检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Xi Zhang, Siwei Xiong, Yun Wu, Xixi Zhang, Jiawei Sun, Xiangguo Zhang, Yao Zhao, Feng Kang, Yulin Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China IFM Lab Department of Computer Science University of California DavisCA United States Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong Ant Group Shanghai Hangzhou China

Temporal Interaction Graphs (TIGs) are widely utilized to represent real-world systems, such as e-commerce and social networks. To facilitate representation learning on TIGs, researchers have proposed a series of TIG models. However, these models are still facing two tough gaps between the pre-training and downstream predictions in their "pre-train, predict" training paradigm. First, there is a temporal gap that exhibits limited accommodation ability to their timely predictions. This shortcoming severely undermines their applicability in distant future predictions on the dynamically evolving TIG data. Second, there is a semantic gap due to the lack of versatility in these pre-trained models to effectively cater to diverse downstream tasks. This hinders their practical applications, as they struggle to align with their learning and prediction capabilities across various application scenarios. Recently, the "pre-train, prompt" paradigm has emerged as a lightweight mechanism for model generalization. Therefore, applying this paradigm within TIGs is a potential solution to solve the aforementioned challenges. However, the adaptation of this paradigm to TIGs is not straightforward. The prevalent application of prompting in static graph contexts falls short in temporal settings due to a lack of consideration for time-sensitive dynamics and a deficiency in expressive power. To address this issue, we introduce Temporal Interaction Graph Prompting (TIGPrompt), a versatile framework that seamlessly integrates with existing TIG models, bridging both the temporal and semantic gaps mentioned above. In detail, we propose a temporal prompt generator to offer temporally-aware prompts for different tasks. These prompts stand out for their minimalistic design, relying solely on the fine-tuning of the prompt generator with very little supervision data, which is extremely efficient. To cater to varying computational resource demands, we propose an extended "pre-train, prompt-based fine

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Stealthy Attacks on Sampled-Data Control and Encryption-Based Countermeasures

引用

IEEE Transactions on Automatic Control 2025年

作者： Shang, Jun Li, Yuzhe Chen, Tongwen Tongji University Department of Control Science and Engineering Shanghai Institute of Intelligent Science and Technology National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Shanghai200092 China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110004 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 1H9 Canada

This paper investigates stealthy attacks on sampled-data control systems, where a continuous process is sampled periodically, and the resultant discrete output and control signals are transmitted through dual channels in wireless communication networks. Acknowledging the vulnerability of these transmitted data to cyber threats, we analyze two types of stealthy attacks that compromise either one or both channels. We explicitly present the necessary and sufficient conditions for the existence of stealthy single-channel attacks. To mitigate these security risks, we implement encryption-based countermeasures, including linear time-invariant and periodic encryption methods. We detail sufficient conditions under which these encryption strategies effectively thwart single- and dual-channel stealthy attacks. The effectiveness of these approaches and the theoretical findings are demonstrated through numerical simulations. © 1963-2012 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning

arXiv

引用

arXiv 2024年

作者： Qu, Sanqing Zou, Tianpei Röhrbein, Florian Lu, Cewu Chen, Guang Tao, Dacheng Jiang, Changjun The School of Automotive Engineering Department of Computer Science Tongji University China The Faculty of Computer Science Chemnitz University of Technology Germany The Department of Computer Science Shanghai Jiao Tong University China The School of Computer Science Faculty of Engineering The University of Sydney Australia The Department of Computer Science Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University China

Deep neural networks often exhibit sub-optimal performance under covariate and category shifts. Source-Free Domain Adaptation (SFDA) presents a promising solution to this dilemma, yet most SFDA approaches are restricted to closed-set scenarios. In this paper, we explore Source-Free Universal Domain Adaptation (SF-UniDA) aiming to accurately classify "known" data belonging to common categories and segregate them from target-private "unknown" data. We propose a novel Global and Local Clustering (GLC) technique, which comprises an adaptive one-vs-all global clustering algorithm to discern between target classes, complemented by a local k-NN clustering strategy to mitigate negative transfer. Despite the effectiveness, the inherent closed-set source architecture leads to uniform treatment of "unknown" data, impeding the identification of distinct "unknown" categories. To address this, we evolve GLC to GLC++, integrating a contrastive affinity learning strategy. We examine the superiority of GLC and GLC++ across multiple benchmarks and category shift scenarios. Remarkably, in the most challenging open-partial-set scenarios, GLC and GLC++ surpass GATE by 16.7% and 18.6% in H-score on VisDA, respectively. GLC++ enhances the novel category clustering accuracy of GLC by 4.3% in open-set scenarios on Office-Home. Furthermore, the introduced contrastive learning strategy not only enhances GLC but also significantly facilitates existing methodologies. Copyright © 2024, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Triple Point Masking

