检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Jin, Zhi Qiu, Yuwei Zhang, Kaihao Li, Hongdong Luo, Wenhan School of Intelligent Systems Engineering Sun Yat-sen University Shenzhen Campus Guangdong Shenzhen518107 China Guangdong Provincial Key Laboratory of Fire Science and Technology Guangzhou510006 China School of Intelligent Systems Engineering Sun Yat-sen University Shenzhen Campus Guangdong Shenzhen518107 China School of Computer Science and Technology Harbin Institute of Technology Shenzhen Campus Guangdong Shenzhen518055 China School of Engineering and Computer Science Australian National University CanberraACT2600 Australia Hong Kong University of Science and Technology Clear Water Bay Hong Kong

Recently, Transformer networks have demonstrated outstanding performance in the field of image restoration due to the global receptive field and adaptability to input. However, the quadratic computational complexity of Softmax-attention poses a significant limitation on its extensive application in image restoration tasks, particularly for high-resolution images. To tackle this challenge, we propose a novel variant of the Transformer. This variant leverages the Taylor expansion to approximate the Softmax-attention and utilizes the concept of norm-preserving mapping to approximate the remainder of the first-order Taylor expansion, resulting in a linear computational complexity. Moreover, we introduce a multi-branch architecture featuring multi-scale patch embedding into the proposed Transformer, which has four distinct advantages: 1) various sizes of the receptive field;2) multi-level semantic information;3) flexible shapes of the receptive field;4) accelerated training and inference speed. Hence, the proposed model, named the second version of Taylor formula expansion-based Transformer (for short MB-TaylorFormer V2) has the capability to concurrently process coarse-to-fine features, capture long-distance pixel interactions with limited computational cost, and improve the approximation of the Taylor expansion remainder. Experimental results across diverse image restoration benchmarks demonstrate that MB-TaylorFormer V2 achieves state-of-the-art performance in multiple image restoration tasks, such as image dehazing, deraining, desnowing, motion deblurring, and denoising, with very little computational overhead. The source code is available at https://***/FVL2020/MB-TaylorFormerV2. Copyright © 2025, The Authors. All rights reserved.

关键词： NP-hard

来源：评论

学校读者我要写书评

暂无评论

Cyber-Security Knowledge Graph Generation by Hierarchical Nonnegative Matrix Factorization

arXiv

引用

arXiv 2024年

作者： Barron, Ryan Eren, Maksim E. Bhattarai, Manish Wanna, Selma Solovyev, Nicholas Rasmussen, Kim Alexandrov, Boian S. Nicholas, Charles Matuszek, Cynthia Theoretical Division Los Alamos National Laboratory Los Alamos United States Advanced Research in Cyber Systems Los Alamos National Laboratory Los Alamos United States Department of Computer Science and Electrical Engineering University of Maryland Baltimore CountyMD United States

Much of human knowledge in cybersecurity is encapsulated within the ever-growing volume of scientific papers. As this textual data continues to expand, the importance of document organization methods becomes increasingly crucial for extracting actionable insights hidden within large text datasets. Knowledge Graphs (KGs) serve as a means to store factual information in a structured manner, providing explicit, interpretable knowledge that includes domain-specific information from the cybersecurity scientific literature. One of the challenges in constructing a KG from scientific literature is the extraction of ontology from unstructured text. In this paper, we address this topic and introduce a method for building a multi-modal KG by extracting structured ontology from scientific papers. We demonstrate this concept in the cybersecurity domain. One modality of the KG represents observable information from the papers, such as the categories in which they were published or the authors. The second modality uncovers latent (hidden) patterns of text extracted through hierarchical and semantic non-negative matrix factorization (NMF), such as named entities, topics or clusters, and keywords. We illustrate this concept by consolidating more than two million scientific papers uploaded to arXiv into the cyber-domain, using hierarchical and semantic NMF, and by building a cyber-domain-specific KG. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

VS-Net: A Voxel Encoding and Sparse Convolution Embedded Network for LiDAR 3D Object Detection

VS-Net: A Voxel Encoding and Sparse Convolution Embedded Net...

