检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Jiahao Zhou, Yipeng Wu, Di Hu, Miao Guizani, Mohsen Sheng, Quan Z. School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China School of Computing Faculty of Science and Engineering Macquarie University Sydney Australia Abu Dhabi United Arab Emirates

Federated learning (FL) is an emerging machine learning paradigm for preserving data privacy. However, diverse client hardware often has varying computation resources. Such system heterogeneity limits the participation of resource-constrained clients in FL, and hence degrades the global model accuracy. To enable heterogeneous clients to participate in and contribute to FL training, previous works tackle this problem by assigning customized sub-models to individual clients with model pruning, distillation, or low-rank based techniques. Unfortunately, the global model trained by these methods still encounters performance degradation due to heterogeneous sub-model aggregation. Besides, most methods are heuristic-based and lack convergence analysis. In this work, we propose the FedLMT framework to bridge the performance gap, by assigning clients with a homogeneous pre-factorized low-rank model to substantially reduce resource consumption without conducting heterogeneous aggregation. We theoretically prove that the convergence of the low-rank model can guarantee the convergence of the original full model. To further meet clients' personalized resource needs, we extend FedLMT to pFedLMT, by separating model parameters into common and custom ones. Finally, extensive experiments are conducted to verify our theoretical analysis and show that FedLMT and pFedLMT outperform other baselines with much less communication and computation costs. Copyright 2024 by the author(s)

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Recent advances in ethanol gas sensors based on metal oxide semiconductor heterojunctions

引用

Rare Metals 2022年第6期41卷 1818-1842页

作者： Ling-Yun Gai Run-Ping Lai Xian-Hui Dong Xing Wu Qiao-Tong Luan Jue Wang Hao-Feng Lin Wen-Hao Ding Guang-Lei Wu Wan-Feng Xie Big Data and Network Management Center Qingdao Agricultural UniversityQingdao 266109China School of Mechanical Electronic and Information Engineering China University of Mining and Technology-BeijingBeijing 10083China School of Material Science and Engineering State Key Laboratory of Bio-Fibers and Eco-TextilesQingdao UniversityQingdao 266071China School of Electronics and Information State Key Laboratory of Bio-Fibers and Eco-TextilesQingdao UniversityQingdao 266071China Shanghai Key Laboratory of Multidimensional Information Processing School of Communication and Electronic EngineeringEast China Normal UniversityShanghai 200241China

Metal oxide semiconductor heterojunctions(MOSHs)can enhance the performance of ethanol gas sen-sors *** gas sensors based on MOSHs are cost-effective and have excellent sensing response,good selectivity,fast response and recovery,long-term stability or repeatability,a low operating temperature,a facile fabrica-tion process,and versatile *** paper reviews the recent advances in gas sensors that are based on MOSHs and the advantages of using them to detect ethanol *** to the literature,compared with ethanol gas sen-sors that use single-component sensing materials,the MOSHs exhibit superior performance due to the synergy between the different components,which can amplify the reception and transduction components of the sensor *** the best of our knowledge,heterojunctions can be grouped into four main categories as metal oxide/metal oxide,metal oxide/metal sulfide,metal oxide/noble metal,and metal oxide/other materials,including rare-earth metals,g-C_(3)N_(4),and graphene,*** future trends and challenges that would be faced in the development of ethanol gas sensors based on MOSHs are discussed in ***,critical ideas and thinking regarding the future progress of MOSH-based gas sensors are presented.

