Multi-Optimiser Training for GANs Based on Evolutionary Comp...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Zhang, Yixia Xue, Yu Neri, Ferrante School of Software Nanjing University of Information Science and Technology Nanjing China School of Computer Science and Electronic Engineering University of Surrey Guildford United Kingdom

ISBN: (纸本)9798350308365

Generative adversarial networks (GANs) are widely recognized for their impressive ability to generate realistic data. Despite the popularity of GANs, training them poses challenges such as mode collapse and instability. To address these issues, many variants enhance GAN performance through improvements in network architecture, modifications to loss functions, and the inclusion of regularization techniques. However, a limited number of methods focuses on optimising GAN performance from the optimiser's perspective, despite the distinct roles different optimisers play in training. Existing GANs typically employ a single optimiser throughout, with Adam being the default choice for GAN training. Approaches using multiple optimisers have shown improved performance but are often task-specific. This paper introduces a novel, portable approach that lever-ages the strengths of multiple training methods, with an evolutionary supervisor coordinating the training of different sections of the network. Initially, real-number-encoded vectors representing the optimiser for each sub-parameter layer undergo pro-gressive enhancement using a standard evolutionary algorithm (SGA). Through the evolutionary process, optimal optimiser combinations are retained based on the performance of the trained GAN. The proposed method, SGA-GANs, is validated on the CIFAR10 dataset by integrating the steps into five benchmark GAN models: GAN, DCGAN, BEGAN, WGAN, and WGAN-GP. Experimental results demonstrate that SGA-GANs outperforms single optimiser training methods, achieving superior evaluation results and generating higher-quality images. Source code can be found at https://***/lizzhang-spec/SGA-GANs. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Region-adaptive Concept Aggregation for Few-shot Visual Recognition

引用

Machine Intelligence Research 2023年第4期20卷 554-568页

作者： Mengya Han Yibing Zhan Baosheng Yu Yong Luo Han Hu Bo Du Yonggang Wen Dacheng Tao School of Computer Science National Engineering Research Center for Multimedia SoftwareWuhan UniversityWuhan430072China Hubei Luojia Laboratory Wuhan430072China School of Computer Science The University of SydneySydney2006Australia JD Explore Academy Beijing101116China School of Information and Electronics Beijing Institute of TechnologyBeijing100081China School of Computer Science and Engineering Nanyang Technological UniversitySingapore639798Singapore

Few-shot learning (FSL) aims to learn novel concepts from very limited examples. However, most FSL methods suffer from the issue of lacking robustness in concept learning. Specifically, existing FSL methods usually ignore the diversity of region contents that may contain concept-irrelevant information such as the background, which would introduce bias/noise and degrade the performance of conceptual representation learning. To address the above-mentioned issue, we propose a novel metric-based FSL method termed region-adaptive concept aggregation network or RCA-Net. Specifically, we devise a region-adaptive concept aggregator (RCA) to model the relationships of different regions and capture the conceptual information in different regions, which are then integrated in a weighted average manner to obtain the conceptual representation. Consequently, robust concept learning can be achieved by focusing more on the concept-relevant information and less on the conceptual-irrelevant information. We perform extensive experiments on three popular visual recognition benchmarks to demonstrate the superiority of RCA-Net for robust few-shot learning. In particular, on the Caltech-UCSD Birds-200-2011 (CUB200) dataset, the proposed RCA-Net significantly improves 1-shot accuracy from 74.76% to 78.03% and 5-shot accuracy from 86.84% to 89.83% compared with the most competitive counterpart.

关键词： Few-shot learning metric-based meta learning concept learning region-adaptive concept-aggregation

来源：评论

学校读者我要写书评

暂无评论

Applying blockchain-based method to smart contract classification for CPS applications

引用

Digital Communications and Networks 2022年第6期8卷 964-975页

作者： Zigui Jiang Kai Chen Hailin Wen Zibin Zheng School of Software Engineering Sun Yat-Sen UniversityChina School of Mathematics Sun Yat-Sen UniversityChina School of Computer Science and Engineering Sun Yat-Sen UniversityChina

Smart contract has been the core of blockchain systems and other blockchain-based systems since Blockchain *** operations on blockchain are performed through the invocation and execution of smart *** leads to extensive combinations between blockchain,smart contract,Internet of Things(IoT)and Cyber-Physical System(CPS)applications,and then many blockchain-based IoT or CPS applications emerge to provide multiple benefits to the economy and *** this case,obtaining a better understanding of smart contracts will contribute to the easier operation,higher efficiency and stronger security of those blockchain-based systems and *** existing studies on smart contract analysis are based on similarity calculation and smart contract ***,smart contract is a piece of code with special characteristics and most of smart contracts are stored without any category labels,which leads to difficulties of smart contract *** the back end of a blockchain-based Decentralized Application(DApp)is one or several smart contracts,DApps with labeled categories and open source codes are applied to achieve a supervised smart contract classification.A three-phase approach is proposed to categorize DApps based on various data *** this approach,5,659 DApps with smart contract source codes and pre-tagged categories are first obtained based on massive collected DApps and smart contracts from Ethereum,State of the DApps and *** feature extraction and construction methods are designed to form multi-feature vectors that could present the major characteristics of ***,a fused classification model consisting of KNN,XGBoost and random forests is applied to the multi-feature vectors of all DApps for performing DApp *** experimental results show that the method is *** addition,some positive correlations between feature variables and categories,as well as several user behavior patterns of DAp

