检索结果-内蒙古大学图书馆

Self-Supervised Locality-Sensitive Deep Hashing for the Robust Retrieval of Degraded Images

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2025年 20卷 1582-1596页

作者： Xiang, Lingyun Hu, Hailang Li, Qian Yu, Hao Shen, Xiaobo Changsha Univ Sci & Technol Sch Comp & Commun Engn Changsha 410114 Peoples R China Nanjing Univ Informat Sci & Technol Engn Res Ctr Digital Forens Minist Educ Nanjing 210044 Peoples R China Changsha Res Inst Min & Met Co Ltd Changsha 410012 Peoples R China North China Inst Comp Technol Beijing 100083 Peoples R China Tech Univ Munich Fak Informat D-85748 Munich Germany Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Peoples R China

Recently, numerous degraded images have flooded search engines and social networks, finding extensive and practical applications in the real world. However, these images have also posed new challenges to conventional image retrieval tasks. To this end, we introduce a new task of retrieving degraded images through deep hashing from large-scale databases, and further present the Locality-Sensitive Hashing Network (LSHNet) to tackle it in a self-supervised manner. More specifically, we first propose a triplet strategy to enable the self-supervised training of LSHNet in an end-to-end fashion. Due to the designed strategy, the highly semantic similarity and discrimination of degraded images are well-preserved in our learned latent codes without requiring additional human labor in labeling tons of degraded images. Moreover, to tackle large-scale image retrieval efficiently, we further propose to transform the latent codes into locality-sensitive hashing codes such that the degraded images can be retrieved in sublinear time with their representation ability almost unaffected. Extensive experiments are conducted on three public benchmarks where the results demonstrate the superior performance of LSHNet in retrieving similar images under degraded conditions.

关键词： Image retrieval Codes Semantics Training Robustness approximation algorithms Quantization (signal) Vectors Hash functions Hands Degraded image large-scale image retrieval locality-sensitive self-supervised deep hashing

来源：评论

学校读者我要写书评

暂无评论

Budget-feasible egalitarian allocation of conflicting jobs

引用

AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS 2025年第1期39卷 1-29页

作者： Gupta, Sushmita Jain, Pallavi Mohanapriya, A. Tripathi, Vikash Inst Math Sci Theoret Comp Sci Chennai Tamil Nadu India Indian Inst Technol Dept Comp Sci & Engn Jodhpur Rajasthan India

Allocating conflicting jobs among individuals while respecting a budget constraint for each individual is an optimization problem that arises in various real-world scenarios. In this paper, we consider the situation where each individual derives some satisfaction from each job. We focus on finding a feasible allocation of conflicting jobs that maximize egalitarian cost, i.e., the satisfaction of the individual who is worst-off. To the best of our knowledge, this is the first paper to combine egalitarianism, budget-feasibility, and conflict-freeness in allocations. We provide a systematic study of the computational complexity of finding budget-feasible conflict-free egalitarian allocation and show that our problem generalizes a large number of classical optimization problems. Therefore, unsurprisingly, our problem is NP-hard even for two individuals and when there is no conflict between any jobs. We show that the problem admits algorithms when studied in the realm of approximation algorithms and parameterized algorithms with a host of natural parameters that match and in some cases improve upon the running time of known algorithms.

关键词： Fair allocation Maximize egalitarian cost Parameterized algorithms approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

On the optimal mixing problem of approximate Nash equilibria in bimatrix games

引用

THEORETICAL COMPUTER SCIENCE 2025年 1031卷

作者： Deng, Xiaotie Li, Dongchen Li, Hanyu Peking Univ Sch Comp Sci CFCS 5 Yiheyuan Rd Beijing 100871 Peoples R China Univ Hong Kong Sch Comp Sci Pokfulam Rd Hong Kong 999077 Peoples R China

This paper introduces the optimal mixing problem, a natural extension of the computation of approximate Nash Equilibria (NE) in bimatrix games. The problem focuses on determining the optimal convex combination of given strategies that minimizes the approximation (i.e., regret) in NE computation. We develop algorithms for the exact and approximate optimal mixing problems and present new complexity results that bridge both practical and theoretical aspects of NE computation. Practically, our algorithms can be used to enhance and integrate arbitrary existing constant-approximate NE algorithms, offering a powerful tool for the design of approximate NE algorithms. Theoretically, these algorithms allow us to explore the implications of support restrictions on approximate NE and derive the upper-bound separations between approximate NE and exact NE. Consequently, this work contributes to theoretical understandings of the computational complexity of approximate NE under various constraints and practical improvements in multi- agent reinforcement learning (MARL) and other fields where NE computation is involved.