关键词： Metal oxides Heterojunction Chemiresistori Ethanol sensor Synergistic behavior

来源：评论

学校读者我要写书评

暂无评论

Partial Label Learning via Conditional-Label-Aware Disambiguation

引用

Journal of computer Science & Technology 2021年第3期36卷 590-605页

作者： Peng Ni Su-Yun Zhao Zhi-Gang Dai Hong Chen Cui-Ping Li Key Laboratory of Data Engineering and Knowledge Engineering(Renmin University of China) Ministry of Education Beijing 100087China School of Information Renmin University of ChinaBeijing 100087China

Partial label learning is a weakly supervised learning framework in which each instance is associated with multiple candidate labels,among which only one is the ground-truth *** paper proposes a unified formulation that employs proper label constraints for training models while simultaneously performing *** existing partial label learning approaches that only leverage similarities in the feature space without utilizing label constraints,our pseudo-labeling process leverages similarities and differences in the feature space using the same candidate label constraints and then disambiguates noise *** experiments on artificial and real-world partial label datasets show that our approach significantly outperforms state-of-the-art counterparts on classification prediction.

关键词： disambiguation partial label learning similarity and dissimilarity weak supervision

来源：评论

学校读者我要写书评

暂无评论

KAN v.s. MLP for Offline Reinforcement Learning

KAN v.s. MLP for Offline Reinforcement Learning

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Guo, Haihong Li, Fengxin Li, Jiao Liu, Hongyan School of Information Renmin University of China China Institute of Medical Information Medical Library Chinese Academy of Medical Sciences Peking Union Medical College China Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education China School of Economics and Management Tsinghua University China

ISBN: (纸本)9798350368741

Kolmogorov-Arnold Networks (KAN) is an emerging neural network architecture in machine learning. It has greatly interested the research community about whether KAN can be a promising alternative to the commonly used Multi-Layer Perceptions (MLP). Experiments in various fields demonstrated that KAN-based machine learning can achieve comparable if not better performance than MLP-based methods, but with much smaller parameter scales and are more explainable. In this paper, we explore the incorporation of KAN into the actor and critic networks for offline reinforcement learning (RL). We evaluated the performance, parameter scales, and training efficiency of various KAN and MLP-based conservative Q-learning (CQL) on the classical D4RL benchmark for offline RL. Our study demonstrates that KAN can achieve performance close to the commonly used MLP with significantly fewer parameters. This allows us to choose the base networks according to the offline RL task requirements. © 2025 IEEE.

关键词： KAN Kolmogorov-Arnold networks MLP multilayer perceptrons offline reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Model Store and Reuse in an OLML database System

引用

Journal of computer Science & Technology 2021年第4期36卷 792-805页

作者： Jian-Wei Cui Wei Lu Xin Zhao Xiao-Yong Du Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education Renmin University of China Beijing 100872China School of Information Renmin University of ChinaBeijing 100872China

Deep learning has shown significant improvements on various machine learning tasks by introducing a wide spectrum of neural network ***,for these neural network models,it is necessary to label a tremendous amount of training data,which is prohibitively expensive in *** this paper,we propose OnLine Machine Learning(OLML)database which stores trained models and reuses these models in a new training task to achieve a better training effect with a small amount of training *** efficient model reuse algorithm AdaReuse is developed in the OLML ***,AdaReuse firstly estimates the reuse potential of trained models from domain relatedness and model quality,through which a group of trained models with high reuse potential for the training task could be selected ***,multi selected models will be trained iteratively to encourage diverse models,with which a better training effect could be achieved by *** evaluate AdaReuse on two types of natural language processing(NLP)tasks,and the results show AdaReuse could improve the training effect significantly compared with models training from scratch when the training data is *** on AdaReuse,we implement an OLML database prototype system which could accept a training task as an SQL-like query and automatically generate a training plan by selecting and reusing trained *** studies are conducted to illustrate the OLML database could properly store the trained models,and reuse the trained models efficiently in new training tasks.