引用

2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022

作者： Liu, Meng Niu, Jianwei Liu, Yu The China North Artificial Intelligence and Innovation Research Institute Beijing100072 China The China North Vehicle Research Institute Beijing100072 China The State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing100191 China The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China The Hangzhou Innovation Institute Beihang University Hangzhou310051 China The Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou450001 China

ISBN: (纸本)9781665481090

Accurate and efficient 3D object detection in LiDAR point cloud is critical for autonomous driving. In this paper, we provide a solution for LiDAR-only detection which employs voxel features and a sparse convolution network. Specifically, we utilized voxel centers to encode point clouds' voxel features. Then, combining the sparse convolution method, we leveraged residual learning to design the backbone network. The detector output predicted results for multi-category and multi-object detection. Our method was evaluated on three popular and challenging datasets (KITTI, nuScence and Waymo). Experimental results demonstrated that the accuracy and speed (27.8 FPS) of our model could effectively support object detection for autonomous driving in various scenarios. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Adam-family methods for nonsmooth optimization with convergence guarantees

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 2398-2450页

作者： Nachuan Xiao Xiaoyin Hu Xin Liu Kim-Chuan Toh Institute of Operations Research and Analytics National University of Singapore Singapore School of Computer and Computing Science Hangzhou City University Hangzhou China State Key Laboratory of Scientific and Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China Department of Mathematics and Institute of Operations Research and Analytics National University of Singapore Singapore

In this paper, we present a comprehensive study on the convergence properties of Adam-family methods for nonsmooth optimization, especially in the training of nonsmooth neural networks. We introduce a novel two-timescale framework that adopts a two-timescale updating scheme, and prove its convergence properties under mild assumptions. Our proposed framework encompasses various popular Adam-family methods, providing convergence guarantees for these methods in training nonsmooth neural networks. Furthermore, we develop stochastic subgradient methods that incorporate gradient clipping techniques for training nonsmooth neural networks with heavy-tailed noise. Through our framework, we show that our proposed methods converge even when the evaluation noises are only assumed to be integrable. Extensive numerical experiments demonstrate the high efficiency and robustness of our proposed methods.

关键词： nonsmooth optimization stochastic subgradient methods Adam nonconvex optimization gradient clipping

来源：评论

学校读者我要写书评

暂无评论

VR content creation and exploration with deep learning: A survey

引用

Computational Visual Media 2020年第1期6卷 3-28页

作者： Miao Wang Xu-Quan Lyu Yi-Jun Li Fang-Lue Zhang State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China. Peng Cheng Laboratory Shenzhen 518000China School of Engineering and Computer Science Victoria University of WellingtonNew Zealand

Virtual reality(VR)offers an artificial,computer generated simulation of a real life *** originated in the 1960 s and has evolved to provide increasing immersion,interactivity,imagination,and *** deep learning systems are able to represent and compose information at various levels in a deep hierarchical fashion,they can build very powerful models which leverage large quantities of visual media *** of VR methods and applications has been significantly boosted by the recent developments in deep learning *** content creation and exploration relates to image and video analysis,synthesis and editing,so deep learning methods such as fully convolutional networks and general adversarial networks are widely employed,designed specifically to handle panoramic images and video and virtual 3 D *** article surveys recent research that uses such deep learning methods for VR content creation and *** considers the problems involved,and discusses possible future directions in this active and emerging research area.

关键词： virtual reality deep learning neural networks 360°image and video virtual content

来源：评论

学校读者我要写书评

暂无评论

GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability

arXiv

引用

arXiv 2024年

作者： Luo, Zihan Song, Xiran Huang, Hong Lian, Jianxun Zhang, Chenhao Jiang, Jinqi Xie, Xing Huazhong University of Science and Technology Wuhan China Microsoft Research Asia Beijing China The National Engineering Research Center for Big Data Technology and System Service Computing Technology and Systems Laboratory Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