关键词： Approximate Nash equilibria Bimatrix games Optimal mixing approximation algorithms Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Efficient algorithms for Minimizing the Kirchhoff Index via Adding Edges

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2025年第6期37卷 3342-3355页

作者： Zhou, Xiaotian Zehmakan, Ahad N. Zhang, Zhongzhi Fudan Univ Sch Comp Sci Shanghai Key Lab Intelligent Informat Proc Shanghai 200433 Peoples R China Australian Natl Univ Sch Comp Canberra ACT 2601 Australia Fudan Univ Res Inst Intelligent Complex Syst Shanghai 200433 Peoples R China

The Kirchhoff index, which is the sum of the resistance distance between every pair of nodes in a network, is a key metric for gauging network performance, where lower values signify enhanced performance. In this paper, we study the problem of minimizing the Kirchhoff index by adding edges. We first provide a greedy algorithm for solving this problem and give an analysis of its quality based on the bounds of the submodularity ratio and the curvature. Then, we introduce a gradient-based greedy algorithm as a new paradigm to solve this problem. To accelerate the computation cost, we leverage geometric properties, convex hull approximation, and approximation of the projected coordinate of each point. To further improve this algorithm, we use pre-pruning and fast update techniques, making it particularly suitable for large networks. Our proposed algorithms have nearly-linear time complexity. We provide extensive experiments on ten real networks to evaluate the quality of our algorithms. The results demonstrate that our proposed algorithms outperform the state-of-the-art methods in terms of efficiency and effectiveness. Moreover, our algorithms are scalable to large graphs with over 5 million nodes and 12 million edges.

关键词： Indexes Greedy algorithms approximation algorithms Time complexity Vectors Resistance Optimization Data mining Laplace equations Error analysis Resistance distance Kirchhoff index graph algorithm

来源：评论

学校读者我要写书评

暂无评论

Memristor Circuits as Linear-Gradient Systems and Discrete Analogues Preserving a First Integral

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2025年

作者： Marco, Mauro Di Forti, Mauro Pancioni, Luca Innocenti, Giacomo Tesi, Alberto Univ Siena Dept Informat Engn & Math I-53100 Siena Italy Univ Florence Dept Informat Engn I-50139 Florence Italy

The paper considers a wide class of nonlinear circuits with an ideal memristor, capacitors, inductors and current or voltage sources. A fundamental dynamical property is that each memristor circuit in this class admits a first integral (invariant of motion or preserved quantity), i.e., a function which is constant along the solutions. The first main result is that we can put the state equations of each circuit in a universal form, known as linear-gradient form, given by a state-dependent skew-symmetric matrix times the gradient of the first integral. This is a simple and general form which is both of theoretic and practical interest. First of all, it makes manifest the existence of a first integral. Moreover, it admits an elegant discrete-time (DT) analogue. Indeed, the linear-gradient form, combined with geometric discretization methods and the concept of discrete gradients, yields a DT version of each memristor circuit that exactly preserves the first integral for any discretization time step. This is relevant, since the existence of a first integral is a fragile property that is in general destroyed by typical discretization schemes used in the literature no matter how small the step size is. On one hand, the proposed discretization scheme can be used for constructing numerical algorithms that better approximate the solutions of memristor circuits for small step sizes. On the other hand, for larger step sizes the obtained DT memristor circuits can be of interest by themselves since they are able to easily generate complex dynamics potentially useful for engineering applications (computational chaos). Furthermore, the paper shows that, thanks to the decomposition of the state space in invariant manifolds, the derived DT circuits exhibit extreme multistability, i.e., the coexistence of infinitely many different attractors for fixed set of circuit parameters, memristor nonlinearity and step size.

关键词： Memristors Circuits Capacitors Inductors Voltage Manifolds Chaos Integral equations Hands approximation algorithms Computational chaos discrete-time system first integral geometric discretization linear-gradient formulation memristor nonlinear circuits extreme multistability

来源：评论

学校读者我要写书评

暂无评论

Communication-Efficient Distributed Bayesian Federated Learning Over Arbitrary Graphs

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2025年 73卷 1351-1366页

作者： Wang, Sihua Guo, Huayan Zhu, Xu Yin, Changchuan Lau, Vincent K. N. Beijing Univ Posts & Telecommun Beijing Lab Adv Informat Network Beijing 100876 Peoples R China Beijing Univ Posts & Telecommun Beijing Key Lab Network Syst Architecture & Conver Beijing 100876 Peoples R China Hong Kong Univ Sci & Technol Dept Elect & Commun Engn Hong Kong 999077 Peoples R China Harbin Inst Technol Sch Informat Sci & Technol Shenzhen 518055 Peoples R China Guangdong Prov Key Lab Aerosp Commun & Networking Shenzhen 518055 Peoples R China Shenzhen Municipal Key Lab AIoT Commun Shenzhen 518055 Peoples R China

