检索结果-内蒙古大学图书馆

International Conference on Parallel and Distributed systems (ICPADS)

作者： Qiyu Li Xianxian Li Haodong Qian De Li Jinyan Wang Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Guangxi Key Lab of Multi-Source Information Mining and Security Guangxi Normal University Guilin China School of Computer Science and Engineering Guangxi Normal University Guilin China

Graph Neural Networks (GNNs) have emerged as promising tools in graph semi-supervised learning. They acquire low-dimensional node embeddings for downstream tasks by aggregating and updating features from neighboring nodes. However, in a semi-supervised setting, the availability of labeled node information is limited, resulting in the underutilization of vast amounts of unlabeled node information. Current research integrates contrastive learning with graph semi-supervised learning to better use this unlabeled node information. Nevertheless, the differences between cross-entropy and self-supervised contrastive loss are often overlooked. To address this issue, we propose a novel relaxed graph contrastive semi-supervised learning method. We analyze the difference between nodes correctly classified under cross-entropy loss and self-supervised contrastive loss. Inspired by this, we design a relaxed contrastive loss that considers the node features optimized under these two loss functions, thereby expanding the positive sample set. Furthermore, to ensure the quality of the positive sample set, we introduce a threshold constraint based on feature similarity and prediction results to select more reliable positive samples. The experimental results indicate that our method exhibits competitive performance across most datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Field Trial on DTMB-A for the Coverage Performance of HDTV Program Under High Mobility and Spectrum Efficiency

Field Trial on DTMB-A for the Coverage Performance of HDTV P...

引用

IEEE International Conference on Electrical engineering and Photonics (EExPolytech)

作者： Jian Song Changyong Pan Kewu Peng Hui Yang Wenxiu Guo Xiaotao Jiang Zongze Li Department of Electronic Engineering Beijing National Research Center for Information Science and Technology (BNRist) Tsinghua University Beijing China Shenzhen International Graduate School Tsinghua University Shenzhen China Peng Cheng Laboratory Shenzhen China Shenzhen City Key Laboratory of Digital TV System Shenzhen China

The coverage performance for Digital Television/ Terrestrial Multimedia Broadcasting-Advance system and 3GPP “Further evolved Multimedia Broadcast Multicast Service”, long-term evolution-based broadcasting system defined by release 16 (R16) with different working parameters has been evaluated through the field trial in Shenzhen with a focus on high-speed mobility car with reasonably high spectrum efficiency. The trial uses the same transmitter facility of same the RF hardware, at the same frequency and with the same power. Results show that terrain is major deterministic factor for coverage performance for each system and well-designed longer time-interleaver for R16 is indispensable to users' satisfaction under this application scenario.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bi-Directional Multi-Scale Graph Dataset Condensation via information Bottleneck 39

Bi-Directional Multi-Scale Graph Dataset Condensation via In...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Fu, Xingcheng Gao, Yisen Yang, Beining Wu, Yuxuan Qian, Haodong Sun, Qingyun Li, Xianxian Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University China Institute of Artificial Intelligence Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China University of Edinburgh Edinburgh United Kingdom

ISBN: (纸本)157735897X

Dataset condensation has significantly improved model training efficiency, but its application on devices with different computing power brings new requirements for different data sizes. Thus, condensing multiple scale graphs simultaneously is the core of achieving efficient training in different on-device scenarios. Existing efficient works for multi-scale graph dataset condensation mainly perform efficient approximate computation in scale order (large-to-small or small-to-large scales). However, for non-Euclidean structures of sparse graph data, these two commonly used paradigms for multi-scale graph dataset condensation have serious scaling down degradation and scaling up collapse problems of a graph. The main bottleneck of the above paradigms is whether the effective information of the original graph is fully preserved when consenting to the primary sub-scale (the first of multiple scales), which determines the condensation effect and consistency of all scales. In this paper, we proposed a novel GNN-centric Bi-directional Multi-Scale Graph Dataset Condensation (BiMSGC) framework, to explore unifying paradigms by operating on both large-to-small and small-to-large for multi-scale graph condensation. Based on the mutual information theory, we estimate an optimal “meso-scale” to obtain the minimum necessary dense graph preserving the maximum utility information of the original graph, and then we achieve stable and consistent “bi-directional” condensation learning by optimizing graph eigenbasis matching with information bottleneck on other scales. Encouraging empirical results on several datasets demonstrates the significant superiority of the proposed framework in graph condensation at different scales. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Trajectory Control for Wheeled Mobile Robots Robot with Longitudinal Slippage

Trajectory Control for Wheeled Mobile Robots Robot with Long...

