检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6369-6384页

作者： Wang, Xiuhua Wang, Shuai Li, Yiwei Fan, Fengrui Li, Shikang Lin, Xiaodong Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu611731 China Xiamen University of Technology Fujian Key Laboratory of Communication Network and Information Processing Xiamen361024 China University of Guelph School of Computer Science GuelphONN1G 2W1 Canada

Federated learning (FL) is a popular distributed paradigm where enormous clients collaboratively train a machine learning (ML) model under the orchestration of a central server without knowing the clients' private raw data. The development of effective FL algorithms faces multiple practical challenges including data heterogeneity and clients' privacy protection. Despite that numerous attempts have been made to deal with data heterogeneity or rigorous privacy protection, none have effectively tackled both issues simultaneously. In this article, we propose a differentially private and heterogeneity-robust FL algorithm, named DP-FedCVR to mitigate the data heterogeneity by following the client-variance-reduction strategy. Besides, it adopts a sophisticated differential privacy (DP) mechanism where the privacy-amplified strategy is applied, to achieve a rigorous privacy protection guarantee. We show that the proposed DP-FedCVR algorithm maintains its heterogeneity-robustness though DP noises are incorporated, while achieving a sublinear convergence rate for a nonconvex FL problem. Numerical experiments based on image classification tasks are presented to demonstrate that DP-FedCVR provides superior performance over the benchmark algorithms in the presence of data heterogeneity and various DP privacy budgets. © 2020 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Massively parallel algorithms for fully dynamic all-pairs shortest paths

引用

Frontiers of Computer Science 2024年第4期18卷 201-203页

作者： Chilei WANG Qiang-Sheng HUA Hai JIN Chaodong ZHENG National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China

1 Introduction In recent years,the Massively Parallel Computation(MPC)model has gained significant ***,most of distributed and parallel graph algorithms in the MPC model are designed for static graphs[1].In fact,the graphs in the real world are constantly *** size of the real-time changes in these graphs is smaller and more *** graph algorithms[2,3]can deal with graph changes more efficiently[4]than the corresponding static graph ***,most studies on dynamic graph algorithms are limited to the single machine ***,a few parallel dynamic graph algorithms(such as the graph connectivity)in the MPC model[5]have been proposed and shown superiority over their parallel static counterparts.

关键词： dynamic shortest gained

来源：评论

学校读者我要写书评

暂无评论

Efficient Homomorphic Approximation of Max Pooling for Privacy-Preserving Deep Learning 6th

Efficient Homomorphic Approximation of Max Pooling for Pri...

引用

6th International Conference on Machine Learning for Cyber Security, ML4CS 2024

作者： Zhang, Peng Qiu, Dongyan Duan, Ao Liu, Hongwei The Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Guangdong Shenzhen518060 China College of Big Data and Internet Shenzhen Technology University Guangdong Shenzhen518118 China

ISBN: (纸本)9789819645657

Privacy-Preserving Deep Learning (PPDL) using Fully Homomorphic Encryption (FHE) addresses potential data privacy exposure risks associated with deploying deep learning models in untrusted cloud environments. FHE-based PPDL enables users to encrypt their data locally, allowing cloud service providers to perform computations directly on the encrypted data without ever accessing it. However, FHE faces challenges in efficiently handling nonlinear computations, which are essential to deep learning frameworks, particularly in implementing activation functions and max pooling layers. To address this challenge, we improve the homomorphic max pooling approximation scheme HMaxPool, and propose an efficient homomorphic max pooling algorithm, denoted as HMaxPool+. Specifically, we first redefine the approximation of the maximum function, and then design sub-algorithm to address the potential output expansion issue. The experimental results validate that both the homomorphic max pooling algorithm itself and the corresponding homomorphic SqueezeNet neural network demonstrate enhancements in computational efficiency and accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Comprehensive recovery of W,V,and Ti from spent selective reduction catalysts

引用

Rare Metals 2023年第10期42卷 3518-3531页

作者： Li-Wen Ma Xiao-Li Xi Jia-Peng Chen Fan Guo Zi-Jie Yang Zuo-Ren Nie Key Laboratory of Advanced Functional Materials Ministry of EducationFaculty of Materials and ManufacturingBeijing University of TechnologyBeijing100124China Collaborative Innovation Center of Capital Resource-Recycling Material Technology Beijing University of TechnologyBeijing100124China National Engineering Laboratory for Industrial Big-Data Application Technology Beijing University of TechnologyBeijing100124China

In this study,spent WO_(3)/V_(2)O_(5)-TiO_(2) catalysts used for selective catalytic reduction were treated by a hydrometallurgical process to comprehensively recover valuable metallic elements,such as W,V,and *** and Si impurities were preferentially removed by selective micro wave-assisted alkali leaching.W and V were leached by enhanced high-pressure leaching with efficiencies estimated at 95% and 81%.The leaching of W and V followed the nuclear shrinkage model controlled by the combination of product layer diffusion and interfacial chemical reaction.A synergistic extraction was applied to separate W and V using an extractant mixture of di-(2-ethylhexyl)phosphoric acid P204 and the primary amine *** extraction efficiencies of V and W reached 86.5% and 6.3%,respectively,with a separation coefficient(V/W) of *** product was precipitated after extraction to yield ammonium paratung state(APT) and NH_(4)VO_(3).The TiO_(2)catalyst carrier residue meets commercial specifications for *** comprehensive recovery process with the characteristics of high-pressure leaching and synergistic extraction realizes the resourceful utilization of the spent catalysts.

