检索结果-内蒙古大学图书馆

Property Constrained Video Summarization via Regret Minimization

SN computer science 2024年第2期5卷 254页

作者： Xu, Yuyao Zheng, Jiping Tao, Yanxin Zhu, Kaiqin College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing 211106 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing 210023 China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing 210016 China

Video summarization has become one of the most effective solutions for quickly understanding a large amount of video data. Video properties such as importance, diversity, representativeness, and storyness have been widely adopted for summarization based on kinds of features of video frames. To fully exploit these properties, in this paper, we propose a property constrained video summarization framework to output fixed-size summaries based on the concept of regret minimization which is popular in the database community for solving multi-criteria decision-making problems. Our framework first uses representativeness property and effective techniques to generate a candidate frame set. Then, the candidate set is transformed into a multi-dimensional point set where dimensions are composed of entities of the importance property and the diversity property. Moreover, our framework runs the regret minimization query on the point set to output a summary. To further improve the quality of the output summary, the property storyness is exploited to add frames satisfying the size constraint. Experimental results on the benchmark datasets demonstrate the effectiveness and superiority of our framework. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： Multiple properties Regret minimization Video summarization

来源：评论

学校读者我要写书评

暂无评论

MSEs Credit Risk Assessment Model Based on Federated Learning and Feature Selection

引用

computers, Materials & Continua 2023年第6期75卷 5573-5595页

作者： Zhanyang Xu Jianchun Cheng Luofei Cheng Xiaolong Xu Muhammad Bilal School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China State Key Laboratory Novel Software Technology Nanjing UniversityNanjing210023China Department of Computer and Electronics Systems Engineering Hankuk University of Foreign StudiesYongin-siGyeonggi-do17035Korea

Federated learning has been used extensively in business inno-vation scenarios in various *** research adopts the federated learning approach for the first time to address the issue of bank-enterprise information asymmetry in the credit assessment ***,this research designs a credit risk assessment model based on federated learning and feature selection for micro and small enterprises(MSEs)using multi-dimensional enterprise data and multi-perspective enterprise *** proposed model includes four main processes:namely encrypted entity alignment,hybrid feature selection,secure multi-party computation,and global model ***,a two-step feature selection algorithm based on wrapper and filter is designed to construct the optimal feature set in multi-source heterogeneous data,which can provide excellent accuracy and *** addition,a local update screening strategy is proposed to select trustworthy model parameters for aggregation each time to ensure the quality of the global *** results of the study show that the model error rate is reduced by 6.22%and the recall rate is improved by 11.03%compared to the algorithms commonly used in credit risk research,significantly improving the ability to identify ***,the business operations of commercial banks are used to confirm the potential of the proposed model for real-world implementation.

关键词： Federated learning feature selection credit risk assessment MSEs

来源：评论

学校读者我要写书评

暂无评论

Self-Training with Label-Feature-Consistency for Domain Adaptation 28th

Self-Training with Label-Feature-Consistency for Domain Ad...

引用

28th International Conference on Database Systems for Advanced Applications, DASFAA 2023

作者： Xin, Yi Luo, Siqi Jin, Pengsheng Du, Yuntao Wang, Chongjun National Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing China

ISBN: (纸本)9783031306778

Mainstream approaches for unsupervised domain adaptation (UDA) learn domain-invariant representations to address the domain shift. Recently, self-training has been used in UDA, which exploits pseudo-labels for unlabeled target domains. However, the pseudo-labels can be unreliable due to distribution shifts between domains, severely impairing the model performance. To address this problem, we propose a novel self-training framework-Self-Training with Label-Feature-Consistency (ST-LFC), which selects reliable target pseudo-labels via label-level and feature-level voting consistency principle. The former means target pseudo-labels generated by a source-trained classifier and the latter means the nearest source-class to the target in feature space. In addition, ST-LFC reduces the negative effects of unreliable predictions through entropy minimization. Empirical results indicate that ST-LFC significantly improves over the state-of-the-arts on a variety of benchmark datasets. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Entropy

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

Trust Score-Based Malicious Vehicle Detection Scheme in Vehicular Network Environments

引用

computers, Materials & Continua 2024年第11期81卷 2517-2545页

作者： Wenming Wang Zhiquan Liu Shumin Zhang Guijiang Liu School of Computer and Information Anqing Normal UniversityAnqing246133China State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing210023China Yunnan Key Laboratory of Service Computing Yunnan University of Finance and EconomicsKunming650221China

