检索结果-内蒙古大学图书馆

Probability graph complementation contrastive learning

NEURAL NETWORKS 2024年 179卷 106522页

作者： Jiang, Wenhao Bai, Yuebin Beihang Univ Sch Comp Sci & Engn Beijing 100191 Peoples R China

Graph Neural Network (GNN) has achieved remarkable progress in the field of graph representation learning. The most prominent characteristic, propagating features along the edges, degrades its performance in most heterophilic graphs. Certain researches make attempts to construct KNN graph to improve the graph homophily. However, there is no prior knowledge to choose proper K and they may suffer from the problem of Inconsistent Similarity Distribution (ISD). To accommodate this issue, we propose Probability Graph Complementation Contrastive Learning (PGCCL) which adaptively constructs the complementation graph. We employ Beta Mixture Model (BMM) to distinguish intra-class similarity and inter-class similarity. Based on the posterior probability, we construct Probability Complementation Graphs to form contrastive views. The contrastive learning prompts the model to preserve complementary information for each node from different views. By combining original graph embedding and complementary graph embedding, the final embedding is able to capture rich semantics in the finetuning stage. At last, comprehensive experimental results on 20 datasets including homophilic and heterophilic graphs firmly verify the effectiveness of our algorithm as well as the quality of probability complementation graph compared with other state-of-the-art methods.

关键词： Heterophily Graph contrastive learning Graph complementation Beta mixture model expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Time discretization of continuous-time filters and smoothers for HMM parameter estimation

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 1996年第2期42卷 593-605页

作者： James, MR Krishnamurthy, V LeGland, F UNIV MELBOURNE DEPT ELECT & ELECTR ENGNPARKVILLEVIC 3052AUSTRALIA INST NATL RECH INFORMAT & AUTOMAT INST RECH INFORMAT & SYST ALEATOIRESF-35042 RENNESFRANCE

In this paper we propose algorithms for parameter estimation of fast-sampled homogeneous Markov chains observed in white Gaussian noise. Our algorithms are obtained by the robust discretization of stochastic differential equations involved in the estimation of continuous-time Hidden Markov Models (HMM's) via the EM algorithm. We present two algorithms: The first is based on the robust discretization of continuous-time filters that were recently obtained by Elliott to estimate quantities used in the EM algorithm. The second is based on the discretization of continuous-time smoothers, yielding essentially the well-known Baum-Welch re-estimation equations. The smoothing formulas for continuous-time HMM's are new, and their derivation involves two sided stochastic integrals. The choice of discretization results in equations which are identical to those obtained by deriving the results directly in discrete time. The filter-based EM algorithm has negligible memory requirements;indeed, independent of the number of observations. In comparison the smoother-based discrete-time EM algorithm require the use of the forward-backward algorithm, which is a fixed-interval smoothing algorithm and has memory requirements proportional to the number of observations. On the other hand, the computational complexity of the filter-based EM algorithm is greater than that of the smoother-based scheme. However, the filters may be suitable for parallel implementation. Using computer simulations we compare the smoother-based and filter-based EM algorithms for HMM estimation. We provide also estimates for the discretization error.

关键词： Hidden Markov Models robust discretization expectation maximization algorithm parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Structural network inference from time-series data using a generative model and transfer entropy

引用

PATTERN RECOGNITION LETTERS 2019年 125卷 357-363页

作者： Zhang, Zhihong Zhang, Genzhou Zhang, Zhonghao Chen, Guo Zeng, Yangbin Wang, Beizhan Hancock, Edwin R. Xiamen Univ Xiamen Fujian Peoples R China State Grid Shaanxi Elect Power Co Xian Shaanxi Peoples R China State Grid Shaanxi Informat & Telecommun Co LTD Xian Shaanxi Peoples R China Univ York York N Yorkshire England

In this paper we develop a novel framework for inferring a generative model of network structure representing the causal relations between data for a set of objects characterized in terms of time series. To do this we make use of transfer entropy as a means of inferring directed information transfer between the time-series data. Transfer entropy allows us to infer directed edges representing the causal relations between pairs of time series, and has thus been used to infer directed graph representations of causal networks for time-series data. We use the expectation maximization algorithm to learn a generative model which captures variations in the causal network over time. We conduct experiments on fMRI brain connectivity data for subjects in different stages of the development of Alzheimer's disease (AD). Here we use the technique to learn class exemplars for different stages in the development of the disease, together with a normal control class, and demonstrate its utility in both graph multi-class and binary classifications. These experiments are showing the effectiveness of our proposed framework when the amounts of training data are relatively small. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Transfer entropy Supergraph Time series Network inference expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Controlling for misclassified land use data: A post-classification latent multinomial logit approach

引用

REMOTE SENSING OF ENVIRONMENT 2015年 170卷 203-215页

作者： Martinez, Raymundo Marcos Baerenldau, Kenneth A. Univ Calif Riverside Dept Environm Sci Riverside CA 92521 USA