关键词： Blockchain Blockchain-based application Smart contract DApP classification Solidity

来源：评论

学校读者我要写书评

暂无评论

A Survey of Edge Caching:Key Issues and Challenges

引用

Tsinghua science and Technology 2024年第3期29卷 818-842页

作者： Hanwen Li Mingtao Sun Fan Xia Xiaolong Xu Muhammad Bilal School of Computer Science Nanjing University of Information Science and TechnologyNanjing 210044China Shandong Provincial University Laboratory for Protected Horticulture Weifang University of Science and TechnologyWeifang 262700China Reading Academy Nanjing University of Information Science and TechnologyNanjing 210044China School of Software Nanjing University of Information Science and TechnologyNanjing 210044China Department of Computer Engineering Hankuk University of Foreign StudiesYongin-si 17035Republic of Korea

With the rapid development of mobile communication technology and intelligent applications,the quantity of mobile devices and data traffic in networks have been growing exponentially,which poses a great burden to networks and brings huge challenge to servicing user *** caching,which utilizes the storage and computation resources of the edge to bring resources closer to end users,is a promising way to relieve network burden and enhance user *** this paper,we aim to survey the edge caching techniques from a comprehensive and systematic *** first present an overview of edge caching,summarizing the three key issues regarding edge caching,i.e.,where,what,and how to cache,and then introducing several significant caching *** then carry out a detailed and in-depth elaboration on these three issues,which correspond to caching locations,caching objects,and caching strategies,*** particular,we innovate on the issue“what to cache”,interpreting it as the classification of the“caching objects”,which can be further classified into content cache,data cache,and service ***,we discuss several open issues and challenges of edge caching to inspire future investigations in this research area.

关键词： edge caching edge computing caching location caching object caching strategy 5G networkarchitecture Internet of Things(IoT)

来源：评论

学校读者我要写书评

暂无评论

CRAYM: Neural Field Optimization via Camera RAY Matching 38

CRAYM: Neural Field Optimization via Camera RAY Matching

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Lin, Liqiang Wu, Wenpeng Fu, Chi-Wing Zhang, Hao Huang, Hui College of Computer Science and Software Engineering Shenzhen University China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong School of Computing Science Simon Fraser University Canada

We introduce camera ray matching (CRAYM) into the joint optimization of camera poses and neural fields from multi-view images. The optimized field, referred to as a feature volume, can be "probed" by the camera rays for novel view synthesis (NVS) and 3D geometry reconstruction. One key reason for matching camera rays, instead of pixels as in prior works, is that the camera rays can be parameterized by the feature volume to carry both geometric and photometric information. Multi-view consistencies involving the camera rays and scene rendering can be naturally integrated into the joint optimization and network training, to impose physically meaningful constraints to improve the final quality of both the geometric reconstruction and photorealistic rendering. We formulate our per-ray optimization and matched ray coherence by focusing on camera rays passing through keypoints in the input images to elevate both the efficiency and accuracy of scene correspondences. Accumulated ray features along the feature volume provide a means to discount the coherence constraint amid erroneous ray matching. We demonstrate the effectiveness of CRAYM for both NVS and geometry reconstruction, over dense- or sparse-view settings, with qualitative and quantitative comparisons to state-of-the-art alternatives. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Reputation Layered Coding Based Storage Strategy for Consortium Blockchain 22

A Reputation Layered Coding Based Storage Strategy for Conso...

引用

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

作者： Li, Ziqian Pan, Maolin Yu, Yang Sun Yat-Sen University School of Computer Science and Engineering Guangzhou China Sun Yat-Sen University School of Software Engineering Zhuhai China

ISBN: (纸本)9798331509712

The improvement of consensus algorithms has greatly enhanced the performance of consortium blockchain, making it possible to be applied in large-scale network scenarios such as finance, healthcare and supply chain management. However, better performance often results in a heavier storage burden on the nodes. A storage strategy based on erasure code is a good solution, capable of reducing the storage consumption of each block to O(1). However, in large-scale consortium blockchain, this storage strategy encounters issues like poor performance and limited system dynamicity. To address the issues associated with the application of coding-based storage strategies in large-scale consortium blockchain, this paper proposes a storage strategy based on reputation-layered coding, named Level-Store. Level-Store first partitions the nodes into different storage units based on their reputations, then allocates the storage tasks of different block segments to different storage units for encoded storage. By calculating reasonable storage schemas for each storage unit, the data availability is ensured. Experiment shows that compared to existing coding-based storage strategies, Level-Store significantly improves system performance and dynamicity. It demonstrates notable advancements in key metrics such as space overhead, time consumption for storage and retrieval, the number of nodes and chunks affected by re-encoding, and the time consumption for re-encoding. Additionally, the system's security and fairness have also been enhanced. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Fusion and Decomposition Network for Single Image Deraining

