检索结果-内蒙古大学图书馆

Towards practical data alignment in production federated learning

Frontiers of computer science 2025年第1期19卷 167-169页

作者： Yexuan SHI Wei YU Yuanyuan ZHANG Chunbo XUE Yuxiang ZENG Zimu ZHOU Manxue GUO Lun XIN Wenjing NIE State Key Laboratory of Complex&Critical Software Environment and Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang UniversityBeijing 100191China Zhongguancun Pan Connected Mobile Communication Technology Innovation and Application Research Institute Beijing 100088China China Mobile Research Institute Beijing 100053China School of Data Science City University of Hong KongHong Kong 999077China

1 Introduction Federated learning has emerged as a promising par-adigm for collaborative model training that facilitates cooperation among multiple parties while ensuring data privacy[1].Successful alignment of data across parties is crucial for effective federated learning[2].This alignment involves harmonizing heterogeneous data from different parties to identify shared data for joint model *** set intersection(PSI)is a technique that allows the alignment of common entities between parties without revealing additional ***,efficiently performing data alignment with PSI in federated learning[3],especially when dealing with highly unbalanced data,remains challenging due to the low efficiency.

关键词： alignment dealing parties

来源：评论

学校读者我要写书评

暂无评论

Building Modeling Tools Based on Metamodeling and Product Line Technologies

引用

Chinese Journal of Electronics 2025年第2期23卷 219-226页

作者： Zhiyi Ma Xiao He Software Institute School of Electronics Engineering and Computer Science Peking University Beijing China Key Laboratory of High Confidence Software Technologies (Peking University) Ministry of Education Beijing China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

With the evolution of existing modeling languages and the emergence of more and more new modeling languages, it is necessary to rapidly build the corresponding software modeling tools with good quality. However, modeling tools for larger modeling languages are usually diversity in function and complexity in implementation technology. Taking building modeling tools as a domain, this paper presents an approach to building software modeling tools based on metamodeling and product line technologies. The paper provides the concept system of the approach and a feature model from diverse functions of modeling tools in order to specify the commonality and variability of the tools by deeply making the domain analysis, discusses the design and implementation of a general tool framework that provides the conveniences for reusing components and generating code for components, and specifies the mapping between the feature model and the components for modeling tools.

关键词： Analytical models Codes Buildings Metamodeling software Complexity theory Research and development

来源：评论

学校读者我要写书评

暂无评论

Meta-Learning-based Safety-Critical Control in Multi-Obstacles Environments

引用

IEEE Transactions on Automation science and Engineering 2025年 22卷 15299-15313页

作者： Zhang, Yu Wen, Long Huang, Yuhong Sun, Siming Bing, Zhenshan He, Wei Knoll, Alois Technical University of Munich Department of Computation Information and Technology Garching85748 Germany Nanjing University State Key Laboratory for Novel Software Technology School of Science and Technology Suzhou Campus China Beijing Information Science and Technology University School of Automation Institute of Artificial Intelligence Beijing102206 China University of Science and Technology Beijing School of Intelligence Science and Technology Institute of Artificial Intelligence Beijing100083 China

Autonomous robots operating in diverse scenarios are expected to safely and efficiently adapt to new, unknown, and cluttered environments. In this paper, we introduce a real-time goal-seeking and exploration framework incorporating novel meta-signed distance functions (MetaSDFs) and metabuffer robust control barrier functions (Meta-BRCBFs). To adapt to environmental changes in real time, we employ Bayesian meta-learning to construct MetaSDFs. Deep neural network weights are initially trained offline, followed by efficient online adaptation at the last Bayesian layer, allowing for online updates at linear time complexity. Each MetaSDF is individually trained for its corresponding obstacle class, enhancing online distance estimation accuracy. Subsequently, buffer zones are constructed around the MetaSDFs to establish corresponding Meta-BRCBFs. These Meta-BRCBFs are activated only when the robot enters these zones, substantially reducing the number of CBFs required. Outside these specified buffer zones, the robot remains in goal-seeking mode, focusing on task completion. After entering a buffer zone, it transitions to exploration mode, prioritizing safety and exploring safe pathways, effectively balancing task execution with environmental adaptability. We demonstrate that, under this framework, the system achieves both safety and asymptotic stabilization. Extensive simulations and experiments are conducted to demonstrate our framework’s effectiveness in both simulated scenarios and real-world environments. These tests confirm our framework’s real-time capabilities and safety assurances in dynamic settings where state-of-the-art methods fail. © 2004-2012 IEEE.

