检索结果-内蒙古大学图书馆

Gradient sparsification for efficient wireless federated learning with differential privacy

science China(Information sciences) 2024年第4期67卷 272-288页

作者： Kang WEI Jun LI Chuan MA Ming DING Feng SHU Haitao ZHAO Wen CHEN Hongbo ZHU School of Electronic and Optical Engineering Nanjing University of Science and Technology Zhejiang Lab Key Laboratory of Computer Network and Information Integration(Southeast University) Ministry of Education Data61 Commonwealth Scientific and Industrial Research Organisation School of Information and Communication Engineering Hainan University School of Communications and Information Engineering Nanjing University of Posts and Telecommunications School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University

Federated learning(FL) enables distributed clients to collaboratively train a machine learning model without sharing raw data with each other. However, it suffers from the leakage of private information from uploading models. In addition, as the model size grows, the training latency increases due to the limited transmission bandwidth and model performance degradation while using differential privacy(DP)protection. In this paper, we propose a gradient sparsification empowered FL framework with DP over wireless channels, to improve training efficiency without sacrificing convergence performance. Specifically, we first design a random sparsification algorithm to retain a fraction of the gradient elements in each client's local model, thereby mitigating the performance degradation induced by DP and reducing the number of transmission parameters over wireless channels. Then, we analyze the convergence bound of the proposed algorithm, by modeling a non-convex FL problem. Next, we formulate a time-sequential stochastic optimization problem for minimizing the developed convergence bound, under the constraints of transmit power, the average transmitting delay, as well as the client's DP requirement. Utilizing the Lyapunov drift-plus-penalty framework, we develop an analytical solution to the optimization problem. Extensive experiments have been implemented on three real-life datasets to demonstrate the effectiveness of our proposed algorithm. We show that our proposed algorithms can fully exploit the interworking between communication and computation to outperform the baselines, i.e., random scheduling, round robin, and delay-minimization algorithms.

关键词： federated learning differential privacy gradient sparsification Lyapunov drift convergence analysis

来源：评论

学校读者我要写书评

暂无评论

Designing adaptive nonlinear controller for optimal tracking of laparoscopic robotic arm with nonholonomic constraints

Designing adaptive nonlinear controller for optimal tracking...

引用

作者： Ghavifekr, Amir Aminzadeh Hassani, Roushanak Haji Calanca, Andrea Department of Electrical and Computer Engineering University of Tabriz Tabriz Iran BIROMED-Lab Deptartment of Biomedical Engineering University of Basel Basel Switzerland Department of Computer Science University of Verona Verona Italy

Laparoscopic surgery is one kind of minimally invasive surgery in which surgeons can control and evaluate the tracking of the robot via special monitoring. Preserving stability, precise tracking, and uncertainties estimation are essential factors in controller design for these systems. Designing autonomous graspers would improve the perception of surgeons and reduce the unwanted errors of operations. An adaptive inverse dynamic controller is proposed in this paper to improve the performance of the tracking desired trajectories for gripper of the surgical robots used in laparoscopic surgeries. By considering nonholonomic conditions for the grasper of the robot, the workspace is generalized, and using the Ritz approximation method, the optimal steering problem for nonholonomic gripper has been solved. In this case, the surgeon can steer the gasper of the surgical robot from any initial condition to any desired destination point. The performance of the proposed controller for nonholonomic conditions is demonstrated by simulation results. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Robotic surgery

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-and Transfer Learning-based Models for COVID-19 Detection using Radiography Images

Deep Learning-and Transfer Learning-based Models for COVID-1...

引用

Advances in Electronics, Control and Communication Systems (ICAECCS), International Conference on

作者： Ahmed Cherif Mazari Hamza Kheddar Dept. of Mathematics and Computer Science Faculty of Science LSEA Lab University of Medea Medea Algeria Dept. of Electrical Engineering Faculty of Technology LSEA Lab University of Medea Medea Algeria

Image classification and segmentation techniques are still very popular in the medical field (for healthcare), in which the medical image plays an important role in the detection and screening of diseases. Recently, the spread of new viral diseases, namely Covid-19, requires powerful computer models and rich resources (datasets) to fight this phenomenon. In this study, we propose to examine the CNN Deep Learning algorithm and two Transfer Learning models, namely RestNet50 and MobileNetV2 using the pretrained model of the ImageNet database, experimented on the new dataset (COVID-QU-Ex Dataset 2022) offered by the University of Qatar. These models are tested to classify radiography images into two classes (Covid19 and Normal). The results achieved by CNN (Acc =95.97%), ResNet50 (Acc =95.53%) and MobileNetV2 (Acc =97.32%) show that these algorithms are promising in order to combat this Covid-19 disease by detecting it through thoracic images (Chest X-ray type).