关键词： Spent selective catalytic reduction(SCR)catalysts Microwaveleaching Pressure leaching Synergistic extraction Comprehensive recovery

来源：评论

学校读者我要写书评

暂无评论

Clause-level Relationship-aware Math Word Problems Solver

引用

Machine Intelligence Research 2022年第5期19卷 425-438页

作者： Chang-Yang Wu Xin Lin Zhen-Ya Huang Yu Yin Jia-Yu Liu Qi Liu Gang Zhou Anhui Province Key Laboratory of Big Data Analysis and Application School of Data ScienceUniversity of Science and Technology of ChinaHefei 230026China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Laboratory of Mathematical Engineering and Advanced Computing Information Engineering UniversityZhengzhou 450001China

Automatically solving math word problems,which involves comprehension,cognition,and reasoning,is a crucial issue in artificial intelligence *** math word problem solvers mainly work on word-level relationship extraction and the generation of expression solutions while lacking consideration of the clause-level *** this end,inspired by the theory of two levels of process in comprehension,we propose a novel clause-level relationship-aware math solver(CLRSolver)to mimic the process of human comprehension from lower level to higher ***,in the lower-level processes,we split problems into clauses according to their natural division and learn their *** the higher-level processes,following human′s multi-view understanding of clause-level relationships,we first apply a CNN-based module to learn the dependency relationships between clauses from word relevance in a local ***,we propose two novel relationship-aware mechanisms to learn dependency relationships from the clause semantics in a global ***,we enhance the representation of clauses based on the learned clause-level dependency *** expression generation,we develop a tree-based decoder to generate the mathematical *** conduct extensive experiments on two datasets,where the results demonstrate the superiority of our framework.

关键词： Artificial intelligence(AI) artificial neural network(ANN) computational mathematics machine intelligence machine learning

来源：评论

学校读者我要写书评

暂无评论

Face micro-expression recognition algorithm based on ResNet depth model

Face micro-expression recognition algorithm based on ResNet ...

引用

6th International Conference on Intelligent Computing and Signal Processing (ICSP)

作者： Liquan Wang Shu Zhan School of Computer and Information Engineering Hefei University of Technology Key Laboratory of Big Data Knowledge Engineering Ministry of Education Hefei China

Micro Expression (ME) is the subtle facial expressions that people show when they express their inner feelings. To address the problem that micro-expression recognition is difficult and less accurate due to the small number of samples and uneven distribution of different categories, we propose a model framework to improve the accuracy of micro-expression recognition. The peak frames containing more key expression information in the micro-expression video sequences are extracted; SE-ResNeXt-50, an improved residual network with SE module, is used to extract features from the peak frames of micro-expressions, where the SE module can better learn the key information in the features, and ResNeXt simplifies the structure by replacing the dense structure with the sparse structure through group convolution, which improves the recognition efficiency. The recognition efficiency is improved by replacing the dense structure with the sparse structure by group convolution. At the same time, the Focal Loss loss function can better solve the model performance problem caused by the imbalance of micro-expression data. Simulation experiments are conducted on the micro-expression dataset CASMEⅡ, and it is found that the improved residual network and peak frame improve the accuracy and F1 value of micro-expression recognition. The improved residual network and peak frame can reduce the effect of small data set, make the model have good fitting effect, and improve the performance of different categories, improve the recognition accuracy of micro-expressions, and have better recognition performance for micro-expression recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive data-Free Quantization

arXiv

引用

arXiv 2023年

作者： Qian, Biao Wang, Yang Hong, Richang Wang, Meng Key Laboratory of Knowledge Engineering with Big Data Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology China

data-free quantization (DFQ) recovers the performance of quantized network (Q) without accessing the original data, but generates the fake sample via a generator (G) by learning from full-precision network (P), which, however, is totally independent of Q, overlooking the adaptability of the knowledge from generated samples, i.e., informative or not to the learning process of Q, resulting into the overflow of generalization error. Building on this, several critical questions - how to measure the sample adaptability to Q under varied bit-width scenarios? how to generate the samples with large adaptability to improve Q's generalization? whether the largest adaptability is the best? To answer the above questions, in this paper, we propose an Adaptive data-Free Quantization (AdaDFQ) method, which revisits DFQ from a zero-sum game perspective upon the sample adaptability between two players - a generator and a quantized network. Following this viewpoint, we further define the disagreement and agreement samples to form two boundaries, where the margin is optimized to address the over-and-under fitting issues, so as to generate the samples with adaptive adaptability to Q. Our AdaDFQ reveals: 1) the largest adaptability is NOT the best for sample generation to benefit Q's generalization;2) the knowledge of the generated sample should not be informative to Q only, but also related to the category and distribution information of the training data for P. The theoretical and empirical analysis validate the advantages of AdaDFQ over the state-of-the-arts. Our code is available at https://***/hfutqian/AdaDFQ. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Rethinking data-Free Quantization as a Zero-Sum Game

