检索结果-内蒙古大学图书馆

Multi-View Dynamic Kernelized Evidential Clustering

IEEE/CAA Journal of Automatica Sinica 2024年第12期11卷 2435-2450页

作者： Jinyi Xu Zuowei Zhang Ze Lin Yixiang Chen Weiping Ding the Software Engineering Institute East China Normal UniversityShanghai 200062 Shanghai Key Laboratory of Trustworthy Computing East China Normal UniversityShanghai 200062China IEEE the School of Automation Northwestern Polytechnical UniversityXi’an 710072China the School of Artificial Intelligence and Computer Science Nantong UniversityNantong 226019 the Faculty of Data Science City University of MacaoMacao 999078China

It is challenging to cluster multi-view data in which the clusters have overlapping *** multi-view clustering methods often misclassify the indistinguishable objects in overlapping areas by forcing them into single clusters,increasing clustering *** solution,the multi-view dynamic kernelized evidential clustering method(MvDKE),addresses this by assigning these objects to meta-clusters,a union of several related singleton clusters,effectively capturing the local imprecision in overlapping *** offers two main advantages:firstly,it significantly reduces computational complexity through a dynamic framework for evidential clustering,and secondly,it adeptly handles non-spherical data using kernel techniques within its objective *** on various datasets confirm MvDKE's superior ability to accurately characterize the local imprecision in multi-view non-spherical data,achieving better efficiency and outperforming existing methods in overall performance.

关键词： Evidential clustering imprecision characterizing kernel technique multi-view clustering

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem 30

Benchmarking Hallucination in Large Language Models based on...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Sun, Yuhong Yin, Zhangyue Guo, Qipeng Wu, Jiawen Qiu, Xipeng Zhao, Hui Software Engineering Institute East China Normal University China School of Computer Science Fudan University China Shanghai AI Laboratory China Shanghai Key Laboratory of Trustworthy Computing Shanghai China

ISBN: (纸本)9782493814104

Large language models (LLMs) are highly effective in various natural language processing (NLP) tasks. However, they are susceptible to producing unreliable conjectures in ambiguous contexts called hallucination. This paper presents a new method for evaluating LLM hallucination in Question Answering (QA) based on the unanswerable math word problem (MWP). To support this approach, we innovatively develop a dataset called Unanswerable Math Word Problem (UMWP) which comprises 5200 questions across five categories. We developed an evaluation methodology combining text similarity and mathematical expression detection to determine whether LLM considers the question unanswerable. The results of extensive experiments conducted on 31 LLMs, including GPT-3, InstructGPT, LLaMA, and Claude, demonstrate that in-context learning and reinforcement learning with human feedback (RLHF) training significantly enhance the model's ability to avoid hallucination. We show that utilizing MWP is a reliable and effective approach to assess hallucination. Our code and data are available at https://***/Yuki-Asuuna/UMWP. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

SUNET: Framework, Security, and Privacy

SUNET: Framework, Security, and Privacy

引用

2024 International Conference on Satellite Internet, SAT-NET 2024

作者： Xie, Zhan Wang, Liangmin Wu, Haiqin Zhang, Xiaoyu Wang, Liang Yang, Haotian Southeast University School of Cyber Science and Engineering Nanjing211189 China Southeast University Engineering Research Center of BASAM Ministry of Education Nanjing211189 China East China Normal University Software Engineering Institute Shanghai Key Laboratory of Trustworthy Computing Shanghai200062 China

ISBN: (纸本)9798350375176

SUNet (Satellite-assisted Unmanned-system Network) integrates satellite communication technology, unmanned equipment systems, and ground support facilities. Compared to traditional network system, SUNet has the advantages of flexible deployment and wide communication range. SUNet with cloud services (SUNET) breaks the limitation of satellites processing large-scale data, and integrates a large scope of computing and storage resources in a system. However, SUNET also poses more serious security risks than traditional networks for two reasons: i) the unique network framework, such as highly dynamic topology, unfixed network access points and decentralized control, of SUNET increases security risks, and ii) the rising probability of existing neighbor nodes with quantum computing. This paper firstly introduces the term SUNET from definition and compares SUNET with several related network frameworks. Then we anaylze the security risks, such as untrust between nodes, unauthorized access and quantum computing attack, faced by SUNET. Meanwhile, we illustrate the security requirements and the corresponding solutions, such as authentication, fine-grained authorization and quantum security, in SUNET. Finally, we discuss the security countermeasures and point out the potential future research directions. © 2024 IEEE.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

SRender: Boosting Neural Radiance Field Efficiency via Sensitivity-Aware Dynamic Precision Rendering 57

SRender: Boosting Neural Radiance Field Efficiency via Sensi...