关键词： COVID-19 Radiography Deep learning Computational modeling Transfer learning Classification algorithms X-ray imaging

来源：评论

学校读者我要写书评

暂无评论

ENVIRONMENTALLY FRIENDLY SOLAR ENERGY: POTENTIAL OF UTILIZING FIELD MARGINS IN RURAL AREAS FOR PHOTOVOLTAIC SYSTEMS IN COMBINATION WITH WILDFLOWER STRIPS 22

ENVIRONMENTALLY FRIENDLY SOLAR ENERGY: POTENTIAL OF UTILIZIN...

引用

22nd Wind and Solar Integration Workshop, WIW 2023

作者： Wunder, Kerstin Foth, Hannes Rolink, Johannes Kayser, Manfred Department of Electrical Engineering and Computer Science University of Applied Sciences Emden/Leer Emden Germany Institute for Applied Photogrammetry and Geoinformatics Jade University of Applied Sciences Oldenburg Germany Geo-Lab University of Vechta Vechta Germany Department of Crop Sciences University of Göttingen Göttingen Germany

ISBN: (纸本)9781839539824

This study assesses the economic potential of using field margins and wildflower strips in rural northwest Lower Saxony, Germany, for eco-friendly solar energy generation. Field margins, located at the edges of farmland, serve as buffers between crops and surrounding ecosystems and can promote biodiversity by using as wildflower strips. By integrating photovoltaic (PV) systems within these field margins, the study aims to investigate clean electricity production while preserving ecological balance. To estimate the potential of grid-connected field margin PV (FMPV), the paper considers regulatory, technical, and economic factors. Using geographic data, suitable areas are identified. The study assesses regulatory influence on FMPV operations and evaluates grid connection points' availability for economic analysis. Results show that 19,378 km of field margins are potentially suitable for grid-connected FMPV, implying an electricity generation potential of 23.6 TWh/a. However, compatible margins constitute just 15.5 % of existing field margins. The combination of wildflower strips and grid-connected FMPV provides an innovative energy approach in rural areas, however, this study highlights high grid connection costs. Off-grid photovoltaic systems seem more practical. Prioritizing off-grid systems for on-site electricity utilization and exploring affordable alternatives are essential for enhancing the economic viability of FMPV systems in rural areas. © Energynautics GmbH.

关键词： Rural areas

来源：评论

学校读者我要写书评

暂无评论

Efficient Federated Learning Using Dynamic Update and Adaptive Pruning with Momentum on Shared Server Data

arXiv

引用

arXiv 2024年

作者： Liu, Ji Jia, Juncheng Zhang, Hong Yun, Yuhui Wang, Leye Zhou, Yang Dai, Huaiyu Dou, Dejing Hithink RoyalFlush Information Network Co. Ltd. Hangzhou China School of Computer Science and Technology Soochow University Collaborative Innovation Center of Novel Software Technology and Industrialization Suzhou China School of Computer Science and Technology Soochow University Suzhou China Baidu Research Beijing China Key Lab of High Confidence Software Technologies Ministry of Education Software Institute Peking University Beijing China Department of Computer Science and Software Engineering Auburn University Auburn United States Department of Electrical and Computer Engineering North Carolina State University NC United States BEDI Cloud and School of Computer Science Fudan University Beijing China

Despite achieving remarkable performance, Federated Learning (FL) encounters two important problems, i.e., low training efficiency and limited computational resources. In this paper, we propose a new FL framework, i.e., FedDUMAP, with three original contributions, to leverage the shared insensitive data on the server in addition to the distributed data in edge devices so as to efficiently train a global model. First, we propose a simple dynamic server update algorithm, which takes advantage of the shared insensitive data on the server while dynamically adjusting the update steps on the server in order to speed up the convergence and improve the accuracy. Second, we propose an adaptive optimization method with the dynamic server update algorithm to exploit the global momentum on the server and each local device for superior accuracy. Third, we develop a layer-adaptive model pruning method to carry out specific pruning operations, which is adapted to the diverse features of each layer so as to attain an excellent trade-off between effectiveness and efficiency. Our proposed FL model, FedDUMAP, combines the three original techniques and has a significantly better performance compared with baseline approaches in terms of efficiency (up to 16.9 times faster), accuracy (up to 20.4% higher), and computational cost (up to 62.6% smaller). © 2024, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

LLMParser: An Exploratory Study on Using Large Language Models for Log Parsing

LLMParser: An Exploratory Study on Using Large Language Mode...