引用

Robotics, Intelligent Control and Artificial Intelligence (RICAI), International Conference on

作者： Tianlong Li Mengwei Ren Jian Du Jianjun Bai Tao Sun School of Modern Information Technology Zhejiang Institute of Mechanical & Electrical Engineering School of Automation Hangzhou Dianzi University Hangzhou P. R. China Key Lab for IOT and Information Fusion Technology of Zhejiang Hangzhou P. R. China China Datang Corporation Science and Technology General Research Institute Ltd. P. R. China

This article addresses the trajectory tracking control problem of a mobile robot with unknown longitudinal slip by introducing the slip ratio and an adaptive method for stability. We establish a kinematic model of Wheeled Mobile Robots (WMR) and design a new Lyapunov equation to extend the attractive domain of steering angle error. Cross terms are introduced to eliminate the need for separate consideration of the traditional Lyapunov equation. Unknown slip is represented as an unknown parameter in the kinematic model and estimated using an adaptive law. The asymptotic stability of the tracking error system is proved. Our proposed control law demonstrates improved stability and effectiveness compared to two reference trajectories, as confirmed by simulations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Assembly of two-dimensional nanofluidic channel with high proton conductivity using single-layer MnO_(2) nanosheets

引用

science China Materials 2022年第9期65卷 2578-2584页

作者： Hongrun Jin Jia Li Zheheng Xu Zhimi Hu Kaisi Liu Kang Liu Jiangjiang Duan Bin Hu Liang Huang Jun Zhou Wuhan National Laboratory for Optoelectronics School of Optical and Electronic InformationHuazhong University of Science and TechnologyWuhan 430074China Rolls-Royce@NTU Corporate Lab Nanyang Technological UniversitySingapore 639798Singapore MOE Key Laboratory of Hydraulic Machinery Transients School of Power and Mechanical EngineeringWuhan UniversityWuhan 430072China

Two-dimensional(2D)single-layer δ-MnO_(2)(SLMO)with cations intercalated in the interlayers demonstrates specific structural characteristics,possessing superiority in the fields such as energy storage,catalysis,and ***,the synthesis technology of large-lateral-size SLMO nanosheets with high uniformity is rare,which hinders their correlated ***,we report an intercalation-assisted exfoliation approach to produce large-sized SLMO nanosheets with high dispersity in aqueous ***-layer K^(+)-intercalated δ-MnO_(2)(KMnO)nanosheets were used as a precursor to ensure complete *** account of high dispersion and ultrathin 2D morphology,SLMO nanosheets self-assembled into a flexible and free-standing film to construct ordered nanochannels.A high surface charge density of 1.71 mC m^(-2) and proton mobility of 2.59×10^(-3) cm^(2) V^(-1) s_(-1) were achieved in the free-standing SLMO *** the extraordinary properties and easily scaled fabrication of the 2D SLMO film,this approach will pave the way for the study of confined ion transportation and enable the easy construction of nanofluidic devices.

关键词： two-dimensional ion-intercalated manganese oxide exfoliation nanofluidic channel ionic conductivity

来源：评论

学校读者我要写书评

暂无评论

Cost Efficient Service Mesh Controller Placement for Edge Native Computing

Cost Efficient Service Mesh Controller Placement for Edge Na...

引用

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Yuepeng Li Deze Zeng Lvhao Chen Lin Gu Weiyin Ma Feng Gao School of Computer Science China University of Geosciences Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology China School of Biomedical Engineering and Informatics Nanjing Medical University Nanjing China Research Center for Cyber-Physical-Social System Zhejiang Lab Hangzhou China

ISBN: (纸本)9781665435413

Cloud native computing featured by microservice has been regarded as a compelling trend in cloud application development. Edge computing, as an alternative or complemen-tary to cloud computing, is potential to expand the microservice to edge computing, simplifying the development and deployment of edge applications. Despite that, there is still a challenge on how to manage the microservices efficiently in the open and heterogeneous distributed environment. To this end, service mesh provides a potential solution in efficient microservices management. However, as a traditional cloud-oriented architecture, it can not be applied into edge computing directly since the centralized controller policy. To address this problem, in this paper, we propose an edge service mesh architecture with distributively deployed controllers for edge native computing. We further inves-tigate the problem on how to deploy these distributive controllers in a cost efficient manner with the consideration of control cost and the synchronization cost. The problem is formulated into a non-linear optimization form and then linearized into an integer linear programming (ILP) problem. To tackle the computation complexity, we then come up with a customized k-means based algorithm (i.e., ck-means) in polynomial computation complexity. The experimental results verify the efficiency of our ck-means algorithm in comparison with the traditional k-means algorithm.

关键词： Cloud computing Costs Heuristic algorithms Microservice architectures Computer architecture Synchronization Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency

arXiv

引用

arXiv 2025年

作者： Shen, Jiangrong Xu, Qi Pan, Gang Chen, Badong Faculty of Electronic and Information Engineering Xi’an Jiaotong University China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China State Key Lab of Brain-Machine Intelligence Zhejiang University China National Key Lab of Human-Machine Hybrid Augmented Intelligence Xi’an Jiaotong University China School of Computer Science Dalian University of Technology China