关键词： Robust control

来源：评论

学校读者我要写书评

暂无评论

Dynamic Graph Transformer with Correlated Spatial-Temporal Positional Encoding 25

Dynamic Graph Transformer with Correlated Spatial-Temporal P...

引用

18th ACM International Conference on Web Search and Data Mining, WSDM 2025

作者： Wang, Zhe Zhou, Sheng Chen, Jiawei Zhang, Zhen Hu, Binbin Feng, Yan Chen, Chun Wang, Can Zhejiang University College of Computer Science Hangzhou China Zhejiang University School of Software Technology Ningbo China Zhejiang University The State Key Laboratory of Blockchain and Data Security Hangzhou China National University of Singapore Singapore Singapore Ant Group Hangzhou China

ISBN: (纸本)9798400713293

Learning effective representations for Continuous-Time Dynamic Graphs (CTDGs) has garnered significant research interest, largely due to its powerful capabilities in modeling complex interactions between nodes. A fundamental and crucial requirement for representation learning in CTDGs is the appropriate estimation and preservation of proximity. However, due to the sparse and evolving characteristics of CTDGs, the spatial-temporal properties inherent in high-order proximity remain largely unexplored. Despite its importance, this property presents significant challenges due to the computationally intensive nature of personalized interaction intensity estimation and the dynamic attributes of CTDGs. To this end, we propose a novel Correlated Spatial-Temporal Positional encoding that incorporates a parameter-free personalized interaction intensity estimation under the weak assumption of the Poisson Point Process. Building on this, we introduce the Dynamic Graph Transformer with Correlated Spatial-Temporal Positional Encoding (CorDGT), which efficiently retains the evolving spatial-temporal high-order proximity for effective node representation learning in CTDGs. Extensive experiments on seven small and two large-scale datasets demonstrate the superior performance and scalability of the proposed CorDGT. The code is available at: https://***/wangz3066/CorDGT. © 2025 Copyright held by the owner/author(s).

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Dancer: Dynamic Compression and Quantization Architecture for Deep Graph Convolutional Network

Dancer: Dynamic Compression and Quantization Architecture fo...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Yunhao Dong Zhaoyu Zhong Yi Wang Chenlin Ma Tianyu Wang College of Computer Science and Software Engineering Shenzhen University Shenzhen China State Key Laboratory of Radio Frequency Heterogeneous Integration

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

Graph Convolutional Networks (GCNs) have been widely applied in fields such as social network analysis and recommendation systems. Recently, deep GCNs have emerged, enabling the exploration of deeper hidden information. Compared to traditional shallow GCNs, deep GCNs feature significantly more layers, leading to considerable computational and data movement challenges. Processing-In-Memory (PIM) offers a promising solution for efficiently handling GCNs by enabling near-data computation, thus reducing data transfer between processing units and memory. However, previous work mainly focused on shallow GCNs and has shown limited performance with deep GCNs. In this paper, we present Dancer, an innovative PIM-based GCN accelerator. Dancer optimizes data movement during the inference process, significantly improving efficiency and reducing energy consumption. Specifically, we introduce a novel compressed graph storage architecture and a dynamic quantization technique to minimize data transfers at each layer of the GCN. Additionally, through a detailed analysis of weight dynamics changes, we propose a sparsity propagation strategy to further alleviate the computational and data transfer burden between layers. Experimental results demonstrate that, compared to current state-of-the-art methods, Dancer achieves 3.7× speedup, 7.6× energy efficiency, and reduces of 9.6× DRAM access on average.