Advancements in the vehicular network technology enable real-time interconnection,data sharing,and intelligent cooperative driving among ***,malicious vehicles providing illegal and incorrect information can compromise the interests of vehicle *** mechanisms serve as an effective solution to this *** recent years,many researchers have incorporated blockchain technology to manage and incentivize vehicle nodes,incurring significant overhead and storage requirements due to the frequent ingress and egress of vehicles within the *** this paper,we propose a distributed vehicular network scheme based on trust ***,the designed architecture partitions multiple vehicle regions into ***,cloud supervision systems(CSSs)verify the accuracy of the information transmitted by ***,the trust scores for vehicles are calculated to reward or penalize them based on the trust evaluation *** proposed scheme demonstrates good scalability and effectively addresses the main cause of malicious information distribution among *** theoretical and experimental analysis show that our scheme outperforms the compared schemes.

关键词： Distributed trust mechanism vehicular network privacy protection

来源：评论

学校读者我要写书评

暂无评论

Quantum Pseudorandom Scramblers 22nd

Quantum Pseudorandom Scramblers

引用

22nd Theory of Cryptography Conference, TCC 2024

作者： Lu, Chuhan Qin, Minglong Song, Fang Yao, Penghui Zhao, Mingnan Computer Science Department Portland State University Portland United States State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China Hefei National Laboratory Hefei230088 China

ISBN: (纸本)9783031780165

Quantum pseudorandom state generators (PRSGs) have stimulated exciting developments in recent years. A PRSG, on a fixed initial (e.g., all-zero) state, produces an output state that is computationally indistinguishable from a Haar random state. However, pseudorandomness of the output state is not guaranteed on other initial states. In fact, known PRSG constructions provably fail on some initial states. In this work, we propose and construct quantum Pseudorandom state Scramblers (PRSSs), which can produce a pseudorandom state on an arbitrary initial state. In the information-theoretical setting, we obtain a scrambler which maps an arbitrary initial state to a distribution of quantum states that is close to Haar random in total variation distance. As a result, our scrambler exhibits a dispersing property. Loosely, it can span an ϵ-net of the state space. This significantly strengthens what standard PRSGs can induce, as they may only concentrate on a small region of the state space provided that the average output state approximates a Haar random state. Our PRSS construction develops a parallel extension of the famous Kac’s walk, and we show that it mixes exponentially faster than the standard Kac’s walk. This constitutes the core of our proof. We also describe a few applications of PRSSs. While our PRSS construction assumes a post-quantum one-way function, PRSSs are potentially a weaker primitive and can be separated from one-way functions in a relativized world similar to standard PRSGs. © International Association for Cryptologic Research 2025.

关键词： Distribution functions

来源：评论

学校读者我要写书评

暂无评论

Massively parallel algorithms for fully dynamic all-pairs shortest paths

引用

Frontiers of computer science 2024年第4期18卷 201-203页

作者： Chilei WANG Qiang-Sheng HUA Hai JIN Chaodong ZHENG National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China

1 Introduction In recent years,the Massively Parallel Computation(MPC)model has gained significant ***,most of distributed and parallel graph algorithms in the MPC model are designed for static graphs[1].In fact,the graphs in the real world are constantly *** size of the real-time changes in these graphs is smaller and more *** graph algorithms[2,3]can deal with graph changes more efficiently[4]than the corresponding static graph ***,most studies on dynamic graph algorithms are limited to the single machine ***,a few parallel dynamic graph algorithms(such as the graph connectivity)in the MPC model[5]have been proposed and shown superiority over their parallel static counterparts.

关键词： dynamic shortest gained

来源：评论

学校读者我要写书评

暂无评论

Towards optimized tensor code generation for deep learning on sunway many-core processor

引用

Frontiers of computer science 2024年第2期18卷 1-15页

作者： Mingzhen LI Changxi LIU Jianjin LIAO Xuegui ZHENG Hailong YANG Rujun SUN Jun XU Lin GAN Guangwen YANG Zhongzhi LUAN Depei QIAN State Key Laboratory of Software Development Environment Beijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China National University of Singapore Singapore 119077Singapore State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi 214000China Science and Technology on Special System Simulation Laboratory Beijing Simulation Center Beijing 100854China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China

The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application *** the existing deep learning compilers,TVM is well known for its efficiency in code generation and optimization across diverse hardware *** the meanwhile,the Sunway many-core processor renders itself as a competitive candidate for its attractive computational power in both scientific computing and deep learning *** paper combines the trends in these two ***,we propose swTVM that extends the original TVM to support ahead-of-time compilation for architecture requiring cross-compilation such as *** addition,we leverage the architecture features during the compilation such as core group for massive parallelism,DMA for high bandwidth memory transfer and local device memory for data locality,in order to generate efficient codes for deep learning workloads on *** experiment results show that the codes generated by swTVM achieve 1.79x improvement of inference latency on average compared to the state-of-the-art deep learning framework on Sunway,across eight representative *** work is the first attempt from the compiler perspective to bridge the gap of deep learning and Sunway processor particularly with productivity and efficiency in *** believe this work will encourage more people to embrace the power of deep learning and Sunwaymany-coreprocessor.