Evaluating and enhancing the general capabilities of large language models (LLMs) has been an important research topic. Graph is a common data structure in the real world, and understanding graph data is a crucial part for advancing general intelligence. To evaluate and enhance the graph understanding abilities of LLMs, in this paper, we propose a benchmark named GraphInstruct, which comprehensively includes 21 classical graph reasoning tasks, providing diverse graph generation pipelines and detailed reasoning steps. Based on GraphInstruct, we further construct GraphLM through efficient instruction-tuning, which shows prominent graph understanding capability. In order to enhance the LLM with graph reasoning capability as well, we propose a step mask training strategy, and construct a model named GraphLM+. As one of the pioneering efforts to enhance the graph understanding and reasoning abilities of LLMs, extensive experiments have demonstrated the superiority of GraphLM and GraphLM+ over other LLMs. We look forward to more researchers exploring the potential of LLMs in the graph data mining domain through GraphInstruct. Our code for generating GraphInstruct is released publicly at: https://***/CGCL-codes/GraphInstruct. Copyright © 2024, The Authors. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Based Scheduling Strategy in Blockchain Payment Channel Networks

引用

IEEE/ACM Transactions on Networking 2024年

作者： Ren, Zhe Wang, Zihao Li, Xinghua Miao, Yinbin Li, Zhuowen Liu, Ximeng Han, Lei Deng, Robert H. Xidian University State Key Laboratory of Integrated Services Networks The School of Cyber Engineering Xi'an710071 China Ministry of Education Engineering Research Center of Big Data Security Xi'an710071 China Fuzhou University College of Mathematics and Computer Science Fuzhou350108 China Fuzhou University Fujian Provincial Key Laboratory of Information Security of Network Systems Fuzhou350116 China Beijing Institute of Computer Technology and Application Beijing100000 China Singapore Management University School of Information Systems Singapore178902 Singapore

With the popularity of blockchains, low transaction throughput has become a significant bottleneck in applications such as cryptocurrencies. Payment channel networks (PCNs) have received attention as a way to improve throughput. However, due to the difficulty of predicting future transactions for nodes, the transactions are prone to failure when the channel balances do not meet required conditions. It has been shown that increasing buffers (queues) in PCNs can increase the success rate of transactions and throughput. Nevertheless, there is no effective transaction scheduling strategy in buffers when transaction values are flexible and variable. To solve this problem, we first formulate the Scheduling Problem in PCNs (named PSP), and then prove it is NP-hard. We design a neural network solver based on the Sequence to Sequence (Seq2Seq) architecture and train the solver using the reinforcement learning method. With the solver, we first give two scheduling strategies to maximize transaction throughput, and then design a PCN simulator for performance evaluation. Extensive experiments are conducted to show the superiority and various performances of our proposal and illustrate that our proposal can get a significant advantage in terms of the transaction throughput compared to the existing works. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

CSQF-based Time-Sensitive Flow Scheduling in Long-distance Industrial IoT Networks

arXiv

引用

arXiv 2024年

作者： Huang, Yudong Huang, Tao Zhang, Xinyuan Wang, Shuo Du, Hongyang Niyato, Dusit Yu, Fei Richard The State Key Laboratory of Networking and Switching Technology BUPT Beijing100876 China The Purple Mountain Laboratories Nanjing211111 China The School of Computer Science and Engineering Nanyang Technological University Singapore The Department of Systems and Computer Engineering Carleton University OttawaONK1S 5B6 Canada

Booming time-critical services, such as automated manufacturing and remote operations, stipulate increasing demands for facilitating large-scale Industrial Internet of Things (IoT). Recently, a cycle specified queuing and forwarding (CSQF) scheme has been advocated to enhance the Ethernet. However, CSQF only outlines a foundational equipment-level primitive, while how to attain network-wide flow scheduling is not yet determined. Prior endeavors primarily focus on the range of a local area, rendering them unsuitable for long-distance factory interconnection. This paper devises the cycle tags planning (CTP) mechanism, the first integer programming model for the CSQF, which makes the CSQF practical for efficient global flow scheduling. In the CTP model, the per-hop cycle alignment problem is solved by decoupling the long-distance link delay from cyclic queuing time. To avoid queue overflows, we discretize the underlying network resources into cycle-related queue resource blocks and detail the core constraints within multiple periods. Then, two heuristic algorithms named flow offset and cycle shift (FO-CS) and Tabu FO-CS are designed to calculate the flows' cycle tags and maximize the number of schedulable flows, respectively. Evaluation results show that FO-CS increases the number of scheduled flows by 31.2%. The Tabu FO-CS algorithm can schedule 94.45% of flows at the level of 2000 flows. © 2024, CC BY.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

