检索结果-南通市图书馆

Federatedmutual learning:a collaborative machine learning method for heterogeneous data,models,and objectives

Frontiers of Information Technology & Electronic Engineering 2023年第10期24卷 1390-1402页

作者： Tao SHEN Jie ZHANG Xinkang JIA Fengda ZHANG Zheqi LV kun kuang Chao WU Fei WU College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China School of Software Technology Zhejiang UniversityHangzhou 310027China School of Public Affairs Zhejiang UniversityHangzhou 310027China

Federated learning(FL)is a novel technique in deep learning that enables clients to collaboratively train a shared model while retaining their decentralized data.However,researchers working on FL face several unique challenges,especially in the context of heterogeneity.Heterogeneity in data distributions,computational capabilities,and scenarios among clients necessitates the development of customized models and objectives in FL.Unfortunately,existing works such as FedAvg may not effectively accommodate the specific needs of each client.To address the challenges arising from heterogeneity in FL,we provide an overview of the heterogeneities in data,model,and objective(DMO).Furthermore,we propose a novel framework called federated mutual learning(FML),which enables each client to train a personalized model that accounts for the data heterogeneity(DH).A“meme model”serves as an intermediary between the personalized and global models to address model heterogeneity(MH).We introduce a knowledge distillation technique called deep mutual learning(DML)to transfer knowledge between these two models on local data.To overcome objective heterogeneity(OH),we design a shared global model that includes only certain parts,and the personalized model is task-specific and enhanced through mutual learning with the meme model.We evaluate the performance of FML in addressing DMO heterogeneities through experiments and compare it with other commonly used FL methods in similar scenarios.The results demonstrate that FML outperforms other methods and effectively addresses the DMO challenges encountered in the FL setting.

关键词： Federated learning Knowledge distillation Privacy preserving Heterogeneous environment

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A full-process intelligent trial system for smart court

引用

Frontiers of Information Technology & Electronic Engineering 2022年第2期23卷 186-206页

作者： Bin WEI kun kuang Changlong SUN Jun FENG Yating ZHANG Xinli ZHU Jianghong ZHOU Yinsheng ZHAI Fei WU Guanghua Law School Zhejiang UniversityHangzhou 310008China College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China Alibaba Group Hangzhou 310099China State Grid Zhejiang Electric Power Co. Ltd.Hangzhou 310007China Zhejiang Higher People’s Court Hangzhou 310012China

In constructing a smart court,to provide intelligent assistance for achieving more efficient,fair,and explainable trial proceedings,we propose a full-process intelligent trial system(FITS).In the proposed FITS,we introduce essential tasks for constructing a smart court,including information extraction,evidence classification,question generation,dialogue summarization,judgment prediction,and judgment document generation.Specifically,the preliminary work involves extracting elements from legal texts to assist the judge in identifying the gist of the case efficiently.With the extracted attributes,we can justify each piece of evidence’s validity by establishing its consistency across all evidence.During the trial process,we design an automatic questioning robot to assist the judge in presiding over the trial.It consists of a finite state machine representing procedural questioning and a deep learning model for generating factual questions by encoding the context of utterance in a court debate.Furthermore,FITS summarizes the controversy focuses that arise from a court debate in real time,constructed under a multi-task learning framework,and generates a summarized trial transcript in the dialogue inspectional summarization(DIS)module.To support the judge in making a decision,we adopt first-order logic to express legal knowledge and embed it in deep neural networks(DNNs)to predict judgments.Finally,we propose an attentional and counterfactual natural language generation(AC-NLG)to generate the court’s judgment.

关键词： Intelligent trial system Smart court Evidence analysis Dialogue summarization Focus of controversy Automatic questioning Judgment prediction

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Federated unsupervised representation learning

引用

信息与电子工程前沿:英文版 2023年第8期24卷 1181-1193页

作者： Fengda ZHANG kun kuang Long CHEN Zhaoyang YOU Tao SHEN Jun XIAO Yin ZHANG Chao WU Fei WU Yueting ZHUANG Xiaolin LI College of Computer Science and Technology Zhejiang UniversityHangzhou310027China School of Public Affairs Zhejiang UniversityHangzhou310027China Tongdun Technology Hangzhou310000China Institute of Basic Medicine and Cancer Chinese Academy of SciencesHangzhou310018China Elastic Mind.AI Technology Inc. Hangzhou310018China

To leverage the enormous amount of unlabeled data on distributed edge devices,we formulate a new problem in federated learning called federated unsupervised representation learning(FURL)to learn a common representation model without supervision while preserving data privacy.FURL poses two new challenges:(1)data distribution shift(non-independent and identically distributed,non-IID)among clients would make local models focus on different categories,leading to the inconsistency of representation spaces;(2)without unified information among the clients in FURL,the representations across clients would be misaligned.To address these challenges,we propose the federated contrastive averaging with dictionary and alignment(FedCA)algorithm.FedCA is composed of two key modules:a dictionary module to aggregate the representations of samples from each client which can be shared with all clients for consistency of representation space and an alignment module to align the representation of each client on a base model trained on public data.We adopt the contrastive approach for local model training.Through extensive experiments with three evaluation protocols in IID and non-IID settings,we demonstrate that FedCA outperforms all baselines with significant margins.