关键词： model selection model reuse OnLine Machine Learning(OLML)database

来源：评论

学校读者我要写书评

暂无评论

Control Logic Routing for Continuous-Flow Microfluidic Biochips Based on Deep Reinforcement Learning

引用

Jisuanji Yanjiu yu Fazhan/computer Research and Development 2025年第4期62卷 950-962页

作者： Cai, Huayang Huang, Xing Liu, Genggeng College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Fuzhou University Ministry of Education Fuzhou350116 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China School of Computer Science Northwestern Polytechnical University Xi’an710072 China

With the advancement of electronic design automation, continuous-flow microfluidic biochips have become one of the most promising platforms for biochemical experiments. This chip manipulates fluid samples in milliliters or nanoliters by utilizing internal microvalves and microchannels, and thus automatically performs basic biochemical experiments, such as mixing and detection. To achieve the correct bioassay function, the microvalves deployed inside the chip are usually managed by a multiplexer-based control logic, and valves receive control signals from a core input through the control channel for accurate switching. Since biochemical reactions typically require high sensitivity, the length of control paths connecting each valve needs to be reduced to ensure immediate signal propagation, and thus to reduce the signal propagation delay. In addition, to reduce the fabrication cost of chips, a vital issue to be addressed in the logic architecture design is how to effectively reduce the total channel length within the control logic. To address the above issues, we propose a deep reinforcement learning-based control logic routing algorithm to minimize the signal propagation delay and total control channel length, thereby automatically constructing an efficient control channel network. The algorithm employs the dueling deep Q-network architecture as the agent of the deep reinforcement learning framework to evaluate the tradeoff between signal propagation delay and total channel length. Besides, the diagonal channel routing is implemented for the first time for control logic, thus fundamentally improving the efficiency of valve switching operations and reducing the fabrication cost of the chip. The experimental results demonstrate that the proposed algorithm can effectively construct a high-performance and low-cost control logic architecture. © 2025 Science Press. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Simulating Bluetooth virus propagation on the real map via infectious attenuation algorithm and discrete dynamical system

引用

Iran Journal of computer Science 2024年第4期7卷 755-776页

作者： Zhu, Qingyi Wan, Wentao Gan, Chengquan Fan, Ziqi Yang, Lu-Xing School of Cyber Security and Information Law Chongqing University of Posts and Telecommunications Chongqing 400065 China School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing 400065 China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing 400065 China School of Information Technology Deakin University Melbourne 3125 VIC Australia

In recent years, mobile smart devices have gained popularity globally due to their convenience and efficiency. However, this popularity has also attracted the attention of virus creators, resulting in a significant cost to users. Current research on virus propagation primarily focuses on developing anti-virus software and macroscopic modeling. Software development often lags behind and only begins when viruses become a significant threat. In contrast, macroscopic modeling frequently deviates from reality as real networks do not completely conform to the characteristics of scale-free or small-world networks. Furthermore, special factors such as device mobility and signal attenuation must be considered when studying Bluetooth-transmitted viruses. Traditional research methods have shown limited performance in this field. To address these issues, this paper proposes a method that describes the propagation behavior of Bluetooth viruses in smart devices by utilizing an Infectious Attenuation Algorithm (IAA) and real maps. This method incorporates population density, map contours, and user security awareness to construct a unique discrete system. More importantly, we integrate this system into the map of Deyuan Street in Chengdu City and create a visualization system using the Simulation of Urban Mobility (SUMO) simulation software. In this system, the proposed IAA simulates the decay of virus infectivity based on the distance between devices and the attenuation of signal power between them. Our research approach considers the two core elements of infectivity attenuation and maps, making it more realistic and overcoming the lag in software development. Additionally, the introduction of SUMO for visualization simulation enhances the practical significance of our experiments. Finally, we propose feasible prevention strategies based on comparative experiments, data analysis, and theoretical analysis. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2

关键词： Bluetooth virus Discrete dynamical system Infectious attenuation algorithm Population density Real map Security awareness SUMO simulation

来源：评论

学校读者我要写书评

暂无评论

REQUIRED NUMBER OF ITERATIONS FOR SPARSE SIGNAL RECOVERY VIA ORTHOGONAL LEAST SQUARES

引用

Journal of Computational Mathematics 2023年第1期41卷 1-17页

作者： Haifeng Li Jing Zhang Jinming Wen Dongfang Li Henan Engineering Laboratory for Big Data Statistical Analysis and Optimal Control College of Mathematics and Information ScienceHenan Normal UniversityXinxiang 453007China College of Information Science and Technology Jinan UniversityGuangzhou 510632China School of Mathematics and Statistics Huazhong University of Science and TechnologyWuhan 430074China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and TechnologyWuhan 430074China