关键词： Training Energy consumption Quantization (signal) Graph convolutional networks Social networking (online) Memory management Random access memory Europe Data transfer Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Minimum Initial Marking Estimation in Labeled Petri Nets Using Minimum Token Number Prediction

引用

IEEE Transactions on Automatic Control 2025年第5期70卷 3296-3302页

作者： Yue, Hao Xu, Yakun Hu, Hesuan Wu, Weimin Li, Lingxi College of Computer Science and Technology Qingdao266580 China Xidian University School of Electro-Mechanical Engineering Xi'an710071 China Nanyang Technological University School of Computer Science and Engineering College of Engineering 639798 Singapore Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China Zhejiang University Institute of Cyber-Systems and Control Hangzhou310027 China Purdue University Elmore Family School of Electrical and Computer Engineering College of Engineering IndianapolisIN46202 United States

This article proposes an approach to addressing the problem of minimum initial marking (MuIM) estimation for labeled Petri nets (LPNs). We introduce the important concept of a label synthesis net for LPNs and develop a method for predicting the minimum number of tokens. By using this prediction method, we develop an algorithm that has polynomial complexity in the length of the observed label sequence for estimating MuIMs. An illustrative example is provided to show the effectiveness and efficiency of our proposed approach. Moreover, experimental results demonstrate its advantage over existing work. Finally, we provide a comparison of some representative studies in the literature for MuIM estimation. © 1963-2012 IEEE.

关键词： Discrete event simulation

来源：评论

学校读者我要写书评

暂无评论

CODESWIFT: Accelerating LLM Inference for Efficient Code Generation

arXiv

引用

arXiv 2025年

作者： Zhao, Qianhui Zhang, Li Liu, Fang Lian, Xiaoli Meng, Qiaoyuanhe Jiao, Ziqian Zhou, Zetong Zhang, Borui Guo, Runlin Li, Jia School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Beihang University China Key Lab of High Confidence Software Technology Peking University China

Code generation is a latency-sensitive task that demands high timeliness, but the autoregressive decoding mechanism of Large Language Models (LLMs) leads to poor inference efficiency. Existing LLM inference acceleration methods mainly focus on standalone functions using only built-in components. Moreover, they treat code like natural language sequences, ignoring its unique syntax and semantic characteristics. As a result, the effectiveness of these approaches in code generation tasks remains limited and fails to align with real-world programming scenarios. To alleviate this issue, we propose CODESWIFT, a simple yet highly efficient inference acceleration approach specifically designed for code generation, without comprising the quality of the output. CODESWIFT constructs a multi-source datastore, providing access to both general and project-specific knowledge, facilitating the retrieval of high-quality draft sequences. Moreover, CODESWIFT reduces retrieval cost by controlling retrieval timing, and enhances efficiency through parallel retrieval and a context- and LLM preference-aware cache. Experimental results show that CODESWIFT can reach up to 2.53× and 2.54× speedup compared to autoregressive decoding in repository-level and standalone code generation tasks, respectively, outperforming state-of-the-art inference acceleration approaches by up to 88%. Our code and data are available at https://***/r/CodeSwift. Copyright © 2025, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Small Signal Stability-Guaranteed Moving Target Defense Against Load Redistribution Attack On IoT-based Smart Grid

引用

IEEE Internet of Things Journal 2025年第11期12卷 17413-17429页

作者： Wang, Bingdong Zhang, Zhenyong Wang, Mufeng Liu, Mengxiang Ye, Rui Deng, Ruilong Zhang, Xin Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China China Industrial Control Systems Cyber Emergency Response Team Beijing100040 China University of Sheffield Department of Automatic Control and System Engineering Sheffield United Kingdom Guizhou Power Grid Co. Ltd. Intelligent Operation Center China Zhejiang University State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Hangzhou310027 China Huzhou Institute of Industrial Control Technology Huzhou313000 China

Moving target defense (MTD) is a promising approach to defend against load redistribution attacks on the internet-of-things (IoT)-based smart grid networks by probing the distorted state estimates with the distributed flexible AC transmission system. However, existing studies mainly focus on optimizing the performance of MTD and ignore the safety effect of it on the system’s operation. In this paper, we fill this gap by deeply analyzing the effect of MTD on the small signal stability and aim to alleviate the negative impact and guarantee its defending performance simultaneously. Firstly, the stability is formally described using the eigenvalue sensitivity. The relationship between the MTD-induced perturbation (MTDper) and the stability criteria is derived. Secondly, a new indicator is proposed to measure the effectiveness of MTDper. Thirdly, a constrained optimization problem is formulated to compute the bound of MTDper for guaranteeing the small signal stability. In addition, a surprising finding is that the stability margin can be improved and enhanced by optimizing the value of MTDper without losing the MTD’s effectiveness. Finally, we evaluate the performance of MTDper and its impact on the small signal stability with extensive simulations on the IEEE 30-bus, 39-bus, and 68-bus test power systems. © 2014 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Refining Boundary Sample Space for Differentiable Rendering 16