Terrain and landscape complexities can limit the accurate discrimination of land use categories with similar spectral signatures, as well as the accurate detection of land use change in temporal analyses of landscape dynamics. Studies based on misclassified land use data can generate biased parameter estimates and standard errors, inaccurate predictions, and incorrect policy recommendations. To address these challenges and improve the accuracy of land use analyses, we implement a post-classification strategy to detect misclassified land use observations using a latent multinomial logit model. This strategy is tested using both Monte Carlo simulations and a time series dataset based on supervised classification of remotely sensed data corresponding to land use decisions observed in a Mexican coffee growing region during the period 1984-2006. The results indicate that the strategy is useful for identifying land use observations with a high probability of being wrongly classified, even between categories with low discriminative spectral signatures. Reclassification of the land use data, based on the model results, increases the magnitudes of the marginal effects of the analyzed land use drivers in the theoretically expected directions, and in some cases improves the statistical significance of the parameter estimates. (C) 2015 Elsevier Inc. All rights reserved.

关键词： Land use Misclassification Latent multinomial logit model expectation maximization algorithm Transition rules Landsat Agroforests Monte Carlo simulation

来源：评论

学校读者我要写书评

暂无评论

A reassessment of dynamic characteristics of the Quincy Bayview Bridge using output-only identification techniques

引用

EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS 2005年第7期34卷 787-805页

作者： Pridham, BA Wilson, JC McMaster Univ Dept Civil Engn Hamilton ON L8S 4L7 Canada

A reassessment of the dynamic characteristics of the 542 m cable-stayed Bayview Bridge in Quincy, Illinois, is presented using a newly developed output-only system identification technique. The technique is applied to an extensive set of ambient vibration response data acquired from the bridge in 1987. Vertical, torsional and transverse modal frequencies of the deck are identified, and uncertainty in damping values are estimated using an automated procedure on several redundant measurements at four locations. Important practical implementation issues associated with the implementation of the procedure and selection of algorithm design parameters for stochastic subspace identification techniques are discussed. An overall mean and standard deviation of damping of 1.0 +/- 0.8% is estimated considering all identified vertical, torsional and transverse modes in the 0-2 Hz band. The mean damping for the fundamental vertical mode (0.37 Hz) is identified as 1.4 +/- 0.5%, and for the first coupled torsion-transverse mode (0.56 Hz) is identified as 1.1 +/- 0.8%. Variability in the damping estimates is shown to decrease as estimated modal RMS acceleration levels increase. Standard deviations on estimated damping range from 0.05% to 2%. The results are shown to be a substantial improvement in the evaluation of damping compared to earlier spectral analysis conducted on the same data set. Copyright (c) 2005 John Wiley & Sons, Ltd.

关键词： ambient vibration cable-stayed bridges damping Quincy Bayview Bridge system identification stochastic subspace methods expectation maximization algorithm outputonly identification

来源：评论

学校读者我要写书评

暂无评论

Moving window adaptive soft sensor for state shifting process based on weighted supervised latent factor analysis

引用

CONTROL ENGINEERING PRACTICE 2017年 61卷 72-80页

作者： Yao, Le Ge, Zhiqiang Zhejiang Univ Coll Control Sci & Engn Inst Ind Proc Control State Key Lab Ind Control Technol Hangzhou 310027 Zhejiang Peoples R China

Process nonlinearity and state shifting are two of the main factors that cause poor performance of online soft sensors. Adaptive soft sensor is a common practice to ensure high predictive accuracy. In this paper, the moving window method is introduced to the supervised latent factor analysis model to capture the state shifting feature of the process. To make the moving window strategy more efficient, the weighted form of the supervised latent factor analysis approach is applied. In this method, contributions of training samples are expressed through incorporating the similarity index into the noise variance of the process variable, which renders strong adaptability of the method for describing nonlinear relationships and abrupt changes of the process. A numerical example and a real industrial process are provided to demonstrate the effectiveness of the proposed adaptive soft sensor.

关键词： Adaptive soft sensor State shifting Moving window Weighted supervised latent factor analysis expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

A New Method for Maximum Likelihood Parameter Estimation of Gamma-Gamma Distribution

引用

JOURNAL OF LIGHTWAVE TECHNOLOGY 2013年第9期31卷 1347-1353页

作者： Kazeminia, Mahdi Mehrjoo, Mehri Univ Sistan & Baluchestan Dept Telecommun Zahedan 98155987 Iran

We propose a method to obtain the maximum likelihood (ML) parameter estimation of the Gamma-Gamma (Gamma - Gamma) distribution representing the free space optical (FSO) channel irradiance fluctuations. The proposed method is based on the expectation maximization (EM) algorithm and the generalized Newton method using a non-quadratic approximation. The numerical results show that, for all turbulence conditions, the proposed ML method is more accurate than the fractional moments (FMOM) method and the numerical ML method (two dimensional numerical maximization of log-likelihood function using the Nelder-Mead algorithm). Moreover, the proposed ML is a fast and stable iterative method, because the iterations always converge to the global optimum with high convergence rate.