This paper investigates a fully distributed federated learning (FL) problem, in which each device is restricted to only utilize its local dataset and the information received from its adjacent devices that are defined in a communication graph to update the local model weights for minimizing the global loss function. To incorporate the communication graph constraint into the joint posterior distribution, we exploit the fact that the model weights on each device is a function of its local likelihood and local prior and then, the connectivity between adjacent devices is modeled by a Dirac Delta distribution. In this way, the joint distribution can be factorized naturally by a factor graph. Based on the Dirac Delta-based factor graph, we propose a novel distributed approximate Bayesian inference algorithm that combines loopy belief propagation (LBP) and variational Bayesian inference (VBI) for distributed FL. Specifically, VBI is used to approximate the non-Gaussian marginal posterior as a Gaussian distribution in local training process and then, the global training process resembles Gaussian LBP where only the mean and variance are passed among adjacent devices. Furthermore, we propose a new damping factor design according to the communication graph topology to mitigate the potential divergence and achieve consensus convergence. Simulation results verify that the proposed solution achieves faster convergence speed with better performance than baselines.

关键词： Bayes methods Training Convergence Inference algorithms Damping Brain modeling approximation algorithms Optimization Signal processing algorithms Federated learning Bayesian federated learning decentralized consensus optimization message passing

来源：评论

学校读者我要写书评

暂无评论

Joint Client and Cross-Client Edge Selection for Cost-Efficient Federated Learning of Graph Convolutional Networks

引用

IEEE TRANSACTIONS ON NETWORKING 2025年第1期33卷 286-298页

作者： Huang, Guangjing Chen, Xu Wu, Qiong Li, Jingyi Huang, Qianyi Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China

Graph-structured data applications promote the development of Graph Neural Networks (GNN) in recent years. Due to privacy concerns, collecting graph data stored in massive client devices for centralized graph learning is prohibitive. It is natural to integrate federated learning (FL) in graph learning to address this issue, which enables clients to collaborate on training a shared model without uploading their data. This generates an emerging paradigm of federated graph learning (FGL). However, due to various costs incurred by FGL training, the collaboration between the server and clients is still a challenging issue in FGL, which remains largely unexplored in existing studies. To bridge this gap, we propose a cost-efficient collaboration framework for FGL of graph convolutional networks on semi-supervised node classification tasks, i.e., Joint Client and Cross-Client Edge Selection (JC(3)ES) for the server. Specifically, we first characterize how varies graph structure affect the final convergence performance of the FGL model. We then reveal the fundamental supermodular property in client selection. Based on this, we further devise an approximately optimal algorithm for the server and theoretically derive the performance gap between the proposed algorithm and the optimal solution. Extensive numerical evaluations show that our proposed algorithm achieves outstanding performance in cost-efficient collaboration for FGL on popular graph datasets.

关键词： Training Servers Collaboration Costs Convergence Social networking (online) Data centers Data models approximation algorithms Graph convolutional networks Federated graph learning collaboration framework client selection cross-client edge selection

来源：评论

学校读者我要写书评

暂无评论

Dynamic Regret for Distributed Online Composite Optimization

引用

IEEE TRANSACTIONS ON AUTOMATIC CONTROL 2025年第5期70卷 3056-3071页

作者： Hou, Ruijie Yu, Yang Li, Xiuxian Tongji Univ Coll Elect & Informat Engn Dept Control Sci & Engn Shanghai 201800 Peoples R China Tongji Univ Shanghai Res Inst Intelligent Autonomous Syst Frontiers Sci Ctr Intelligent Autonomous Syst Natl Key Lab Autonomous Intelligent Unmanned Syst Shanghai 201210 Peoples R China Tongji Univ Shanghai Inst Intelligent Sci & Technol Shanghai 201210 Peoples R China

This article focuses on online composite optimization over multiagent networks. In the distributed setting, each agent has its own local loss function, which consists of a convex, strongly convex or strongly convex and smooth function, and a time-varying nonsmooth regularizer. Two distributed online algorithms are proposed and corresponding dynamic regrets are analyzed. Two proposed algorithms are based on signs of relative states. The first algorithm obtains O(root T(C-T + 1)) dynamic regret bound when each local loss is a general convex composite function, where C-T is the path variation. If C-T can be estimated in advance for convex or strongly convex local loss with a time-varying nonsmooth regularizer, then dynamic regret bounds are, respectively, in the order of O(root T(C-T + 1)) and O(logT(1 + C-T)). The second algorithm is based on the first one, especially for handling the local loss composed of a strongly convex and smooth function with a nonsmooth regularizer, and then obtains O(1 + C-T) dynamic regret bound. In the end, numerical results are given to support the theoretical findings.