Refining Boundary Sample Space for Differentiable Rendering

引用

2024 16th International Conference on Graphics and Image Processing, ICGIP 2024

作者： Gao, Ruicheng Qi, Yue State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Jingdezhen Research Institute Beihang University Jingdezhen333000 China Qingdao Research Institute Beihang University Qingdao266104 China

ISBN: (数字)9781510688780

ISBN: (纸本)9781510688773

The objective of physics-based differentiable rendering (PBDR) is to propagate gradients between scene parameters and the intensities of image pixels in a manner that is physically correct. The gradients obtained can be applied in optimization algorithms for the reconstruction of 3D geometry or materials, or they can be further propagated into neural network to learn neural representations of the scene. However, applying automatic differentiation techniques directly to the primary rendering process will result in biased gradients, as the rendering integral contains moving high-dimensional discontinuities. Based on how these discontinuities are managed-either implicitly or explicitly-existing PBDR methods can be categorized into two groups: reparameterization methods and boundary sampling methods. Boundary sampling methods need to construct paths that have one segment tangent to the geometry being differentiated in order to estimate a boundary integral to address the discontinuities explicitly. Such paths are usually constructed by sampling the tangent segment first and then extending it to complete the paths for subsequent processing. Fortunately, the number of dimensions in the space composed of such tangent segments is only three. In scenes comprised solely of triangle meshes, the first dimension is used to parameterize all the edges on the mesh, which determines a point on the tangent segment. The remaining two dimensions are used to parameterize the direction of the tangent segment. However, state-of-the-art boundary sampling methods parameterize the first dimension uniformly, which is inefficient because only a small portion of the edges contributes to the boundary integral, resulting in wasted parameter space. In this paper, we parameterize the first dimension by considering both edge length and contributions, thereby allocating more parameter space to important edges. Experiments demonstrate that our methods achieve lower variance gradients in the forward dif

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Pairing-Free Blockchain-Assisted Certificateless Aggregation Signcryption Scheme for VANETs

引用

IEEE Internet of Things Journal 2025年第11期12卷 15545-15557页

作者： Wang, Yahui Peng, Cong Jia, Xiaoying Wen, Jiaming Zhang, Yuanyuan Xinyang Normal University School of Computer and Information Technology School of Software Xinyang464000 China Wuhan University School of Cyber Science and Engineering Wuhan430072 China South-Central Minzu University School of Mathematics and Statistics Wuhan430074 China Wuhan University Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan430072 China University of Wollongong Institute of Cybersecurity and Cryptology School of Computing and Information Technology WollongongNSW2522 Australia Hubei University of Technology School of computer science Wuhan430072 China

Smart vehicle applications play a crucial role in intelligent transportation systems, enabling sensor-equipped vehicles to establish dynamic networks for efficient collection, sharing, and aggregation. This significantly enhances road security and efficiency by transmitting crucial information to traffic authorities. However, partial research on certificateless aggregation signcryption (CLAS) scheme reveals an intriguing phenomenon where each proposed scheme consistently exhibits numerous security vulnerabilities, particularly susceptible to public key replacement attacks. To address these challenges, this paper proposes a blockchain-assisted certificateless aggregation sign-cryption scheme (BACLAS), leveraging blockchain technology to securely store users' public key on a distributed ledger and prevent public key replacement attacks effectively. Furthermore, it is a provably secure communication scheme for real-world Vehicle-to-Infrastructure (V2I) communication while addressing practical security concerns. The BACLAS scheme ensures security in terms of existential unforgeability against adaptive chosen message attacks (EUF-CMA) and indistinguishability against adaptive chosen ciphertext attacks (IND-CCA2) based on the hardness assumption of the elliptic curve discrete logarithm problem and computational Diffie-Hellman problem in the random oracle model. The proposed scheme effectively reduces computational costs and time consumption, resulting in a significant reduction of the computation burden ranging from 50.02% to 88.28% compared to other competitive schemes. Moreover, it successfully addresses the key-escrow problem, thereby achieving enhanced security properties. © 2014 IEEE.

关键词： Vehicular ad hoc networks

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：