检索结果-内蒙古大学图书馆

Privacy and Accuracy Implications of model complexity and Integration in Heterogeneous Federated Learning

IEEE ACCESS 2025年 13卷 40258-40274页

作者： Nemeth, Gergely D. Lozano, Miguel Angel Quadrianto, Novi Oliver, Nuria ELLIS Alicante Alicante 03005 Spain Univ Alicante Alicante 03690 Spain Univ Sussex Dept Comp Sci & Artifical Intelligence Brighton BN1 9RH England Basque Ctr Appl Math Dept Informat Bilbao 48009 Spain

Federated Learning (FL) has been proposed as a privacy-preserving solution for distributed machine learning, particularly in heterogeneous FL settings where clients have varying computational capabilities and thus train models with different complexities compared to the server's model. However, FL is not without vulnerabilities: recent studies have shown that it is susceptible to membership inference attacks (MIA), which can compromise the privacy of client data. In this paper, we examine the intersection of these two aspects, heterogeneous FL and its privacy vulnerabilities, by focusing on the role of client model integration, the process through which the server integrates parameters from clients' smaller models into its larger model. To better understand this process, we first propose a taxonomy that categorizes existing heterogeneous FL methods and enables the design of seven novel heterogeneous FL model integration strategies. Using CIFAR-10, CIFAR-100, and FEMNIST vision datasets, we evaluate the privacy and accuracy trade-offs of these approaches under three types of MIAs. Our findings reveal significant differences in privacy leakage and performance depending on the integration method. Notably, introducing randomness in the model integration process enhances client privacy while maintaining competitive accuracy for both the clients and the server. This work provides quantitative light on the privacy-accuracy implications client model integration in heterogeneous FL settings, paving the way towards more secure and efficient FL systems.

关键词： Computational modeling Servers Data models Training Taxonomy Solid modeling Federated learning complexity theory Privacy Data privacy membership inference attack model complexity privacy

来源：评论

学校读者我要写书评

暂无评论

Appraising model complexity in Option Pricing

引用

JOURNAL OF FUTURES MARKETS 2025年第5期45卷 455-472页

作者： Cummins, Mark Esposito, Francesco Univ Strathclyde Glasgow Scotland Dublin City Univ Dublin Ireland

The research question we consider is whether incremental complexity in option pricing models is justified by incremental model performance. We apply the model confidence set as a formal model comparison approach in appraising stochastic volatility jump-diffusion option pricing models, spanning affine and nonaffine specifications. Jumps in price with stochastic (constant) arrival intensity produce superior (inferior) outcomes. A parsimonious negative exponential price jump distribution outperforms the popular normal distribution. Jumps in volatility (synchronized or not) worsen model performance. A parsimonious nonlinear hyperbolic drift extension of the Heston model performs particularly well. Nonlinear CEV models generally do not produce appreciable model performance.

关键词： affine and nonaffine jump-diffusion model specifications model complexity model confidence set option pricing models stochastic volatility

来源：评论

学校读者我要写书评

暂无评论

Simulating biotic disturbance responses in forests requires a balance of model performance, complexity, and accessibility

引用

ECOLOGICAL modelLING 2025年 502卷

作者： Haber, Lisa T. Bond-Lamberty, Ben Chan, David Dorheim, Kalyn Matthes, Jaclyn Hatala Gough, Christopher Virginia Commonwealth Univ Dept Biol 1000 W Cary StSuite 126 Richmond VA 23284 USA Pacific Northwest Natl Lab Joint Global Change Res Inst 5825 Univ Res Court College Pk MD 20740 USA Virginia Commonwealth Univ Dept Math & Appl Math 1015 Floyd Ave Richmond VA 23220 USA Harvard Univ Harvard Forest 324 North Main St Petersham MA 01366 USA

Biotic disturbances, i.e. ecosystem perturbations driven by insects and pathogens, are distinct from abiotic events in their duration, severity, and variable effects on carbon (C) pools and fluxes. Because of these factors and their interactions with climate, biotic disturbances present a substantial challenge to ecosystem modelers attempting to balance model complexity, accessibility, and realism. Here we share our recent experience with model-data fusion experiments as part of the Forest Resilience Threshold Experiment (FoRTE), using both a very simple and a highly complex model to simulate ecologically complex biotic disturbance responses. In this Viewpoint, our goals are to (1) synthesize our experiences with both models, weighing model complexity-process specificity trade-offs, and (2) suggest three priorities for future efforts to improve ecosystem modeling of biotic disturbance impacts to the terrestrial C cycle.