关键词： Federated learning Unsupervised learning Representation learning Contrastive learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Causal Inference

引用

Engineering 2020年第3期6卷 253-263页

作者： kun kuang Lian Li Zhi Geng Lei Xu kun Zhang Beishui Liao Huaxin Huang Peng Ding Wang Miao Zhichao Jiang College of Computer Science and Technology Zhejiang UniversityHangzhou 310058China Department of Computer Science and Technology Hefei University of TechnologyHefei 230009China School of Mathematical Science Peking UniversityBeijing 100871China Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China Department of Philosophy Carnegie Mellon UniversityPittsburghPA 15213USA School of Humanities Zhejiang UniversityHangzhou 310058China University of California Berkeley BerkeleyCA 94720USA Guanghua School of Management Peking UniversityBeijing 100871China Department of Government&Department of Statistics Harvard UniversityCambridgeMA 02138USA

Causal inference is a powerful modeling tool for explanatory analysis,which might enable current machine learning to become explainable.How to marry causal inference with machine learning to develop explainable artificial intelligence(XAI)algorithms is one of key steps toward to the artificial intelligence 2.0.With the aim of bringing knowledge of causal inference to scholars of machine learning and artificial intelligence,we invited researchers working on causal inference to write this survey from different aspects of causal inference.This survey includes the following sections:“Estimating average treatment effect:A brief review and beyond”from Dr.kun kuang,“Attribution problems in counterfactual inference”from Prof.Lian Li,“The Yule–Simpson paradox and the surrogate paradox”from Prof.Zhi Geng,“Causal potential theory”from Prof.Lei Xu,“Discovering causal information from observational data”from Prof.kun Zhang,“Formal argumentation in causal reasoning and explanation”from Profs.Beishui Liao and Huaxin Huang,“Causal inference with complex experiments”from Prof.Peng Ding,“Instrumental variables and negative controls for observational studies”from Prof.Wang Miao,and“Causal inference with interference”from Dr.Zhichao Jiang.

关键词： Causal inference Instructive variables Negative control Causal reasoning and explanation Causal discovery Counterfactual inference Treatment effect estimation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

How to Interpret Machine Knowledge

引用

Engineering 2020年第3期6卷 218-220页

作者： Fashen Li Lian Li Jianping Yin Yong Zhang Qingguo Zhou kun kuang Department of Physics Lanzhou UniversityLanzhou 430000China Department of Computer Science Hefei University of TechnologyHefei 230009China Department of Computer Science Dongguan University of TechnologyDongguan 523808China Department of Physics Xiamen UniversityXiamen 361005China Department of Computer Science Lanzhou UniversityLanzhou 430000China College of Computer Science and Technology Zhejiang UniversityHangzhou 310058China

Machine knowledge refers to the knowledge contained in artificial intelligence.This article discusses how to acquire machine knowledge,with a particular focus on the acquisition of causal knowledge.The latter is the process of interpreting machine knowledge.Through the analysis of certain research methods in the fields of physics and artificial intelligence,we propose principles and models for interpreting machine knowledge,and discuss specific methods including the automation of the interpretation process and local linearization.

关键词： artificial knowledge interpreting

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

人工智能在化学逆合成中的应用

引用

Engineering 2023年第6期25卷 32-50,M0003页

作者： Yinjie Jiang Yemin Yu Ming Kong Yu Mei Luotian Yuan Zhengxing Huang kun kuang Zhihua Wang Huaxiu Yao James Zou Connor W.Coley Ying Wei College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China Department of Computer Science City University of Hong KongHong Kong 999077China Shanghai Institute for Advanced Study Zhejiang UniversityShanghai 201203China Shanghai Artificial Intelligence Laboratory Shanghai 201203China Department of Computer Science Stanford UniversityStanfordCA 94305–2004USA Department of Chemical Engineering&Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of TechnologyCambridgeMA 02139USA

近年来,人们对通过人工智能(AI)技术解决化学逆合成预测问题产生了巨大的兴趣。与化学家和基于规则的专家系统进行的逆合成预测不同,AI驱动的逆合成预测自动从现成的实验数据集中学习化学知识,以预测反应和逆合成路径。这提供了解决许... 详细信息

