检索结果-内蒙古大学图书馆

Learning continuous network emerging dynamics from scarce observations via data-adaptive stochastic processes

science China(Information sciences) 2024年第12期67卷 240-255页

作者： Jiaxu CUI Qipeng WANG Bingyi SUN Jiming LIU Bo YANG College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Public Computer Education and Research Center Jilin University Department of Computer Science Hong Kong Baptist University

Learning network dynamics from the empirical structure and spatio-temporal observation data is crucial to revealing the interaction mechanisms of complex networks in a wide range of domains. However,most existing methods only aim at learning network dynamic behaviors generated by a specific ordinary differential equation instance, resulting in ineffectiveness for new ones, and generally require dense *** observed data, especially from network emerging dynamics, are usually difficult to obtain, which brings trouble to model learning. Therefore, learning accurate network dynamics with sparse, irregularly-sampled,partial, and noisy observations remains a fundamental challenge. We introduce a new concept of the stochastic skeleton and its neural implementation, i.e., neural ODE processes for network dynamics(NDP4ND), a new class of stochastic processes governed by stochastic data-adaptive network dynamics, to overcome the challenge and learn continuous network dynamics from scarce observations. Intensive experiments conducted on various network dynamics in ecological population evolution, phototaxis movement, brain activity, epidemic spreading, and real-world empirical systems, demonstrate that the proposed method has excellent data adaptability and computational efficiency, and can adapt to unseen network emerging dynamics, producing accurate interpolation and extrapolation with reducing the ratio of required observation data to only about 6% and improving the learning speed for new dynamics by three orders of magnitude.

关键词： complex networks network dynamics emerging spatio-temporal dynamics neural processes

来源：评论

学校读者我要写书评

暂无评论

A survey on cross-user federated recommendation

引用

science China(Information sciences) 2025年第4期68卷 7-32页

作者： Enyue YANG Yudi XIONG Wei YUAN Weike PAN Qiang YANG Zhong MING College of Computer Science and Software Engineering Shenzhen University School of Electrical Engineering and Computer Science The University of Queensland WeBank AI Lab WeBank Department of Computer Science and Engineering Hong Kong University of Science and Technology College of Big Data and Internet Shenzhen Technology University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)

Recommender systems are effective in mitigating information overload, yet the centralized storage of user data raises significant privacy concerns. Cross-user federated recommendation(CUFR) provides a promising distributed paradigm to address these concerns by enabling privacy-preserving recommendations directly on user devices. In this survey, we review and categorize current progress in CUFR, focusing on four key aspects: privacy, security, accuracy, and efficiency. Firstly,we conduct an in-depth privacy analysis, discuss various cases of privacy leakage, and then review recent methods for privacy protection. Secondly, we analyze security concerns and review recent methods for untargeted and targeted *** untargeted attack methods, we categorize them into data poisoning attack methods and parameter poisoning attack methods. For targeted attack methods, we categorize them into user-based methods and item-based methods. Thirdly,we provide an overview of the federated variants of some representative methods, and then review the recent methods for improving accuracy from two categories: data heterogeneity and high-order information. Fourthly, we review recent methods for improving training efficiency from two categories: client sampling and model compression. Finally, we conclude this survey and explore some potential future research topics in CUFR.

关键词： cross-user federated recommendation federated recommendation federated learning recommender systems user privacy

来源：评论

学校读者我要写书评

暂无评论

Deep learning based on hand pose estimation methods: a systematic literature review

引用

Multimedia Tools and Applications 2025年 1-38页

作者： Roumaissa, Bekiri Mohamed Chaouki, Babahenini Computer Science Department LESIA Laboratory Mohamed Khider University Biskra07000 Algeria