关键词： Ecosystem models model complexity Biotic disturbance Intermediate complexity models modeling trade-offs

来源：评论

学校读者我要写书评

暂无评论

model complexity adaptation using a discriminant measure

引用

IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING 2000年第2期8卷 205-208页

作者： Padmanabhan, M Bahl, LR IBM Corp Thomas J Watson Res Ctr Yorktown Hts NY 10598 USA

We present a discriminant measure that can be used to determine the model complexity in a speech recognition system. In the speech recognition process, sub-phonetic classes are modelled as mixtures of Gaussians, and in this correspondence we present a new discriminant measure that uses the classification accuracy to determine in an objective fashion, the number of Gaussians required to best model the pdf of an allophone class. We compare the performance of this criterion with other criteria such as BIG, and show that BIC and the discriminative criterion lead to parsimonious models that provide the same word error rate performance as much larger baseline systems. However, this performance improvement depends on the size of the system, and there appears to be a crossover point beyond which both BIC and the discriminative criterion are worse than a much simpler criterion. The discriminative criterion also enables this crossover point to be controlled by means of a threshold that is used in the criterion, and can lead to a better tradeoff of complexity versus word error rate.

关键词： BIC discriminative training MCA MDL mixtures of Gaussians model complexity

来源：评论

学校读者我要写书评

暂无评论

model complexity of deep learning: a survey

引用

KNOWLEDGE AND INFORMATION SYSTEMS 2021年第10期63卷 2585-2619页

作者： Hu, Xia Chu, Lingyang Pei, Jian Liu, Weiqing Bian, Jiang Simon Fraser Univ Sch Comp Sci Burnaby BC Canada McMaster Univ Dept Comp & Software Hamilton ON Canada Microsoft Res Beijing Peoples R China

model complexity is a fundamental problem in deep learning. In this paper, we conduct a systematic overview of the latest studies on model complexity in deep learning. model complexity of deep learning can be categorized into expressive capacity and effective model complexity. We review the existing studies on those two categories along four important factors, including model framework, model size, optimization process, and data complexity. We also discuss the applications of deep learning model complexity including understanding model generalization, model optimization, and model selection and design. We conclude by proposing several interesting future directions.

关键词： Deep learning Deep neural network model complexity Expressive capacity

来源：评论

学校读者我要写书评

暂无评论

model complexity, Expectations, and Asset Prices

引用

REVIEW OF ECONOMIC STUDIES 2023年第4期91卷 2462-2507页

作者： Molavi, Pooya Tahbaz-Salehi, Alireza Vedolin, Andrea Northwestern Univ Evanston IL 60208 USA CEPR London England Boston Univ NBER Boston MA USA

This paper analyses how limits to the complexity of statistical models used by market participants can shape asset prices. We consider an economy in which the stochastic process that governs the evolution of economic variables may not have a simple representation, and yet, agents are only capable of entertaining statistical models with a certain level of complexity. As a result, they may end up with a lower-dimensional approximation that does not fully capture the intertemporal complexity of the true data-generating process. We first characterize the implications of the resulting departure from rational expectations and relate the extent of return and forecast-error predictability at various horizons to the complexity of agents' models and the statistical properties of the underlying process. We then apply our framework to study violations of uncovered interest rate parity in foreign exchange markets. We find that constraints on the complexity of agents' models can generate return predictability patterns that are simultaneously consistent with the well-known forward discount and predictability reversal puzzles.

关键词： Subjective expectations model complexity Uncovered interest rate parity

来源：评论

学校读者我要写书评

暂无评论

model complexity Control in Clustering

Model Complexity Control in Clustering

引用

25th International Workshop on Neural Networks (WIRN)

作者： Rovetta, Stefano Univ Genoa DIBRIS Via Dodecaneso 35 I-16146 Genoa Italy

This work deals with model complexity in clustering. Methods to control complexity in unsupervised learning are reviewed. A method that decouples the number of clusters from clustering model complexity is presented an... 详细信息

ISBN: (纸本)9783319337470

关键词： Data clustering model complexity Spectral clustering

来源：评论

学校读者我要写书评

暂无评论

A generalized fuzzy clustering regularization model with optimality tests and model complexity analysis

引用

IEEE TRANSACTIONS ON FUZZY SYSTEMS 2007年第5期15卷 904-915页

作者： Yu, Jian Yang, Miin-Shen Beijing Jiaotong Univ Dept Comp Sci Inst Comp Sci Beijing 100044 Peoples R China Chung Yuan Christian Univ Dept Appl Math Chungli 32023 Taiwan

In this paper, we propose a generalized fuzzy clustering regularization (GFCR) model and then study its theoretical properties. GFCR unifies several fuzzy clustering algorithms, such as fuzzy c-means (FCM), maximum entropy clustering (MEC), fuzzy clustering based on Fermi-Dirac entropy, and fuzzy bidirectional associative clustering network, etc. The proposed GFCR becomes an alternative model of the generalized FCM (GFCM) that was recently proposed by Yu and Yang. To advance theoretical study, we have the following three considerations. 1) We give an optimality test to monitor if GFCR converges to a local minimum. 2) We relate the GFCR optimality tests to Occam's razor principle, and then analyze the model complexity for fuzzy clustering algorithms. 3) We offer a general theoretical method to evaluate the performance of fuzzy clustering algorithms. Finally, some numerical experiments are used to demonstrate the validity of our theoretical results and complexity analysis.