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Liu, Jiaming Kong, Linghe Wu, Yue Gong, Maoguo Li, Hao Miao, Qiguang Ma, Wenping Qin, Can The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The School of Computer Science and Technology Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an710071 China The School of Electronic Engineering Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an710071 China The College of Mathematics Science Inner Mongolia Normal University Hohhot010022 China The School of Artificial Intelligence Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Xi’an710071 China The Department of Electrical and Computer Engineering Northeastern University BostonMA02115 United States

Existing 3D mask learning methods encounter performance bottlenecks under limited data, and our objective is to overcome this limitation. In this paper, we introduce a triple point masking scheme, named TPM, which serves as a scalable plug- and-play framework for MAE pre-training to achieve multi-mask learning for 3D point clouds. Specifically, we augment the baseline methods with two additional mask choices (i.e., medium mask and low mask) as our core insight is that the recovery process of an object can manifest in diverse ways. Previous high-masking schemes focus on capturing the global representation information but lack fine-grained recovery capabilities, so that the generated pre-training weights tend to play a limited role in the fine-tuning process. With the support of the proposed TPM, current methods can exhibit more flexible and accurate completion capabilities, enabling the potential autoencoder in the pre-training stage to consider multiple representations of a single 3D point cloud object. In addition, during the fine-tuning stage, an SVM-guided weight selection module is proposed to fill the encoder parameters for downstream networks with the optimal weight, maximizing linear accuracy and facilitating the acquisition of intricate representations for new objects. Extensive experimental results and theoretical analysis show that five baselines equipped with the proposed TPM achieve comprehensive performance improvements on various downstream tasks. © 2025 IEEE. All rights reserved.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Federated Learning With Client Clustering Selection and Quality-Aware Model Aggregation(2024)

引用

IEEE Internet of Things Journal 2025年

作者： Peng, Y. Wang, C. Shi, H. Ma, R. Guan, H. Yang, Hanbo Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai China Beijing Simulation Center National Key Laboratory of Modeling and Simulation for Complex Systems Beijing China

The Industrial Internet of Things (IIoT) is revolutionizing industries through device interconnectivity, enabling real-time data collection and transmission for enhanced monitoring, control, and automation. This has led to improvements in predictive maintenance, production optimization, and supply chain management. The integration of machine learning (ML) and deep learning (DL) within IIoT has been accelerated by increased data availability, computational advancements, and algorithmic innovations, with applications ranging from image processing to autonomous vehicles. Foundation models, such as ChatGPT, are becoming prevalent in IIoT for their capabilities in natural language processing and computer vision. However, the growth of IIoT and foundation models presents challenges, including data volume, real-time processing requirements, computational costs, and security vulnerabilities. Federated learning (FL) addresses these issues by allowing distributed model training without raw data transfer, enhancing privacy and security. FL is particularly beneficial for IIoT’s decentralized architecture and real-time decision-making needs. Despite the advantages, FL faces challenges such as data heterogeneity and communication overhead. To overcome these, we propose a federated learning framework, Fed-CCSQMA, which includes client selection and model aggregation modules to mitigate data heterogeneity’s impact. The client selection module uses Principal Component Analysis (PCA) and clustering to select clients with diverse yet representative data, while the model aggregation module assigns weights based on model accuracy to ensure faster global model convergence. We test our proposed framework on FMNIST and CIFAR-10 datasets, with accuracy surpassing baseline methods and faster convergence, demonstrating an improvement in overall generalizability and learning efficiency. © 2014 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Balancing Flexibility and Compliance in Response to Long-Tailed Business Process Changes