引用

IEEE Transactions on Image Processing 2024年 33卷 191-204页

作者： Wang, Qiong Jiang, Kui Wang, Zheng Ren, Wenqi Zhang, Jianhui Lin, Chia-Wen Wuhan University National Engineering Research Center for Multimedia Software School of Computer Science Wuhan430072 China Sun Yat-sen University School of Cyber Science and Technology Guangzhou510275 China Hangzhou Dianzi University College of Computer Science and Technology Hangzhou310018 China National Tsing Hua University Department of Electrical Engineering The Institute of Communications Engineering Hsinchu30013 Taiwan

Convolutional neural networks (CNNs) and self-attention (SA) have demonstrated remarkable success in low-level vision tasks, such as image super-resolution, deraining, and dehazing. The former excels in acquiring local connections with translation equivariance, while the latter is better at capturing long-range dependencies. However, both CNNs and Transformers suffer from individual limitations, such as limited receptive field and weak diversity representation of CNNs during low efficiency and weak local relation learning of SA. To this end, we propose a multi-scale fusion and decomposition network (MFDNet) for rain perturbation removal, which unifies the merits of these two architectures while maintaining both effectiveness and efficiency. To achieve the decomposition and association of rain and rain-free features, we introduce an asymmetrical scheme designed as a dual-path mutual representation network that enables iterative refinement. Additionally, we incorporate high-efficiency convolutions throughout the network and use resolution rescaling to balance computational complexity with performance. Comprehensive evaluations show that the proposed approach outperforms most of the latest SOTA deraining methods and is versatile and robust in various image restoration tasks, including underwater image enhancement, image dehazing, and low-light image enhancement. The source codes and pretrained models are available at https://***/qwangg/MFDNet. © 1992-2012 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

An elastic framework construction method based on task migration in edge computing

An elastic framework construction method based on task migra...

引用

作者： Pu, Yonglin Li, Ziyang Yu, Jiong Lu, Liang Guo, Binglei School of Software Nanjing University of Information Science and Technology Nanjing China School of Software Xinjiang University Urumqi China College of Computer Science and Technology Civil Aviation University of China Tianjin China School of Computer Engineering Hubei University of Arts and Science Xiangyang China

Edge computing (EC) serves as an effective technology, empowering end-users to attain high bandwidth and low latency by offloading tasks with high computational demands from mobile devices to edge servers. However, a major challenge arises when the processing load fluctuates continuously, leading to a performance bottleneck due to the inability to rescale edge node (EN) resources. To address this problem, the approach of task migration is introduced, and EN load prediction model, the resource constrained model, optimal communication overhead model, optimal task migration model, and energy consumption model are built to form a theoretical foundation from which to propose a task migration based resilient framework construction method in EC. With the aid of the domino effect and the combined effect of task migration, a dynamic node-growing algorithm (DNGA) and a dynamic node-shrinking algorithm (DNSA), both based on the task migration strategy, are proposed. Specifically, the DNGA smoothly expands the EN scale when the processing load increases, while the DNSA shrinks the EN scale when the processing load decreases. The experimental results show that for standard benchmarks deployed on an elastic framework, the proposed method realizes a smooth scaling mechanism in the EC, which reduces the latency and improves the reliability of data processing. © 2023 John Wiley & Sons, Ltd.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph Driven Inference Testing for Question Answering software 24

Knowledge Graph Driven Inference Testing for Question Answer...

引用

44th ACM/IEEE International Conference on software engineering, ICSE 2024

作者： Wang, Jun Li, Yanhui Chen, Zhifei Chen, Lin Zhang, Xiaofang Zhou, Yuming Nanjing University State Key Laboratory for Novel Software Technology China School of Computer Science and Engineering Nanjing University of Science and Technology China School of Computer Science and Technology Soochow University China

ISBN: (纸本)9798400702174

In the wake of developments in the field of Natural Language Processing, Question Answering (QA) software has penetrated our daily lives. Due to the data-driven programming paradigm, QA software inevitably contains bugs, i.e., misbehaving in real-world applications. Current testing techniques for testing QA software include two folds, reference-based testing and metamorphic testing. This paper adopts a different angle to achieve testing for QA software: we notice that answers to questions would have inference relations, i.e., the answers to some questions could be logically inferred from the answers to other questions. If these answers on QA software do not satisfy the inference relations, an inference bug is detected. To generate the questions with the inference relations automatically, we propose a novel testing method Knowledge Graph driven Inference Testing (KGIT), which employs facts in the Knowledge Graph (KG) as the seeds to logically construct test cases containing questions and contexts with inference relations. To evaluate the effectiveness of KGIT, we conduct an extensive empirical study with more than 2.8 million test cases generated from the large-scale KG YAGO4 and three QA models based on the state-of-the-art QA model structure. The experimental results show that our method (a) could detect a considerable number of inference bugs in all three studied QA models and (b) is helpful in retraining QA models to improve their inference ability. © 2024 ACM.

关键词： Knowledge graph

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：