检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Adipoetra, Michael Martin, Ségolène TU Berlin Germany

We propose a novel deep clustering method that integrates Variational Autoencoders (VAEs) into the expectation-maximization (EM) framework. Our approach models the probability distribution of each cluster with a VAE and alternates between updating model parameters—by maximizing the Evidence Lower Bound (ELBO) of the log-likelihood—and refining cluster assignments based on the learned distributions. This enables effective clustering and generation of new samples from each cluster. Unlike existing VAE-based methods, our approach eliminates the need for a Gaussian Mixture Model (GMM) prior or additional regularization techniques. Experiments on MNIST and FashionMNIST demonstrate superior clustering performance compared to state-of-the-art methods. Copyright © 2025, The Authors. All rights reserved.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Graph Self-Training with expectation-maximization Regularization

arXiv

引用

arXiv 2025年

作者： Wang, Emily Chen, Michael Li, Chao School of Information Technology Lakeside College Ohio United States Department of Applied Mathematics North River University Manchester United Kingdom Department of Computer Science Eastern Asia Institute of Technology Beijing China

In this paper, we propose a novel uncertainty-aware graph self-training approach for semi-supervised node classification. Our method introduces an expectation-maximization (EM) regularization scheme to incorporate an uncertainty mechanism during pseudo-label generation and model retraining. Unlike conventional graph self-training pipelines that rely on fixed pseudo-labels, our approach iteratively refines label confidences with an EM-inspired uncertainty measure. This ensures that the predictive model focuses on reliable graph regions while gradually incorporating ambiguous nodes. Inspired by prior work on uncertainty-aware self-training techniques [5], our framework is designed to handle noisy graph structures and feature spaces more effectively. Through extensive experiments on several benchmark graph datasets, we demonstrate that our method outperforms strong baselines by a margin of up to 2.5% in accuracy while maintaining lower variance in performance across multiple runs. Copyright © 2025, The Authors. All rights reserved.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Progressive Community Merging Cooperative Coevolution algorithm for Influence Blocking maximization in Social Networks

引用

IEEE Transactions on Network Science and Engineering 2025年第3期12卷 2093-2106页

作者： Gu, Ming Zhao, Tian-Fang Zhong, Jinghui Chen, Wei-Neng South China University of Technology School of Computer Science and Engineering Guangzhou510006 China South China University of Technology State Key Laboratory of Subtropical Building and Urban Science Guangzhou510006 China Jinan University School of Journalism and Communication Guangzhou510610 China

The widespread adoption of online social networks (OSNs) has facilitated social interaction and knowledge dissemination while raising concerns about extensive negative information propagation. Competitive propagation of positive and negative information can mitigate negative impacts. Influence blocking maximization (IBM) identifies a set of nodes initiating positive information propagation in OSNs to maximize blocking negative influence. This paper first introduces an effective influence blocking estimator (DPADV) that replaces computationally expensive Monte Carlo simulations. DPADV can calculate the approximate diffusion value for nodes activated by negative information in any hop neighborhood. Meanwhile, to address the challenges of complexity and computational efficiency brought about by the continuous expansion of OSNs, we propose the progressive community merging cooperative coevolution (PCMCC) algorithm. PCMCC divides the search space into communities and initializes a subpopulation for each community. Each subpopulation is responsible for optimizing a community, thereby implementing a divide-and-conquer approach. To enhance collaboration among communities and global exploration, we employed a progressive community merging strategy, supplemented by multi-population evolution strategies to guide the search towards global optima. Additionally, we developed an efficient heuristic metric for evaluating node importance, which is used to design population crossover and local search in the evolutionary scheme. Experimental results on six real-world and four synthetic networks demonstrate that PCMCC exhibits competitive performance compared to state-of-the-art algorithms, achieving near-greedy performance with lower time complexity. © 2013 IEEE.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Target Detection Architecture for Mismatched Signals

引用

IEEE Signal Processing Letters 2025年 32卷 1860-1864页

作者： Jin, Yuxi Yin, Chaoran Wang, Tianqi Hao, Chengpeng Orlando, Danilo Chinese Academy of Sciences Institute of Acoustics Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Universita di Pisa Dipartimento di Ingegneria dell'Informazione Via Caruso 16 Pisa56122 Italy