关键词： expectation maximization algorithm free space optical communications generalized Newton method maximum likelihood parameter estimation

来源：评论

学校读者我要写书评

暂无评论

DETECTING TRAINING DATA OF LARGE LANGUAGE MODELS VIA expectation maximization

arXiv

引用

arXiv 2024年

作者： Kim, Gyuwan Li, Yang Spiliopoulou, Evangelia Ma, Jie Ballesteros, Miguel Wang, William Yang University of California Santa Barbara United States AWS AI Lab United States

The widespread deployment of large language models (LLMs) has led to impressive advancements, yet information about their training data, a critical factor in their performance, remains undisclosed. Membership inference attacks (MIAs) aim to determine whether a specific instance was part of a target model's training data. MIAs can offer insights into LLM outputs and help detect and address concerns such as data contamination and compliance with privacy and copyright standards. However, applying MIAs to LLMs presents unique challenges due to the massive scale of pre-training data and the ambiguous nature of membership. Additionally, creating appropriate benchmarks to evaluate MIA methods is not straightforward, as training and test data distributions are often unknown. In this paper, we introduce EM-MIA, a novel MIA method for LLMs that iteratively refines membership scores and prefix scores via an expectation-maximization algorithm, leveraging the duality that the estimates of these scores can be improved by each other. Membership scores and prefix scores assess how each instance is likely to be a member and discriminative as a prefix, respectively. Our method achieves state-of-the-art results on the WikiMIA dataset. To further evaluate EMMIA, we present OLMoMIA, a benchmark built from OLMo resources, which allows us to control the difficulty of MIA tasks with varying degrees of overlap between training and test data distributions. We believe that EM-MIA serves as a robust MIA method for LLMs and that OLMoMIA provides a valuable resource for comprehensively evaluating MIA approaches, thereby driving future research in this critical area. Copyright © 2024, 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

Fast Identification of Transients: Applying expectation maximization to Neutrino Data

arXiv

引用

arXiv 2023年

作者： Karl, Martina Eller, Philipp Technische Universität München TUM School of Natural Sciences Physics Department James-Frank-Str. 1 Garching bei MünchenD-85748 Germany European Southern Observatory Karl-Schwarzschild-Str. 2 Garching bei MünchenD-85748 Germany

We present a novel method for identifying transients suitable for both strong signal-dominated and background-dominated objects. By employing the unsupervised machine learning algorithm known as expectation maximization, we achieve computing time reductions of over 104 on a single CPU compared to conventional brute-force methods. Furthermore, this approach can be readily extended to analyze multiple flares. We illustrate the algorithm’s application by fitting the IceCube neutrino flare of TXS 0506+056. Copyright © 2023, 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

Theoretical and Numerical Study of MLEM and OSEM Reconstruction algorithms for Motion Correction in Emission Tomography

引用

IEEE TRANSACTIONS ON NUCLEAR SCIENCE 2009年第5期56卷 2739-2749页

作者： Dey, Joyoni King, Michael A. Univ Massachusetts Sch Med Div Nucl Med & Radiol Worcester MA 01655 USA

Patient body-motion and respiratory-motion impacts the image quality of cardiac SPECT and PET perfusion images. Several algorithms exist in the literature to correct for motion within the iterative maximum-likelihood reconstruction framework. In this work. three algorithms are derived starting with Poisson statistics to correct for patient motion. The first one is a motion compensated MLEM algorithm (MC-MLEM). The next two algorithms called MGEM-1 and MGEM-2 (short for Motion Gated OSEM, 1 and 2) use the motion states as subsets, in two different ways. Experiments were performed with NCAT phantoms (with exactly known motion) as the source and attenuation distributions. Experiments were also performed on in anthropomorphic phantom and a patient study. The SIMIND Monte Carlo simulation software was used to create SPECT projection images of the NCAT phantoms. The projection images were then modified to have Poisson noise levels equivalent to that of clinical acquisition. We investigated application of these algorithms to correction of (1) 1 large body-motion of 2 cm in Superior-Inferior (SI) and Anterior-Posterior (AP) directions each and (2) respiratory motion of 2 cm in SI and 0.6 cm in AP. We determined the bias with respect to the NCAT phantom activity for noiseless reconstructions as well as the bias-variance for noisy reconstructions. The MGEM-1 advanced along the bias-variance curve faster than the MC-MLEIM with iterations. The MCEM-1 also lowered the noiseless bias (with respect to NCAT truth) faster with iterations, compared to file MC-MLEM algorithms, as expected with subset algorithms. For the body motion correction with two motion states, after the 9th iteration the Was was close to that of MC-MLEM at iteration 17, reducing the number of iterations by a factor of 1.89. For the respiratory motion correction with 9 motion states, based on the noiseless bias, the iteration reduction factor was approximately 7. For the MGEM-2, however. bias-plot or the bias-var

关键词： expectation maximization algorithm image reconstruction

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：