关键词： sunway processor deep learning compiler code generation performance optimization

来源：评论

学校读者我要写书评

暂无评论

DeepTD: Diversity-Guided Deep Neural Network Test Generation 9th

DeepTD: Diversity-Guided Deep Neural Network Test Generation

引用

9th International Symposium on Dependable software Engineering: Theories, Tools and Applications, SETTA 2023

作者： Zhu, Jin Tao, Chuanqi Guo, Hongjing Ju, Yue College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Ministry Key Laboratory for Safety-Critical Software Development and Verification Nanjing China State Key Laboratory for Novel Software Technology Nanjing China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China

ISBN: (纸本)9789819986637

Coverage-guided Fuzz Testing (CGF) techniques have been applied to deep neural network (DNN) testing in recent years, generating a significant number of test samples to uncover inherent defects in DNN models. However, the effectiveness of CGF techniques that utilize structured coverage metrics as coverage criteria is currently being questioned. A few unstructured coverage metrics, such as surprise adequacy, only take into account the diversity of the test samples against the training set, while ignoring the diversity of the test samples themselves. In addition to this, the existing surprise adequacy metrics have some limitations in their applications. Therefore, this paper proposes DeepTD, a diversity-guided deep neural networks test generation method. Firstly, DeepTD selects high-loss test samples from each class on average, ensuring these test seeds possess a strong ability to reveal model errors. Then, DeepTD transforms these test seeds to enhance the diversity of the generated samples. Finally, Cluster-based Surprise Adequacy is designed to guide the generation of test samples. To evaluate the effectiveness of DeepTD, six DNN models are selected as subjects, covering two well-known image datasets. Experimental results demonstrate that the Cluster-based Surprise Adequacy outperforms the two existing metrics not only in computational efficiency but also in discovering more model defects. What’s more, the test samples generated by DeepTD are on average 6.04% and 3.24% more effective for model retraining in MNIST and CIFAR10 compared to baseline methods, respectively. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Coverage-guided fuzz testing Deep neural network Test generation Test samples diversity

来源：评论

学校读者我要写书评

暂无评论

AutoAC: Towards Automated Attribute Completion for Heterogeneous Graph Neural Network 39

AutoAC: Towards Automated Attribute Completion for Heterogen...

引用

39th IEEE International Conference on Data Engineering, ICDE 2023

作者： Zhu, Guanghui Zhu, Zhennan Wang, Wenjie Xu, Zhuoer Yuan, Chunfeng Huang, Yihua Nanjing University State Key Laboratory for Novel Software Technology Nanjing China Nanjing University Department of Computer Science and Technology Nanjing China

ISBN: (纸本)9798350322279

Many real-world data can be modeled as heterogeneous graphs that contain multiple types of nodes and edges. Meanwhile, due to excellent performance, heterogeneous graph neural networks (GNNs) have received more and more attention. However, the existing work mainly focuses on the design of novel GNN models, while ignoring another important issue that also has a large impact on the model performance, namely the missing attributes of some node types. The handcrafted attribute completion requires huge expert experience and domain knowledge. Also, considering the differences in semantic characteristics between nodes, the attribute completion should be fine-grained, i.e., the attribute completion operation should be node-specific. Moreover, to improve the performance of the downstream graph learning task, attribute completion and the training of the heterogeneous GNN should be jointly optimized rather than viewed as two separate processes. To address the above challenges, we propose a differentiable attribute completion framework called AutoAC for automated completion operation search in heterogeneous GNNs. We first propose an expressive completion operation search space, including topology-dependent and topology-independent completion operations. Then, we propose a continuous relaxation schema and further propose a differentiable completion algorithm where the completion operation search is formulated as a bi-level joint optimization problem. To improve the search efficiency, we leverage two optimization techniques: discrete constraints and auxiliary unsupervised graph node clustering. Extensive experimental results on real-world datasets reveal that AutoAC outperforms the SOTA handcrafted heterogeneous GNNs and the existing attribute completion method. © 2023 IEEE.

关键词： Graph neural networks

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：