Estimating hand pose is a challenge that has significantly benefited from using deep learning-based algorithms. This study area holds critical significance across various computer vision and robotics domains, including applications in sign language interpretation, computer-Aided Design (CAD), and 3D humanoid reconstruction systems. These technologies flourish in augmented reality systems, facilitating immersive interactions within virtual reality contexts. The complexity of human hand anatomy and its intricate range of motions intensifies the difficulty of accurate pose estimation, posing significant academic and technical hurdles. Recent advancements have seen the emergence of rapid and comprehensive methods for hand pose estimation, driven by advancements in-depth camera technology and Deep Neural Networks (DNNs). The previous surveys studied most of these hand pose issues, including hand parsing, data labeling technologies, hand motion, fingertip detection, hand localization, and self-occlusion. This paper addresses the aforementioned challenges in hand pose estimation. Further, we propose a novel taxonomy based on deep-learning-based approaches that aim to gather the previous research advances systems that tackled these actual challenges. We provide an overview of existing research, discussing their strengths and limitations. Additionally, we identify various benchmark datasets, their characteristics and prevalent evaluation metrics used to assess these approaches. Finally, we explore potential research directions focusing on speed, accuracy, and type of deep learning architecture in this rapidly evolving field. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Clustered Reinforcement Learning

引用

Frontiers of computer science 2025年第4期19卷 43-57页

作者： Xiao MA Shen-Yi ZHAO Zhao-Heng YIN Wu-Jun LI National Key Laboratory for Novel Software Technology Department of Computer Science and TechnologyNanjing UniversityNanjing 210023China Department of Electrical Engineering and Computer Sciences University of CaliforniaBerkeleyCA 94720-1770USA

Exploration strategy design is a challenging problem in reinforcement learning(RL),especially when the environment contains a large state space or sparse *** exploration,the agent tries to discover unexplored(novel)areas or high reward(quality)*** existing methods perform exploration by only utilizing the novelty of *** novelty and quality in the neighboring area of the current state have not been well utilized to simultaneously guide the agent’s *** address this problem,this paper proposes a novel RL framework,called clustered reinforcement learning(CRL),for efficient exploration in *** adopts clustering to divide the collected states into several clusters,based on which a bonus reward reflecting both novelty and quality in the neighboring area(cluster)of the current state is given to the *** leverages these bonus rewards to guide the agent to perform efficient ***,CRL can be combined with existing exploration strategies to improve their performance,as the bonus rewards employed by these existing exploration strategies solely capture the novelty of *** on four continuous control tasks and six hard-exploration Atari-2600 games show that our method can outperform other state-of-the-art methods to achieve the best performance.

关键词： deep reinforcement learning exploration count-based method clustering K-means

来源：评论

学校读者我要写书评

暂无评论

FilterGNN:Image feature matching with cascaded outlier filters and linearattention

引用

Computational Visual Media 2024年第5期10卷 873-884页

作者： Jun-Xiong Cai Tai-Jiang Mu Yu-Kun Lai Key Laboratory of Pervasive Computing Ministry of EducationDepartment of Computer Science and TechnologyTsinghua UniversityBeijing 100084China School of Computer Science and Informatics Cardiff UniversityWales CF244AGUK

The cross-view matching of local image features is a fundamental task in visual localization and 3D *** study proposes FilterGNN,a transformer-based graph neural network(GNN),aiming to improve the matching efficiency and accuracy of visual *** on high matching sparseness and coarse-to-fine covisible area detection,FilterGNN utilizes cascaded optimal graph-matching filter modules to dynamically reject outlier ***,we successfully adapted linear attention in FilterGNN with post-instance normalization support,which significantly reduces the complexity of complete graph learning from O(N2)to O(N).Experiments show that FilterGNN requires only 6%of the time cost and 33.3%of the memory cost compared with SuperGlue under a large-scale input size and achieves a competitive performance in various tasks,such as pose estimation,visual localization,and sparse 3D reconstruction.