This letter addresses the problem of adaptive target detection in the presence of possible mismatched sidelobe interfering signals assumed orthogonal to the nominal target signature in the whitened space. To this end, we devise a joint Maximum Likelihood (ML)-Bayesian based detector that simultaneously improves the target detection performance and the rejection capability of the mismatched signals. Specifically, we first inject an orthogonal interfering signal into the null hypothesis of the traditional binary hypothesis test and, then, solve it by means of the latent variable model and the expectation maximization algorithm. Finally, we maximize the posterior probability of the hypotheses for decision. In addition, we prove the Constant False-Alarm Rate property of the proposed detection architecture. The illustrative examples conducted on synthetic data corroborate the enhanced detection performance and rejection capability with respect to the state-of-the-art. © 1994-2012 IEEE.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

A Model Fusion Distributed Kalman Filter for Non-Gaussian measurement Noise

引用

IEEE Internet of Things Journal 2025年第10期12卷 14677-14690页

作者： Mao, Xuemei He, Jiacheng Wang, Gang Peng, Bei Zhang, Kun Gao, Song Chen, Jian The School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu611731 China The School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China

Wireless sensor networks (WSNs) represent a critical research domain within the Internet of Things (IoT) technology. The distributed Kalman filter (DKF) has garnered significant attention as an information fusion method for WSNs. However, effectively handling non-Gaussian environments remains a crucial challenge for DKF. This paper proposes a solution by partitioning the noise distribution into multiple Gaussian components, thereby approximating the measurement model with sub-models. We introduce a model fusion distributed Kalman filter (MFDKF) that combines sub-models by assuming independent random processes for the model’s transition probabilities. The expectation maximization (EM) algorithm is employed to estimate the relevant parameters. To address specific requirements in WSNs that demand high consensus or have limited communication, two derivative algorithms, namely consensus MFDKF (C-MFDKF) and simplified MFDKF (S-MFDKF), are proposed based on consensus theory. The convergence of MFDKF and its derivative algorithms is analyzed. A series of simulations demonstrate the effectiveness of MFDKF and its derivative algorithms. © 2014 IEEE.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

A Decision-Theoretic Approach to Model Choice

引用

Annals of Data Science 2025年 1-11页

作者： Karhunen, Markku Jyväskylän Toimipaikka Survontie 9A Jyväskylä40500 Finland

Model choice algorithms are usually compared based on their accuracy, i.e. ability to find true models. However, conservative algorithms (such as BIC minimisation) are accurate when no true effects exist, while more liberal algorithms (such as Lasso) are accurate when there are plenty of true effects. There is ambiguity, then, regarding the correct algorithm. The purpose of this paper is to show how expected utility maximisation and Monte Carlo simulations can be used to compare model choice algorithms. Two loss functions are derived from the expected utility function of the researcher. Both loss functions turn out to be linear combinations of specificity and one or two kinds of sensitivity which are discussed in this paper. Subsequently, this paper experiments with four parametrisations of these loss functions, and then uses these parametrised versions to compare nine algorithms within the contexts of both logistic and Gaussian regression. The results demonstrate that researchers who avoid false positives should either use BIC or BICc for model choice or report nothing at all. AIC does not seem to be the optimal method for the range of parameters covered in this study. © The Author(s) 2025.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Online Influence maximization With Semi-Bandit Feedback Under Corruptions

引用

IEEE Transactions on Network Science and Engineering 2025年第3期12卷 2308-2321页

作者： Cheng, Xiaotong Nourani-Koliji, Behzad Maghsudi, Setareh Ruhr-University Bochum Department of Electrical Engineering and Information Technology Bochum44801 Germany University of Tübingen Department of Computer Science Tübingen72074 Germany Fraunhofer Heinrich Hertz Institute Berlin10587 Germany