关键词： fuzzy clustering algorithms fuzzy c-means (FCM) generalized fuzzy clustering regularization (GFCR) model optimality test occam's razor principle model complexity parameter selection

来源：评论

学校读者我要写书评

暂无评论

The effect of model complexity in simulating unsaturated zone flow processes on recharge estimation at varying time scales

引用

JOURNAL OF HYDROLOGY 2015年第Part3期529卷 1173-1184页

作者： Ghasemizade, Mehdi Moeck, Christian Schirmer, Mario Eawag Swiss Fed Inst Aquat Sci & Technol CH-8600 Dubendorf Switzerland Univ Neuchatel Ctr Hydrogeol & Geotherm CHYN CH-2000 Neuchatel Switzerland

Recent increases in computational power have led to the development of more advanced physically-based models which can handle a wide range of environmental processes. Although these models are very useful for increasing our understanding of unsaturated zone flow processes, their outputs usually contain high uncertainty, particularly when the level of complexity is not supported by observations. In this context, the aim of this paper is to compare the performance of three different model conceptualizations of a shallow unsaturated soil zone using the physically-based model HydroGeoSphere (HGS). To accomplish this task, we simulated actual evapotranspiration (ET), water content (WC) and discharge (D) from a weighing lysimeter for each of the conceptual models. Conceptual model 1 considers the lysimeter as a homogeneous zone with matrix flow, while Conceptual model 2 has an added preferential flow component. Conceptual model 3 includes layered heterogeneity in addition to the matrix and preferential flow components. The results indicated that the model performance in reproducing daily ET, WC and D improves when we move from simple models to more complex models. A comparison between event-based, monthly, seasonal and yearly time scales indicates that the simplest conceptual model is not reliable for reproducing event-based discharges. However, it can compete with more complex models at annual scales, although the uncertainty bound for the simple model is very high. While increasing complexity from the simplest to the more complex model leads to lower uncertainty bounds and more reliable values of the lysimeter discharge at monthly and seasonal time scales, uncertainty bounds became larger when complexity increased in the most complex model. This is related to a higher number of unknown model parameters in the calibration which are not supported by the available observation datasets. (C) 2015 Elsevier B.V. All rights reserved.

关键词： model complexity Physically-based model hydrogeosphere Seasonal Annual Prediction uncertainty Preferential flow

来源：评论

学校读者我要写书评

暂无评论

Finite element analysis of aircraft tyre - Effect of model complexity on tyre performance characteristics

引用

MATERIALS & DESIGN 2012年 35卷 810-819页

作者： Behroozi, M. Olatunbosun, O. A. Ding, W. Univ Birmingham Sch Mech Engn Birmingham B15 2TT W Midlands England Dunlop Aircraft Tyres Ltd Birmingham B24 9HL W Midlands England

A brief study on the complexity of the structure of aircraft tyres is presented. The main goal is to investigate how complexity of Finite element (FE) models of the tyre can affect the simulation behaviour with respect to accurate prediction of real tyre behaviour. Three FE models, so called "simple", "regular" and "complex" were developed for this investigation so that the accuracy of results obtained from the models for different types of analysis can be determined in comparison with measured test data. For all the simulations carried out, including tyre burst test and tyre inflation, a hyperelastic material property was assumed for modelling rubber and cord materials, using the Yeoh model [1]. Simulations were performed using Abaqus/CAE for two dimensional (2D) analysis and Abaqus command line partly for three dimensional (3D) simulation of tyre inflation. Physical tests were carried out on two tyres for FE model validation in terms of tyre burst test and profile sizing measurements. The results showed excellent accuracy in terms of deformation in FE models by comparison with real size measurements of tyre profiles. Also, a quite good prediction of tyre burst pressure under high inflation was obtained for the different models. Finally, the investigation showed that while maximum stress in cords and maximum deflection of tyres at the rated inflation pressure were fairly insensitive to varying the mesh size in the FE models, maximum stress in the rubber components was particularly sensitive to such mesh size variation. (C) 2011 Elsevier Ltd. All rights reserved.

关键词： Aircraft tyre Finite element analysis model complexity Burst simulation

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：