关键词： image matching transformer linear attention visual localization sparse reconstruction

来源：评论

学校读者我要写书评

暂无评论

User Purchase Intention Prediction Based on Improved Deep Forest

引用

computer Modeling in Engineering & sciences 2024年第4期139卷 661-677页

作者： Yifan Zhang Qiancheng Yu Lisi Zhang School of Computer Science and Engineering North Minzu UniversityYinchuan750030China Laboratory of Graphics and Images of the State Ethnic Affairs Commission North Minzu UniversityYinchuan750030China

Widely used deep neural networks currently face limitations in achieving optimal performance for purchase intention prediction due to constraints on data volume and hyperparameter *** address this issue,based on the deep forest algorithm and further integrating evolutionary ensemble learning methods,this paper proposes a novel Deep Adaptive Evolutionary Ensemble(DAEE)*** model introduces model diversity into the cascade layer,allowing it to adaptively adjust its structure to accommodate complex and evolving purchasing behavior ***,this paper optimizes the methods of obtaining feature vectors,enhancement vectors,and prediction results within the deep forest algorithm to enhance the model’s predictive *** demonstrate that the improved deep forest model not only possesses higher robustness but also shows an increase of 5.02%in AUC value compared to the baseline ***,its training runtime speed is 6 times faster than that of deep models,and compared to other improved models,its accuracy has been enhanced by 0.9%.

关键词： Purchase prediction deep forest differential evolution algorithm evolutionary ensemble learning model selection

来源：评论

学校读者我要写书评

暂无评论

CSNet:A Count-Supervised Network via Multiscale MLP-Mixer for Wheat Ear Counting

引用

植物表型组学（英文） 2024年第4期6卷 995-1009页

作者： Yaoxi Li Xingcai Wu Qi Wang Zhixun Pei Kejun Zhao Panfeng Chen Gefei Hao State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China National Key Laboratory of Green Pesticide Key Laboratory of Green Pesticide and Agricultural BioengineeringMinistry of EducationGuiyang 550025China

Wheat is the most widely grown crop in the world,and its yield is closely related to global food *** number of ears is important for wheat breeding and yield ***,automated wheat ear counting techniques are essential for breeding high-yield varieties and increasing grain ***,all existing methods require position-level annotation for training,implying that a large amount of labor is required for annotation,limiting the application and development of deep learning technology in the agricultural *** address this problem,we propose a count-supervised multiscale perceptive wheat counting network(CSNet,count-supervised network),which aims to achieve accurate counting of wheat ears using quantity *** particular,in the absence of location information,CSNet adopts MLP-Mixer to construct a multiscale perception module with a global receptive field that implements the learning of small target attention maps between wheat ear *** conduct comparative experiments on a publicly available global wheat head detection dataset,showing that the proposed count-supervised strategy outperforms existing position-supervised methods in terms of mean absolute error(MAE)and root mean square error(RMSE).This superior performance indicates that the proposed approach has a positive impact on improving ear counts and reducing labeling costs,demonstrating its great potential for agricultural counting *** code is available at .

关键词： network counting csnet mlp-mixer multiscale supervised wheat

来源：评论

学校读者我要写书评

暂无评论

MPF-GAN: an enhanced architecture for 3D face reconstruction

引用

Multimedia Tools and Applications 2024年 1-18页

作者： Malah, Mehdi Abbas, Fayçal Agaba, Ramzi Bardou, Dalal Babahenini, Mohamed Chaouki Computer Science Department Mohamed Cherif Messaadia University-Souk Ahras Souk Ahras Algeria LESIA Laboratory Computer Science Department University of Abbes Laghrour Khenchela Khenchela Algeria ReLaCS2 Laboratory Computer Science Department University Larbi Ben Mhidi Oum El Bouaghi Algeria Computer Science and Mathematics Department University of Abbes Laghrour Khenchela Khenchela Algeria LESIA Laboratory Computer Science Department University of Mohamed Khider Biskra Biskra Algeria