关键词： Heuristic algorithms Optimization Power system dynamics approximation algorithms Vectors Noise Linear programming Convex functions Benchmark testing Loss measurement Composite optimization distributed algorithms dynamic regret online optimization proximal gradient sign information

来源：评论

学校读者我要写书评

暂无评论

Multi-Grade Revenue Maximization for Promotional and Competitive Viral Marketing in Social Networks

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2025年第3期37卷 1339-1353页

作者： Teng, Ya-Wen Shi, Yishuo Yang, De-Nian Tai, Chih-Hua Yu, Philip S. Chen, Ming-Syan Acad Sinica Inst Informat Sci Taipei 115201 Taiwan Wenzhou Univ Stat & Informat Sci Wenzhou 325060 Zhejiang Peoples R China Acad Sinica Res Ctr Informat Technol Innovat Taipei 115201 Taiwan Natl Taipei Univ Comp Sci & Informat Engn New Taipei City 104380 Taiwan Univ Illinois Comp Sci Chicago IL 60607 USA Natl Taiwan Univ Elect Engn Taipei 106319 Taiwan

In this paper, we address the problem of revenue maximization (RM) for multi-grade products in social networks by considering pricing, seed selection, and coupon distribution. Previous works on RM often focus on a single product and neglect the use of coupons for promotion. We propose a new optimization problem, Revenue Maximization of Multi-Grade Product(RMMGP), to simultaneously determine pricing, seed selection, and coupon distribution for multi-grade products with both promotional and competitive relationships between grades in order to maximize revenue through viral marketing. We prove the hardness and inapproximability of RMMGP and show that the revenue function is not monotone or submodular. To solve RMMGP, we design an approximation algorithm, namely Data-Dependent Revenue Maximization (DDRM), and propose the Pricing-Seeding-Coupon allocation (PriSCa) algorithm, which uses the concepts of Worth Receiving Probability, Pricing-Promotion Alternating Framework, and Independent/Holistic Customer-Grade Determinant sets. Our experiments on real social networks, using valuation distributions from ***, demonstrate that PriSCa and DDRM achieve on average 1.5 times higher revenue than state-of-the-art approaches. Additionally, PriSCa is efficient and scalable on large datasets.

关键词： Pricing Cost accounting Resource management Social networking (online) Companies approximation algorithms Investment Psychology Diffusion models Time complexity Social influence revenue maximization coupons

来源：评论

学校读者我要写书评

暂无评论

Stagewise Training With Exponentially Growing Training Sets

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2025年第4期36卷 6148-6158页

作者： Gu, Bin Alquabeh, Hilal de Vazelhes, William Huo, Zhouyuan Huang, Heng Jilin Univ Sch Artificial Intelligence Changchun 130012 Peoples R China Mohamed bin Zayed Univ Artificial Intelligence Dept Machine Learning Abu Dhabi U Arab Emirates Univ Pittsburgh Dept Elect & Comp Engn Pittsburgh PA 15260 USA Univ Maryland Dept Comp Sci College Pk MD 20742 USA

In the world of big data, training large-scale machine learning problems has gained considerable attention. Numerous innovative optimization strategies have been presented in recent years to accelerate the large-scale training process. However, the possibility of further accelerating the training process of various optimization algorithms remains an unresolved subject. To begin addressing this difficult problem, we exploit the researched findings that when training data are independent and identically distributed, the learning problem on a smaller dataset is not significantly different from the original one. Upon that, we propose a stagewise training technique that grows the size of the training set exponentially while solving nonsmooth subproblem. We demonstrate that our stagewise training via exponentially growing the size of the training sets (STEGSs) are compatible with a large number of proximal gradient descent and gradient hard thresholding (GHT) techniques. Interestingly, we demonstrate that STEGS can greatly reduce overall complexity while maintaining statistical accuracy or even surpassing the intrinsic error introduced by GHT approaches. In addition, we analyze the effect of the training data growth rate on the overall complexity. The practical results of applying l(2,1) -and l(0) -norms to a variety of large-scale real-world datasets not only corroborate our theories but also demonstrate the benefits of our STEGS framework.

关键词： Training Optimization Computational complexity Upper bound approximation algorithms Training data Risk minimization Gradient hard thresholding (GHT) algorithms proximal algorithms stagewise training strategy stochastic 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：