HEART: Achieving Timely Multi-Model Training for Vehicle-Edge-Cloud-Integrated Hierarchical Federated Learning

arXiv

引用

arXiv 2025年

作者： Yang, Xiaohong Liwang, Minghui Wang, Xianbin Cheng, Zhipeng Hosseinalipour, Seyyedali Dai, Huaiyu Jiao, Zhenzhen School of Informatics Xiamen University Fujian China Department of Control Science and Engineering The National Key Laboratory of Autonomous Intelligent Unmanned Systems Japan Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Tongji University Shanghai China Department of Electrical and Computer Engineering Western University ON Canada School of Future Science and Engineering Soochow University Suzhou China Department of Electrical Engineering University at Buffalo-SUNY BuffaloNY United States Department of Electrical and Computer Engineering NC State University RaleighNC United States iF-Labs Beijing Teleinfo Technology Company Ltd. CAICT Beijing China

The rapid growth of AI-enabled Internet of Vehicles (IoV) calls for efficient machine learning (ML) solutions that can handle high vehicular mobility and decentralized data. This has motivated the emergence of Hierarchical Federated Learning over vehicle-edge-cloud architectures (VEC-HFL). Nevertheless, one aspect which is underexplored in the literature on VEC-HFL is that vehicles often need to execute multiple ML tasks simultaneously, where this multi-model training environment introduces crucial challenges. First, improper aggregation rules can lead to model obsolescence and prolonged training times. Second, vehicular mobility may result in inefficient data utilization by preventing the vehicles from returning their models to the network edge. Third, achieving a balanced resource allocation across diverse tasks becomes of paramount importance as it majorly affects the effectiveness of collaborative training. We take one of the first steps towards addressing these challenges via proposing a framework for multi-model training in dynamic VEC-HFL with the goal of minimizing global training latency while ensuring balanced training across various tasks—a problem that turns out to be NP-hard. To facilitate timely model training, we introduce a hybrid synchronous-asynchronous aggregation rule. Building on this, we present a novel method called Hybrid Evolutionary And gReedy allocaTion (HEART). The framework operates in two stages: first, it achieves balanced task scheduling through a hybrid heuristic approach that combines improved Particle Swarm Optimization (PSO) and Genetic Algorithms (GA);second, it employs a low-complexity greedy algorithm to determine the training priority of assigned tasks on vehicles. Experiments on real-world datasets demonstrate the superiority of HEART over existing methods. © 2025, CC BY-NC-ND.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

On Reliably Decodable Information Bits of Linear Codes

On Reliably Decodable Information Bits of Linear Codes

引用

IEEE International Symposium on Information Theory

作者： Yixin Wang Xiao Ma School of Systems Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Information Security Technology Sun Yat-Sen University Guangzhou China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China

It is well-known that a linearly coded vector over an erasure channel can be decoded uniquely if the sub-generator matrix formed by the unerased columns has full row rank. This property is generalized in this paper to a necessary and sufficient condition for an information bit to be retrieved uniquely from a received vector with erasures. We show that an information bit of a linear code can be uniquely decodable if and only if its corresponding row of the sub-generator matrix is linearly independent from the other rows. Then we prove that, for semi-random linear codes over binary-input output-symmetric (BIOS) memoryless channels, the information bits associated with the random part of the generator matrices can be decoded with arbitrarily small error probability as the codelength increases. This in turn is applied to prove the coding theorem for time-invariant convolutional codes.

关键词：

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：