In this article, we address the challenge of accurate 3D face reconstruction by proposing an enhanced architecture. We observe that using a single error calculation formula for the entire face leads to precise reconstruction of certain parts at the expense of others, particularly the eyes and mouth. We introduce a multi-task learning approach to address this issue, allowing our model to train on multiple data types. We propose a new analytical solution for mouth shape identification and its integration into the loss function optimization process. This solution resolves a problem that was often difficult to model in previous works accurately and has demonstrated improved reconstruction performance. In our research, we have also created and made available a new dataset for 3D face reconstruction. This dataset is unique as it focuses on different facial parts. The results show that our multi-task learning approach significantly improves the loss function for delicate facial parts, thus enhancing the quality of reconstruction in these specific areas. The code and data are publicly available on the project’s link: https://*** © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Robust tube-based MPC with smooth computation for dexterous robot manipulation

引用

science China(Information sciences) 2024年第11期67卷 252-268页

作者： Yu LUO Tianying JI Fuchun SUN Qie SIMA Huaping LIU Mingxuan JING Jianwei ZHANG Department of Computer Science and Technology Tsinghua University Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Department of Informatics University of Hamburg

Dexterous robot manipulation has shone in complex industrial scenarios, where multiple manipulators, or fingers, cooperate to grasp and manipulate objects. When encountering multi-objective optimization with system constraints in such scenarios, model predictive control(MPC) has demonstrated exceptional performance in complex multi-robot manipulation tasks involving multi-objective optimization with system constraints. However, in such scenarios, the substantial computational load required to solve the optimal control problem(OCP) at each triggering instant can lead to significant delays between state sampling and control application, hindering real-time performance. To address these challenges, this paper introduces a novel robust tube-based smooth MPC approach for two fundamental manipulation tasks: reaching a given target and tracking a reference trajectory. By predicting the successor state as the initial condition for imminent OCP solving, we can solve the forthcoming OCP ahead of time, alleviating delay effects. Additionally,we establish an upper bound for linearizing the original nonlinear system, reducing OCP complexity and enhancing response speed. Grounded in tube-based MPC theory, the recursive feasibility and closed-loop stability amidst constraints and disturbances are ensured. Empirical validation is provided through two numerical simulations and two real-world dexterous robot manipulation tasks, which shows that the seamless control input by our methods can effectively enhance the solving efficiency and control performance when compared to conventional time-triggered MPC strategies.

关键词： dexterous robot manipulation model predictive control smooth computation

来源：评论

学校读者我要写书评

暂无评论

Multi-Dimensional QoS Evaluation and Optimization of Mobile Edge Computing for IoT:A Survey

引用

Chinese Journal of Electronics 2024年第4期33卷 859-874页

作者： Jiwei HUANG Fangzheng LIU Jianbing ZHANG Beijing Key Laboratory of Petroleum Data Mining China University of Petroleum Department of Computer Science and Technology China University of Petroleum

With the evolvement of the Internet of things(IoT), mobile edge computing(MEC) has emerged as a promising computing paradigm to support IoT data analysis and processing. In MEC for IoT, the differentiated requirements on quality of service(QoS) have been growing rapidly, making QoS a multi-dimensional concept including several attributes, such as performance, dependability, energy efficiency, and economic factors. To guarantee the QoS of IoT applications, theories and techniques of multi-dimensional QoS evaluation and optimization have become important theoretical foundations and supporting technologies for the research and application of MEC for IoT,which have attracted significant attention from both academia and industry. This paper aims to survey the existing studies on multi-dimensional QoS evaluation and optimization of MEC for IoT, and provide insights and guidance for future research in this field. This paper summarizes the multi-dimensional and multi-attribute QoS metrics in Io T scenarios, and then several QoS evaluation methods are presented. For QoS optimization, the main research problems in this field are summarized, and optimization models as well as their corresponding solutions are elaborated. We take notice of the booming of edge intelligence in artificial intelligence-empowered Io T scenarios, and illustrate the new research topics and the state-of-the-art approaches related to QoS evaluation and optimization. We discuss the challenges and future research directions.

关键词： Internet of things Mobile edge computing Quality of service Quality of service evaluation Quality of service optimization

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：