In this article, we investigate the online influence maximization in social networks. Most prior research studies on online influence maximization assume that the nodes are fully cooperative and act according to their stochastically generated influence probabilities on others. In contrast, we study the online influence maximization problem in the presence of some corrupted nodes whose damaging effects diffuse throughout the network. We propose a novel bandit algorithm, CW-IMLinUCB, which robustly learns and finds the optimal seed set in the presence of corrupted users. Theoretical analyses establish that the regret performance of our proposed algorithm is better than the state-of-the-art online influence maximization algorithms. Extensive empirical evaluations on synthetic and real-world datasets also show the superior performance of our proposed algorithm. © 2013 IEEE.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

MAXIMUM PRINCIPLE FOR STOCHASTIC OPTIMAL CONTROL PROBLEM UNDER CONVEX expectation

引用

SIAM Journal on Control and Optimization 2025年第1期63卷 524-545页

作者： Li, Xiaojuan Hu, Mingshang Department of Mathematics Qilu Normal University Shandong Jinan250200 China Zhongtai Securities Institute for Financial Studies Shandong University Shandong Jinan250100 China

In this paper, we study a stochastic optimal control problem under a type of consistent convex expectation dominated by G-expectation. By the separation theorem for convex sets, we get the representation theorems for this convex expectation and conditional convex expectation. Based on these results, we obtain the variational equation for the cost functional by weak convergence and discretization methods. Furthermore, we establish the maximum principle which is sufficient under usual convex assumptions. Finally, we study the linear quadratic control problem by using the obtained maximum principle. © by SIAM. Unauthorized reproduction of this article is prohibited.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

A Novel Finite Mixture Model Based on the Generalized t Distributions with Two-Sided Censored Data

引用

Annals of Data Science 2025年第1期12卷 341-379页

作者： Guan, Ruijie Rong, Yaohua Cheng, Weihu Xin, Zhenyu Key Laboratory of Network Information System Technology Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Faculty of Science Beijing University of Technology Beijing100124 China Master of management EBS Universität für Wirtschaft und Recht Oestrich-Winkel65375 Germany

In light of the rapid technological advancements witnessed in recent decades, numerous disciplines have been inundated with voluminous datasets characterized by multimodality, heavy-tailed distributions, and prevalent missing information. Consequently, the task of effectively modeling such intricate data poses a formidable yet indispensable challenge. This paper endeavors to address this challenge by introducing a novel finite mixture model predicated upon the generalized t distribution, tailored specifically to accommodate two-sided censored observations, thereby establishing a foundational framework for modeling this complex data structure. To facilitate parameter estimation within this model, we devise a variant of the EM-type algorithm, amalgamating the profile likelihood approach with the classical expectation Conditional maximization algorithm. Notably, this hybridized methodology affords analytical expressions in the E-step and a tractable M-step, thereby substantially enhancing computational expediency and efficiency. Furthermore, we furnish closed-form expressions delineating the observed information matrix, pivotal for approximating the asymptotic covariance matrix of the MLEs within this mixture model. To empirically evaluate the efficacy of the proposed algorithm, a series of simulation studies are conducted, demonstrating promising performance across various artificial datasets. Additionally, the practical applicability of the proposed methodology is elucidated through its deployment on two real-world datasets, thereby underscoring its feasibility and utility in practical settings. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

A Physical Cluster-based Passive Scatterer Detection Method in ISAC Systems 16

A Physical Cluster-based Passive Scatterer Detection Method ...

引用

16th International Conference on Signal Processing Systems, ICSPS 2024

作者： Wang, Yu Zhou, Tao Liu, Xiangping Liu, Liu School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9781510689251

This paper proposes a novel passive scatterer detection method in integrated sensing and communication (ISAC) systems. The proposed scatterer detection method employs Subspace Alternating Generalized expectation maximization (SAGE) to estimate the parameters of the multipath components (MPCs), which are used to determine the locations of scattering points (SPs). Subsequently, a joint clustering and tracking algorithm is applied to identify the clusters which the SPs belong to. As a result, valuable information of scatterer is obtained, including location, quantity and shape. The proposed method leverages the relationship between physical clusters and scatterers in the environment, which is validated according to channel simulation based on ray-tracer. Compared to other scatterer detection methods, the proposed approach can detect scatterers with high accuracy, low false alarm rate and miss alarm rate, and low mean center distance error with real-time detection capability. © 2025 SPIE.

关键词： expectation maximization algorithm

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：