引用

International Conference on Software engineering (ICSE)

作者： Zeyang Ma An Ran Chen Dong Jae Kim Tse-Hsun Peter Chen Shaowei Wang Software PEformance Analysis and Reliability (SPEAR) Lab Concordia University Montreal Quebec Canada Electrical and Computer Engineering Department University of Alberta Edmonton Alberta Canada Department of Computer Science University of Manitoba Winnipeg Manitoba Canada

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

Logs are important in modern software development with runtime information. Log parsing is the first step in many log-based analyses, that involve extracting structured information from unstructured log data. Traditional log parsers face challenges in accurately parsing logs due to the diversity of log formats, which directly impacts the performance of downstream log-analysis tasks. In this paper, we explore the potential of using Large Language Models (LLMs) for log parsing and propose LLMParser, an LLM-based log parser based on generative LLMs and few-shot tuning. We leverage four LLMs, Flan-T5-small, Flan-T5-base, LLaMA-7B, and ChatGLM-6B in LLMParsers. Our evaluation of 16 open-source systems shows that LLMParser achieves statistically significantly higher parsing accuracy than state-of-the-art parsers (a 96% average parsing accuracy). We further conduct a comprehensive empirical analysis on the effect of training size, model size, and pre-training LLM on log parsing accuracy. We find that smaller LLMs may be more effective than more complex LLMs; for instance where Flan-T5-base achieves comparable results as LLaMA-7B with a shorter inference time. We also find that using LLMs pre-trained using logs from other systems does not always improve parsing accuracy. While using pre-trained Flan-T5-base shows an improvement in accuracy, pre-trained LLaMA results in a decrease (decrease by almost 55% in group accuracy). In short, our study provides empirical evidence for using LLMs for log parsing and highlights the limitations and future research direction of LLM-based log parsers.

关键词： Training Analytical models Runtime computer architecture Inference algorithms Data mining Task analysis

来源：评论

学校读者我要写书评

暂无评论

Ultra-Thinned Individual SOI die ACF Fc Bonded on Rigid and Flex PCB 23

Ultra-Thinned Individual SOI die ACF Fc Bonded on Rigid and ...

引用

23rd European Microelectronics and Packaging Conference and Exhibition, EMPC 2021

作者： Stoukatch, Serguei André, Nicolas Dupont, Francois Redouté, Jean-Michel Flandre, Denis Microsys lab Department of Electrical Engineering and Computer Science Liege University Seraing Belgium UC Louvain Louvain-la-Neuve Belgium

ISBN: (纸本)9780956808677

We have developed a straightforward die-level thinning process suitable for Silicon-On-Insulator (SOI) dies. The process has been demonstrated on SOI CMOS die assembled on rigid and flexible PCBs using previously-developed anisotropic conductive adhesive flip-chip method. Unlike standard wafer-level thinning processes, in the demonstrated process the full thickness SOI die is directly mounted on PCB and after that thinned. The demonstrated process is simple and robust;it comprises fewer process steps compared to conventional die thinning process. The ultra-thinning process has no effects on the assembly integrity and device performance. © 2021 2021 23rd European Microelectronics and Packaging Conference and Exhibition, EMPC 2021. All rights reserved.

关键词： Dies

来源：评论

学校读者我要写书评

暂无评论

Enhancing Skin Cancer Diagnosis (SCD) Using Late Discrete Wavelet Transform (DWT) and New Swarm-Based Optimizers

arXiv

引用

arXiv 2024年

作者： Mousa, Ramin Chamani, Saeed Morsali, Mohammad Kazzazi, Mohammad Hatami, Parsa Sarabi, Soroush University of Zanjan Department of Computer Engineering Zanjan Iran Iran University of Science and Technology Department of Biomedical Engineering Tehran Iran Sharif University of Technology Department of Electrical Engineering Tehran Iran Raderon AI Lab BC Canada