SSRN

引用

SSRN 2023年

作者： Zhu, Jingwei Peng, Jun Zhang, Liang Truong, Hong-Linh School of Computer Science Fudan University Shanghai Key Laboratory of Data Science Shanghai Institute of Intelligent Electronics & Systems 2005 Songhu Road Yangpu District Shanghai200438 China Department of Computer Science Aalto University Espoo Finland

The resilience of process-aware information systems (PAIS) is vital for enterprises' competitiveness in the ever-changing world. Enterprises need continuously maintain business processes in PAIS against uncertainty, resulting in the constant research topic of change management in business process management (BPM). However, previous efforts have left some gaps in dealing with uncertainties in change requirements, either due to high costs or technical incapability. Among these gaps, long-tailed change (LTC), characterized as the urgent and customizable maintenance needs in response to the residual uncertainty, has been largely undeveloped. COVID-19 and some emergent events in 2022 call for more effective solutions to such problems, to mitigate the business loss and to seek emerging opportunities. LTC challenges come from the contention between the degree of flexibility and compliance with business regulations in the context of rapid adaptation. In this paper, we develop a systematic approach to deal with these issues. First, we formulate the problem as a cooperation of multiple participants in the business by leveraging the separation of concerns principle to clarify the division of labor contributing to agility and fine-tuning capability of the approach, and to provide a controllable mechanism to balance operational resilience and dependable adaptation for PAIS. According to the framework, we develop a domain-specific language (DSL) and corresponding techniques to support business people in customizing business processes' behavior to meet circumstances. At the same time, business stakeholders can enforce core functions and service-level agreement (SLA) constraints on the whole business process. We validate our framework through two scenarios, one for design-time model adaptation and the other for run-time instance adaptation. These experiments reveal promising potentials of the framework in adapting to LTC and resolving the contention between agility/flexibility in c

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

cVTS: A Constrained Voronoi Tree Search Method for High Dimensional Analog Circuit Synthesis 23

cVTS: A Constrained Voronoi Tree Search Method for High Dime...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Aidong Zhao Xianan Wang Zixiao Lin Zhaori Bi Xudong Li Changhao Yan Fan Yang Li Shang Dian Zhou Xuan Zeng State Key Laboratory of Integrated Chips and Systems Microelectronics Department Fudan University Shanghai China Department of Electrical Engineering University of Texas at Dallas USA Department of Electrical and Computer Engineering University of California at San Diego USA School of Data Science Fudan University Shanghai China School of Computer Science Fudan University Shanghai China

ISBN: (纸本)9798350323481

A constrained Voronoi tree-based domain decomposition method for high-dimensional Bayesian optimization is proposed to solve large scale analog circuit synthesis problems, which can be formulated as high-dimensional heterogeneous black-box optimization. Hierarchical Voronoi tree progressively breaks down the design space into partitions with implicit performance boundaries such that promising regions are efficiently explored. Fast exploitation is ensured in Voronoi nest via local Bayesian optimization with a few observations. A slice-enhanced Gibbs sampling method is proposed to sample acquisition function cMES in irregular polyhedrons with design constraints. Compared with state-of-the-art methods, cVTS achieves significant speed up without loss of accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Continuity Scaling: A Rigorous Framework for Detecting and Quantifying Causality Accurately

引用

Research 2022年第4期2022卷 137-146页

作者： Xiong Ying Si-Yang Leng Huan-Fei MaD Qing Nie Ying-Cheng Lai Wei Lin School of Mathematical Sciences SCMSand SCAMFudan UniversityShanghai 200433China Research Institute for Inteligent Complex Systems CCSBand LCNBIFudan UniversityShanghai 200433China State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science Institutes of Brain ScienceFudan UniversityShanghai 200032China Institute of AI and Robotics Academy for Engineering and TechnologyFudan UniversityShanghai 200433China School of Mathematical Sciences Soochow UniversitySuzhou 215006China Department of Mathematics Department of Developmental and Cll BiologyAnd NSF-Simons Center for Multiscale Cell Fate ResearchUniversity of CaliforniaIrvineCA 92697-3875USA School of Electrical ComputerAnd Energy EngineeringArizona State UniversityTempeArizona 85287-5706USA Shanghai Artificial Intelligence Laboratory Shanghai 200232China