引用

57th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2024

作者： Song, Zhuoran He, Houshu Liu, Fangxin Hao, Yifan Song, Xinkai Jiang, Li Liang, Xiaoyao Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai China Institute of Computing Technology Chinese Academy of Sciences State Key Lab of Processors Beijing China

ISBN: (纸本)9798350350579

Neural Radiance Field (NeRF) holds immense promise for generating photo-realistic images and videos. How-ever, the computation and memory demands significantly impede its applicability in real-Time tasks such as virtual reality and augmented reality. While accelerators dedicatedly designed for NeRF have emerged, they may not be the optimal solution as they only consider the optimization of full-precision NeRF models, leading to unsatisfactory memory and computation saving. This paper proposes Sensitivity-Aware Dynamic Precision Rendering, abbreviated as SRender, an algorithm-hardware co-design framework that borrows the idea of Adaptive Rendering commonly used in conventional graphics rendering to accelerate the rendering process of NeRF exploiting the fine-grained per-ray and per-point levels sensitivity. The fundamental idea behind SRender is that rays and points with high sensitivity require high-precision data types, while the insensitive rays and points do not, allowing them to be sacrificed for greater acceleration. Accordingly, the algorithm part of SRender dynamically configures the precision of the hash table and the multilayer perceptron (MLP), and the hardware part features a specialized accelerator that exploits such mixed-precision memory access and computation patterns. Specifically, we predict the sensitive rays and points based on low-precision hash encoding and feature computation. Then, we trigger a high-precision rendering again on the sensitive ones to guarantee the rendering quality. The hardware design of SRender includes a sensitivity prediction engine, coarse-Then-fine-grained encoding engines, and a recovery engine, which translates the computational saving in the algorithm to real speedup. Using the coarse-Then-fine-grained encoding engine, we maximize the data reuse on-chip, thereby reducing the stress of off-chip memory bandwidth. Experiments show that the edge-level SRender can achieve 3.94x and 34.06x speedup over state-of-The-Art NeRF

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

A Decentralized Vehicle-to-Vehicle Energy Trading System Based on Efficient Sharding Services 21

A Decentralized Vehicle-to-Vehicle Energy Trading System Bas...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big data and Cloud computing, 16th IEEE International Conference on Social computing and Networking and 13th International Conference on Sustainable computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Meng, Kun Sun, Lijun Chen, Xiao Wu, Haiqin Li, Shuaiyong Qingdao University of Science and Technology College of Information Science and Technology Shandong China University of Leicester School of Computing and Mathematical Sciences Leicester United Kingdom Software Engineering Institute Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China Key Laboratory of Industrial Internet of Things and Networked Control Ministry of Education Chongqing China

ISBN: (纸本)9798350329223

Vehicle-to-vehicle (V2V) energy trading stands as a significant technology, allowing electric vehicles (EVs) to share energy. This balances energy demand and supply, reducing pressure on the power grid. However, two substantial challenges require attention: 1) Creating a standardized protocol universally adoptable by EV manufacturers and energy trading participants to establish a common secure and reliable platform for real-time energy trading between EVs. 2) Determining a fair and transparent pricing and transaction management mechanism, accounting for factors such as energy demand and supply, location, and user preferences. To tackle these hurdles, this paper proposes a decentralized V2V energy trading system (VETS) based on a novel high-performance sharding blockchain framework. VETS incorporates a standard energy trading management protocol, achieving trustless and transparent transaction processing. It employs a blockchain sharding and parallel architecture for high transaction throughput, catering to a large number of EVs. Furthermore, an efficient consensus algorithm is developed to minimize service delays and adapt to real-time transaction demands. A practical testbed operationalizes VETS, facilitating experimental analysis within a real-world cloud environment. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Feature Attribution Explanation for Explainable Machine Learning

引用

ACM Transactions on Evolutionary Learning and Optimization 2024年第1期4卷 1-32页

作者： Wang, Ziming Huang, Changwu Li, Yun Yao, Xin Research Institute of Trustworthy Autonomous Systems Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Departmentof Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China The Advanced Cognitive Technology Lab Huawei Technologies Co. Ltd Shanghai201206 China School of Computer Science University of Birmingham BirminghamB15 2TT United Kingdom

The feature attribution-based explanation (FAE) methods, which indicate how much each input feature contributes to the model's output for a given data point, are one of the most popular categories of explainable machine learning techniques. Although various metrics have been proposed to evaluate the explanation quality, no single metric could capture different aspects of the explanations. Different conclusions might be drawn using different metrics. Moreover, during the processes of generating explanations, existing FAE methods either do not consider any evaluation metric or only consider the faithfulness of the explanation, failing to consider multiple metrics simultaneously. To address this issue, we formulate the problem of creating FAE explainable models as a multi-objective learning problem that considers multiple explanation quality metrics simultaneously. We first reveal conflicts between various explanation quality metrics, including faithfulness, sensitivity, and complexity. Then, we define the considered multi-objective explanation problem and propose a multi-objective feature attribution explanation (MOFAE) framework to address this newly defined problem. Subsequently, we instantiate the framework by simultaneously considering the explanation's faithfulness, sensitivity, and complexity. Experimental results comparing with six state-of-The-Art FAE methods on eight datasets demonstrate that our method can optimize multiple conflicting metrics simultaneously and can provide explanations with higher faithfulness, lower sensitivity, and lower complexity than the compared methods. Moreover, the results have shown that our method has better diversity, i.e., it provides various explanations that achieve different tradeoffs between multiple conflicting explanation quality metrics. Therefore, it can provide tailored explanations to different stakeholders based on their specific requirements. © 2024 Copyright held by the owner/author(s). Publication rights licensed