Skin cancer (SC) stands out as one of the most life-threatening forms of cancer, with its danger amplified if not diagnosed and treated promptly. Early intervention is critical, as it allows for more effective treatment approaches, potentially halting the disease’s progression and improving patient outcomes. In recent years, Deep Learning (DL) has emerged as a powerful tool in the early detection and skin cancer diagnosis (SCD). Although the DL seems promising for the diagnosis of skin cancer, still ample scope exists for improving model efficiency and accuracy. This paper proposes a novel approach to skin cancer detection, utilizing optimization techniques in conjunction with pre-trained networks and wavelet transformations. First, normalized images will undergo pre-trained networks such as Densenet-121, Inception, Xception, and MobileNet to extract hierarchical features from input images. After feature extraction, the feature maps are passed through a Discrete Wavelet Transform (DWT) layer to capture low and high-frequency components. Then the self-attention module is integrated to learn global dependencies between features and focus on the most relevant parts of the feature maps. The number of neurons and optimization of the weight vectors are performed using three new swarm-based optimization techniques, such as Modified Gorilla Troops Optimizer (MGTO), Improved Gray Wolf Optimization (IGWO), and Fox optimization algorithm, to improve the efficacy of the model and diagnostic accuracy. Evaluation results demonstrate that optimizing weight vectors using optimization algorithms can enhance diagnostic accuracy and make it a highly effective approach for SCD. The proposed method demonstrates substantial improvements in accuracy, achieving top rates of 98.11% with the MobileNet + Wavelet + FOX and DenseNet + Wavelet + Fox combination on the ISIC-2016 dataset and 97.95% with the Inception + Wavelet + MGTO combination on the ISIC-2017 dataset, which improves accuracy by

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Purify unlearnable examples via rate-constrained variational autoencoders 24

Purify unlearnable examples via rate-constrained variational...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Yi Yu Yufei Wang Song Xia Wenhan Yang Shijian Lu Yap-Peng Tan Alex C. Kot Rapid-Rich Object Search Lab Interdisciplinary Graduate Programme and School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore PengCheng Laboratory Shenzhen China School of Computer Science and Engineering Nanyang Technological University Singapore

Unlearnable examples (UEs) seek to maximize testing error by making subtle modifications to training examples that are correctly labeled. Defenses against these poisoning attacks can be categorized based on whether specific interventions are adopted during training. The first approach is training-time defense, such as adversarial training, which can mitigate poisoning effects but is computationally intensive. The other approach is pre-training purification, e.g., image short squeezing, which consists of several simple compressions but often encounters challenges in dealing with various UEs. Our work provides a novel disentanglement mechanism to build an efficient pre-training purification method. Firstly, we uncover rate-constrained variational autoencoders (VAEs), demonstrating a clear tendency to suppress the perturbations in UEs. We subsequently conduct a theoretical analysis for this phenomenon. Building upon these insights, we introduce a disentangle variational autoencoder (DVAE), capable of disentangling the perturbations with learnable class-wise embeddings. Based on this network, a two-stage purification approach is naturally developed. The first stage focuses on roughly eliminating perturbations, while the second stage produces refined, poison-free results, ensuring effectiveness and robustness across various scenarios. Extensive experiments demonstrate the remarkable performance of our method across CIFAR-10, CIFAR-100, and a 100-class ImageNet-subset. Code is available at https://***/yuyi-sd/D-VAE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LECF: recommendation via learnable edge collaborative filtering

引用

science China(Information sciences) 2022年第1期65卷 116-130页

作者： Shitao XIAO Yingxia SHAO Yawen LI Hongzhi YIN Yanyan SHEN Bin CUI School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing Key Lab of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications School of Information Technology and Electrical Engineering The University of Queensland Department of Computer Science and Engineering Shanghai Jiao Tong University Department of Computer Science and Technology Peking University National Engineering Laboratory for Big Data Analysis and Applications Peking University

The core of recommendation models is estimating the probability that a user will like an item based on historical interactions. Existing collaborative filtering(CF) algorithms compute the likelihood by utilizing simple relationships between objects, e.g., user-item, item-item, or user-user. They always rely on a single type of object-object relationship, ignoring other useful relationship information in data. In this paper, we model an interaction between user and item as an edge and propose a novel CF framework, called learnable edge collaborative filtering(LECF). LECF predicts the existence probability of an edge based on the connections among edges and is able to capture the complex relationship in data. Specifically, we first adopt the concept of line graph where each node represents an interaction edge; then calculate a weighted sum of similarity between the query edge and the observed edges(i.e., historical interactions) that are selected from the neighborhood of query edge in the line graph for a recommendation. In addition, we design an efficient propagation algorithm to speed up the training and inference of LECF. Extensive experiments on four public datasets demonstrate LECF can achieve better performance than the state-of-the-art methods.

关键词： collaborative filtering recommender system implicit feedback edge-edge similarity line graph

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：