The human brain utilizes spikes for information transmission and dynamically reorganizes its network structure to boost energy efficiency and cognitive capabilities throughout its lifespan. Drawing inspiration from this spike-based computation, Spiking Neural Networks (SNNs) have been developed to construct event-driven models that emulate this efficiency. Despite these advances, deep SNNs continue to suffer from over-parameterization during training and inference, a stark contrast to the brain’s ability to self-organize. Furthermore, existing sparse SNNs are challenged by maintaining optimal pruning levels due to a static pruning ratio, resulting in either under or over-pruning. In this paper, we propose a novel two-stage dynamic structure learning approach for deep SNNs, aimed at maintaining effective sparse training from scratch while optimizing compression efficiency. The first stage evaluates the compressibility of existing sparse subnetworks within SNNs using the PQ index, which facilitates an adaptive determination of the rewiring ratio for synaptic connections based on data compression insights. In the second stage, this rewiring ratio critically informs the dynamic synaptic connection rewiring process, including both pruning and regrowth. This approach significantly improves the exploration of sparse structures training in deep SNNs, adapting sparsity dynamically from the point view of compression efficiency. Our experiments demonstrate that this sparse training approach not only aligns with the performance of current deep SNNs models but also significantly improves the efficiency of compressing sparse SNNs. Crucially, it preserves the advantages of initiating training with sparse models and offers a promising solution for implementing Edge AI on neuromorphic hardware. © 2025, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PGUD: Personalized Graph Universal Defense

PGUD: Personalized Graph Universal Defense

引用

International Conference on Parallel and Distributed systems (ICPADS)

作者： Zeming Gan Linlin Su Xianxian Li Jinyan Wang Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Guangxi Key Lab of Multi-Source Information Mining and Security Guangxi Normal University Guilin China School of Computer Science and Engineering Guangxi Normal University Guilin China

Extensive evidence shows that Graph Neural Networks (GNNs) are vulnerable to adversarial attacks. Previous work has made great efforts to improve the performance and usability of GNNs, but they remain sensitive and vulnerable to local attacks. Local attacks slightly perturb the target nodes, resulting in misclassification of GNNs on these specific nodes. Graph Universal Defense (GUD) is proposed to generate a defense patch to protect important nodes in a graph from local attacks. However, the research on GUD is still in the preliminary stage. The unique patch does not adaptively protect different nodes, and it has weak robustness against strong local attacks. To address this problem, we propose Personalized Graph Universal Defense (PGUD). It maps nodes into several clusters, each corresponding to a personalized defense patch. We further instantiate a class-specific PGUD. From a perspective of effective perturbation at minimal cost, we theoretically derive the potential attacker nodes manipulated by the adversary, and use patches to mitigate their impact on target nodes. Experimental results show that our approach can be efficiently integrated into any GNN for downstream tasks and provide effective protection for different target nodes in a personalized manner. Our method significantly improves the robustness against local attacks compared to prior work and can be easily scaled to large graphs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multimedia Approach to Problem Descriptions for Fine-Grained Detail Characterization

A Multimedia Approach to Problem Descriptions for Fine-Grain...

引用

IEEE International Requirements engineering Conference Workshops (REW)

作者： Bowen Zheng Zhi Li Hongbin Xiao School of Computer Science and Engineering Guangxi Normal University Guilin China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Guangxi Key Lab of Multi-Source Information Mining and Security Guangxi Normal University Guilin China

Requirements analysis has always been regarded as the starting point and focus of requirements engineering. The Problem Frames (PF) approach provides a problem-oriented requirements analysis method by describing the software's operating environment in detail. It can effectively bridge the gap between requirements analysis and system design. However, an intuitive and convenient means of elaborating the rich details of complex requirements and their contexts is missing from the literature. Currently, the main methods for describing requirements are through textual descriptions or formal language descriptions, which can result in the PF model containing a large amount of textual representations, and increasing the difficulty and time required for user understanding. In this paper, we present the PF2Detail, a tool that enables fine-grained descriptions of the PF model. Building upon the PF model construction, PF2Detail incorporates multimedia to describe complex requirements in context. Each node in the model can include multimedia, text, or formal language to provide detailed characterizations. Additionally, users can view detailed information about any node in the model and navigate the entire model, aiming to enhance the level of details in the PF model descriptions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scene 3-D Reconstruction system in Scattering Medium

arXiv

引用

arXiv 2023年

作者： Zhang, Zhuoyifan Zhang, Lu Wang, Liang Wu, Haoming School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China School of Information and Communication Engineering Hainan University Haikou China School of Computer Science and Technology Hainan University Haikou China RobAI-Lab Hainan University China

The research on neural radiance fields for new view synthesis has experienced explosive growth with the development of new models and extensions. The NERF algorithm, suitable for underwater scenes or scattering media, is also evolving. Existing underwater 3D reconstruction systems still face challenges such as extensive training time and low rendering efficiency. This paper proposes an improved underwater 3D reconstruction system to address these issues and achieve rapid, high-quality 3D *** begin with, we enhance underwater videos captured by a monocular camera to correct the poor image quality caused by the physical properties of the water medium while ensuring consistency in enhancement across adjacent frames. Subsequently, we perform keyframe selection on the video frames to optimize resource utilization and eliminate the impact of dynamic objects on the reconstruction results. The selected keyframes, after pose estimation using COLMAP, undergo a three-dimensional reconstruction improvement process using neural radiance fields based on multi-resolution hash coding for model construction and rendering. © 2023, CC BY-NC-SA.

关键词： Image enhancement

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：