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

MPC-Based Privacy-Preserving Serverless Federated Learning 3

MPC-Based Privacy-Preserving Serverless Federated Learning

引用

3rd International Conference on Big data, Artificial Intelligence and Internet of Things engineering, ICBAIE 2022

作者： Zhong, Liangyu Zhang, Lei Xu, Lin Wang, Lulu East China Normal University Shanghai Key Laboratory of Trustworthy Computing Software Engineering Institute Shanghai200062 China Science and Technology on Communication Security Laboratory Sichuan Chengdu610041 China

ISBN: (数字)9781665451604

ISBN: (纸本)9781665451604

Federated learning (FL) enables multiple users to collaboratively train a global model by keeping their data sets local. Since a single server is used, traditional FL faces the single point of failure problem. An available approach is to adopt a serverless architecture. However, most of existing serverless FL schemes fail to protect gradient privacy, except for a few schemes that adopt differential privacy (DP) where the global model accuracy will decrease. To address these problems, we propose a privacy-preserving serverless FL scheme based on secure multiparty computation (MPC). Combining multiple cryptographic primitives (e.g., key agreement and symmetric encryption), our scheme protects gradient privacy in FL and it is accuracy-lossless. By secret sharing, our scheme supports users to quit an FL task in each round during training. © 2022 IEEE.

关键词： Privacy-preserving techniques

来源：评论

学校读者我要写书评

暂无评论

Effective Entry-Wise Flow for Molecule Generation 40

Effective Entry-Wise Flow for Molecule Generation

引用

40th IEEE International Conference on data engineering, ICDE 2024

作者： Zhang, Qifan Yao, Junjie Yang, Yuquan Shi, Yizhou Gao, Wei Wang, Xiaoling School of Computer Science and Technology East China Normal University China Software Engineering Institute East China Normal University China Shanghai Key Laboratory of Trustworthy Computing China University of Massachusetts Department of Chemistry Boston United States University of Michigan Ann Arbor United States

ISBN: (纸本)9798350317152

Molecule generation is a critical process in the fields of drug discovery and materials science. Recently, generative models based on normalizing flows have demonstrated significant potential in this domain. These models are particularly suited for handling the symmetrical and complex chemical structures often encountered in molecular datasets. Despite their promising nature, normalizing flow-based models for molecule generation face considerable challenges. The complexity of molecule representation, the rigorous demands of optimization, and the scarcity of training labels in molecular datasets contribute to these difficulties. Additionally, adequately and comprehensively learning the distribution of molecular datasets remains a formidable task. In this paper, we delve into the intricate entry-wise modules in vanilla flows, introducing an effective variation of flow-based models. Our proposed approach innovatively encapsulates affine coupling transformations within normalizing flows. Furthermore, we deconstruct existing invertible flow models, integrating them with newly developed entry-wise transformations. Our experimental studies demonstrate that these proposed entry-wise modules, when incorporated into standard flow-based models, surpass other generative models in performance on various representative datasets and generation tasks. Notably, in the context of low-resourced molecular graph generation, our model achieves remarkable performance compared to its counterparts. © 2024 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Optimized Computation for Determinant of Multivariate Polynomial Matrices on GPGPU 24

Optimized Computation for Determinant of Multivariate Polyno...

引用

24th IEEE International Conference on High Performance computing and Communications, 8th IEEE International Conference on data science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Chen, Liangyu Wei, Jianjun Zeng, Zhenbing Zhang, Min East China Normal University Shanghai Key Lab of Trustworthy Computing Shanghai China Washington University in St. Louis Department of Computer Science and Engineering St Louis United States Shanghai University Department of Mathematics Shanghai China

ISBN: (纸本)9798350319934

The determinant of the matrix is a fundamental concept in linear algebra and has various applications in research and engineering. Compared to the easy-calculating numeric matrix, a symbolic matrix with multivariate polynomial entries is hard to calculate because of immediate expression expansion, which often leads to drastic exhaustion of the physical memory. In this paper, we present a novel four-stage-approach to calculate the accurate determinant of multivariate polynomial matrices on GPGPU, through using the modular method, the Stockham Fast Fourier Transformation(FFT), the inverse FFT, and the Chinese Remainder Theorem. In our approach, the computation tasks in each stage are deployed on GPGPU so that the calculation could be recovered without loss at any point in case of inevitable interruptions happened during the parallel processing. In addition, to control the parallel computation time, we propose a time prediction model for the computation of polynomial determinant according to the basic matrix attributes. The experiment results show that our approach owns substantial speedups compared to Maple, allowing memory and time usage in steady increments. © 2022 IEEE.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning 22

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Cao, Weipeng Yao, Xuyang Xu, Zhiwu Pan, Yinghui Sun, Yixuan Li, Dachuan Qiu, Bohua Wei, Muheng Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (纸本)9798331527471

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model’s capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods. © 2024 IEEE.

关键词： Zero-shot learning

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：