Data-based detection and quantification of causation in complex,nonlinear dynamical systems is of paramount importance to science,engineering,and *** by the widely used methodology in recent years,the cross-map-based techniques,we develop a general framework to advance towards a comprehensive understanding of dynamical causal mechanisms,which is consistent with the natural interpretation of *** particular,instead of measuring the smoothness of the cross-map as conventionally implemented,we define causation through measuring the scaling law for the continuity of the investigated dynamical system *** uncovered scaling law enables accurate,reliable,and eficient detection of causation and assessment of its strength in general complex dynamical systems,outperforming those existing representative *** continuity scaling-based framework is rigorously established and demonstrated using datasets from model complex systems and the real world.

关键词： dynamical scaling continuity

来源：评论

学校读者我要写书评

暂无评论

Reversible Data Hiding With Secret Encrypted Image Sharing and Adaptive Coding

引用

IEEE Internet of Things Journal 2025年

作者： Fang, Guangtian Wang, Feng Zhao, Chenbin Qin, Chuan Chang, Ching-Chun Chang, Chin-Chen Fujian University of Technology College of Computer Science and Mathematics Fuzhou350118 China Fujian University of Technology College of Computer Science and Mathematics Key Laboratory of Big Data Mining and Applications Fuzhou350118 China Monash University Faculty of IT Department of Software Systems and Cybersecurity VIC3800 Australia Ministry of Education School of Cyber Science and Engineering Key Laboratory of Aerospace Information Security and Trusted Computing Wuhan430072 China University of Shanghai for Science and Technology School of Optical-Electrical and Computer Engineering Shanghai200093 China Feng Chia University Information and Communication Security Research Center Taichuang 40724 Taiwan Feng Chia University Department of Information Engineering and Computer Science Taichung40724 Taiwan

To ensure the security of image information and facilitate efficient management in the cloud, the utilization of reversible data hiding in encrypted images (RDHEI) has emerged as pivotal. However, most existing RDHEI schemes suffer from lower security and limited embedding capacity. To tackle these challenges, we propose a reversible data hiding with secret encrypted image sharing and adaptive coding scheme. Specifically, in the encryption phase, we introduce an improved secret sharing (SS) encryption method based on the chinese remainder theorem for polynomials (CRTP). This method not only improves the security of encrypted images but also vacates a larger room for embedding. In the embedding phase, we introduce an adaptive coding embedding approach using XOR preservation (XORP) and huffman coding, which provides high embedding capacity. Experimental results and security analysis demonstrate that our proposed encryption method achieves optimal values in security indicators for encrypted images, such as information entropy, histograms, NPCR and UACI. The proposed embedding method is superior to some state-of-the-art schemes in terms of embedding capacity. Furthermore, in datasets BOSSBase and BOWS2, the average embedding rates of the proposed embedding approach can reach 2.1745 bpp and 2.0656 bpp, respectively. © 2025 IEEE.

关键词： adaptive coding chinese remainder theorem for polynomials encrypted images Reversible data hiding secret sharing

来源：评论

学校读者我要写书评

暂无评论

Block Broyden's methods for solving nonlinear equations 23

Block Broyden's methods for solving nonlinear equations

引用

Proceedings of the 37th International Conference on Neural Information Processing systems

作者： Chengchang Liu Cheng Chen Luo Luo John C.S. Lui Department of Computer Science & Engineering The Chinese University of Hong Kong Shanghai Key Laboratory of Trustworthy Computing East China Normal University School of Data Science Fudan University

This paper studies quasi-Newton methods for solving nonlinear equations. We propose block variants of both good and bad Broyden's methods, which enjoy explicit local superlinear convergence rates. Our block good Broyden's method has a faster condition-number-free convergence rate than existing Broyden's methods because it takes the advantage of multiple rank modification on Jacobian estimator. On the other hand, our block bad Broyden's method directly estimates the inverse of the Jacobian provably, which reduces the computational cost of the iteration. Our theoretical results provide some new insights on why good Broyden's method outperforms bad Broyden's method in most of the cases. The empirical results also demonstrate the superiority of our methods and validate our theoretical analysis.

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：