arXiv

引用

arXiv 2023年

data-free quantization (DFQ) recovers the performance of quantized network (Q) without accessing the real data, but generates the fake sample via a generator (G) by learning from full-precision network (P) instead. However, such sample generation process is totally independent of Q, specialized as failing to consider the adaptability of the generated samples, i.e., beneficial or adversarial, over the learning process of Q, resulting into non-ignorable performance loss. Building on this, several crucial questions — how to measure and exploit the sample adaptability to Q under varied bit-width scenarios? how to generate the samples with desirable adaptability to benefit the quantized network? — impel us to revisit DFQ. In this paper, we answer the above questions from a game-theory perspective to specialize DFQ as a zero-sum game between two players — a generator and a quantized network, and further propose an Adaptability-aware Sample Generation (AdaSG) method. Technically, AdaSG reformulates DFQ as a dynamic maximization-vs-minimization game process anchored on the sample adaptability. The maximization process aims to generate the sample with desirable adaptability, such sample adaptability is further reduced by the minimization process after calibrating Q for performance recovery. The Balance Gap is defined to guide the stationarity of the game process to maximally benefit Q. The theoretical analysis and empirical studies verify the superiority of AdaSG over the state-of-the-arts. Our code is available at https://***/hfutqian/AdaSG. Copyright © 2023, The Authors. All rights reserved.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Winter wheat phenology classification using stacking ensemble learning algorithm based on Sentinel-1A SAR images 5

Winter wheat phenology classification using stacking ensembl...

引用

5th International Conference on Geoscience and Remote Sensing Mapping, ICGRSM 2023

作者： Duan, Haoxin Yang, Huijin Zhao, Jianhui Li, Ning School of Computer and Information Engineering Henan University Kaifeng China Henan Province Engineering Research Center of Spatial Information Processing Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

ISBN: (纸本)9781510672789

Crop monitoring and phenology estimation based on the satellite systems have become an important research area due to high demand on crops. Synthetic Aperture Radar (SAR) is a kind of microwave remote sensing equipment, which has the advantage of all-weather and all-day, and can realize large-scale and periodic crop phenological monitoring. Besides, thanks to the high temporal resolution of new generation space-based sensors, it has been possible to monitor growth cycle of crops by classification algorithms. A stacking ensemble learning algorithm using time series Sentinel-1A SAR images for winter wheat phenology classification was proposed in this paper based on multiple machine learning models, including Random Forest (RF), Support Vector Machine (SVM), K-nearest Neighbor(K-NN), Naive Bayes (NB) and BP Neural Network (BP) models. The experimental results showed that, comparing with each single model, the stacking ensemble learning algorithm proposed in this paper had the optimal performance, with the highest overall recognition accuracy of 81.40%, demonstrating its effectiveness and application potential for winter wheat phenology identification. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

An Effective Security Comparison Protocol in Cloud Computing

引用

Computers, Materials & Continua 2023年第6期75卷 5141-5158页

作者： Yuling Chen Junhong Tao Tao Li Jiangyuan Cai Xiaojun Ren State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550000China Guangxi Key Laboratory of Cryptography and Information Security Guilin University of Electronic TechnologyGuilin550000China POWERCHINA Guizhou Electric Power Engineering Co. Ltd.Guiyang550000China Blockchain Laboratory of Agricultural Vegetables Weifang University of Science and TechnologyWeifang261000China

With the development of cloud computing technology,more and more data owners upload their local data to the public cloud server for storage and *** this can save customers’operating costs,it also poses privacy and security *** challenges can be solved using secure multi-party computation(SMPC),but this still exposes more security *** cloud computing using SMPC,clients need to process their data and submit the processed data to the cloud server,which then performs the calculation and returns the results to each *** client and server must be *** there is cooperation or dishonest behavior between clients,some clients may profit from it or even disclose the private data of other *** paper proposes the SMPC based on a Partially-Homomorphic Encryption(PHE)scheme in which an addition homomorphic encryption algorithm with a lower computational cost is used to ensure data comparability and Zero-knowledge Proof(ZKP)is used to limit the client’s malicious *** addition,the introduction of Oblivious Transfer(OT)technology also ensures that the semi-honest cloud server knows nothing about private data,so that the cloud server of this scheme can calculate the correct data in the case of malicious participant models and safely return the calculation results to each ***,the security analysis shows that the scheme not only ensures the privacy of participants,but also ensures the fairness of the comparison protocol data.

关键词： Secure comparison protocols zero-knowledge proof homomorphic encryption cloud computing

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：