In countless applications,we need to reconstruct a K-sparse signal x∈R n from noisy measurements y=Φx+v,whereΦ∈R^(m×n)is a sensing matrix and v∈R m is a noise *** least squares(OLS),which selects at each step the column that results in the most significant decrease in the residual power,is one of the most popular sparse recovery *** this paper,we investigate the number of iterations required for recovering x with the OLS *** show that OLS provides a stable reconstruction of all K-sparse signals x in[2.8K]iterations provided thatΦsatisfies the restricted isometry property(RIP).Our result provides a better recovery bound and fewer number of required iterations than those proposed by Foucart in 2013.

关键词： Sparse signal recovery Orthogonal least squares(OLS) Restricted isometry property(RIP)

来源：评论

学校读者我要写书评

暂无评论

Clause-level Relationship-aware Math Word Problems Solver

引用

Machine Intelligence Research 2022年第5期19卷 425-438页

作者： Chang-Yang Wu Xin Lin Zhen-Ya Huang Yu Yin Jia-Yu Liu Qi Liu Gang Zhou Anhui Province Key Laboratory of Big Data Analysis and Application School of Data ScienceUniversity of Science and Technology of ChinaHefei 230026China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Laboratory of Mathematical Engineering and Advanced Computing Information Engineering UniversityZhengzhou 450001China

Automatically solving math word problems,which involves comprehension,cognition,and reasoning,is a crucial issue in artificial intelligence *** math word problem solvers mainly work on word-level relationship extraction and the generation of expression solutions while lacking consideration of the clause-level *** this end,inspired by the theory of two levels of process in comprehension,we propose a novel clause-level relationship-aware math solver(CLRSolver)to mimic the process of human comprehension from lower level to higher ***,in the lower-level processes,we split problems into clauses according to their natural division and learn their *** the higher-level processes,following human′s multi-view understanding of clause-level relationships,we first apply a CNN-based module to learn the dependency relationships between clauses from word relevance in a local ***,we propose two novel relationship-aware mechanisms to learn dependency relationships from the clause semantics in a global ***,we enhance the representation of clauses based on the learned clause-level dependency *** expression generation,we develop a tree-based decoder to generate the mathematical *** conduct extensive experiments on two datasets,where the results demonstrate the superiority of our framework.

关键词： Artificial intelligence(AI) artificial neural network(ANN) computational mathematics machine intelligence machine learning

来源：评论

学校读者我要写书评

暂无评论

Prescribed Performance-Based Finite-Time Neural Adaptive Backstepping Control for the Chaotic PMSM

Prescribed Performance-Based Finite-Time Neural Adaptive Bac...

引用

2022 International Conference on Mechanical and Electronics engineering, ICMEE 2022

作者： Wu, Fengbin Zhang, Junxing Li, Shaobo Li, Shaoyang Wu, Xiao Wang, Shuai College of Computer Science and Technology Guizhou University State Key Laboratory of Public Big Data Guiyang China School of Mechanical Engineering Guizhou University State Key Laboratory of Public Big Data Guiyang China School of Mechanical Engineering Guizhou University Guiyang China Guizhou University State Key Laboratory of Public Big Data Guiyang China

ISBN: (纸本)9781665492201

This paper presents a prescribed performance-based finite-time neural adaptive backstepping control scheme for the chaotic permanent magnet synchronous motor (PMSM). Specifically, an error transformation coupled with a prescribed performance function is introduced to guarantee that the tracking error keeps within a defined bound. The finite-time stability theory and backstepping framework are further combined to design finite-time adaptive laws and controllers. Then, it is shown that all signals are ultimately bounded in finite time and the tracking error can converge to a defined region in finite time. Finally, simulation results are presented to verify the feasibility of the proposed controller. © 2022 IEEE.

关键词： Backstepping

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：