近年来,人们对通过人工智能(AI)技术解决化学逆合成预测问题产生了巨大的兴趣。与化学家和基于规则的专家系统进行的逆合成预测不同,AI驱动的逆合成预测自动从现成的实验数据集中学习化学知识,以预测反应和逆合成路径。这提供了解决许多传统挑战的机会,包括专业知识过于繁杂、路线的长度过大和计算成本高。本文描述了当前AI驱动的逆合成预测的概况。我们首先讨论了化学逆合成的数学定义,并回顾了这个问题中的研究挑战。然后,我们回顾相关的AI技术和最新进度,以实现逆合成预测。此外,我们提供了逆合成系统不同部分的全面分类,并调查了AI方法如何重塑每个子模块。最后,我们讨论了未来有希望的研究领域。

关键词：逆合成计算成本数学定义化学知识 AI技术基于规则的专家系统专业知识子模块

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Machine Knowledge and Human Cognition

引用

Big Data Mining and Analytics 2020年第4期3卷 292-299页

作者： Fashen Li Lian Li Jianping Yin Liang Huang Qingguo Zhou Ning An Yong Zhang Li Liu Jialin Zhang kun kuang Lei Yang Zhixi Wu Lianchun Yu the School of Physical Science and Technology Lanzhou UniversityLanzhou 730000China the School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230009China the School of Cyber Science and Engineering Dongguan University of TechnologyDongguan 523808China the Institute of Computational Physics and Complex Systems Lanzhou UniversityLanzhou 730000China the School of Information Science and Engineering Lanzhou UniversityLanzhou 730000China the School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230601China the Department of Physics Xiamen UniversityXiamen 361005China the School of Big Data&Software Engineering Chongqing UniversityChongqing 400044China the Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China the College of Computer Science and Technology Zhejiang UniversityHangzhou 310000China the Institute ofModern Physics Chinese Academy of SciencesLanzhou 730000China

Intelligent machines are knowledge systems with unique knowledge structure and function.In this paper,we discuss issues including the characteristics and forms of machine knowledge,the relationship between knowledge and human cognition,and the approach to acquire machine knowledge.These issues are of great significance to the development of artificial intelligence.

关键词： intelligent machine machine knowledge human cognition knowledge interpretation principle of functional similarity Probable Approximative Correction(PAC)model

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

基于多平台激光扫描技术的城市级数字线划图更新方法研究

引用

测绘 2024年第2期47卷 61-65页

作者：田径尚金光邝鹍成都市勘察测绘研究院四川成都610081 四川省城市信息化工程技术研究中心四川成都610081

城市数字线划图是国土空间基础数据资源体系的重要数据,为城市规划、建设提供强有力的技术支撑。本文从作业原理、技术特点、优缺点及应用场景等方面对倾斜摄影测量技术、机载激光雷达测量技术、车载激光雷达测量技术和背负式激光雷达... 详细信息

城市数字线划图是国土空间基础数据资源体系的重要数据,为城市规划、建设提供强有力的技术支撑。本文从作业原理、技术特点、优缺点及应用场景等方面对倾斜摄影测量技术、机载激光雷达测量技术、车载激光雷达测量技术和背负式激光雷达测量技术进行对比分析,提出一种基于多平台激光扫描系统的城市数字线划图的更新方法,并在成都市中心城区1∶500线划图生产与更新项目中进行了广泛应用,结果表明该方法可以实现新型基础测绘“全息采集、多级复用”的目的,在满足规范精度前提下大大提高了作业效率与更新质量,对同类型基础测绘项目具有一定参考价值。

关键词：数字线划图多平台激光扫描多源数据

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

端云协同智能计算的关键问题、方法和应用

引用

中国工程科学 2024年第1期26卷 127-138页

作者：张圣宇况琨吕承飞李纪为肖俊吴帆吴飞浙江大学软件学院杭州310013 浙江大学计算机科学与技术学院杭州310013 淘宝(中国)软件有限公司杭州310012 上海交通大学计算机科学与工程系上海200240 浙江大学上海高等研究院上海201203

端云协同智能计算是大数据、云计算、边缘计算发展的产物,可在保护用户隐私的前提下显著提升数据利用率,实现智能计算实时响应能力与服务鲁棒性的优势互补,而相应技术研发和实践应用具有复杂性。本文剖析了端云协同智能计算的应用价值,... 详细信息

端云协同智能计算是大数据、云计算、边缘计算发展的产物,可在保护用户隐私的前提下显著提升数据利用率,实现智能计算实时响应能力与服务鲁棒性的优势互补,而相应技术研发和实践应用具有复杂性。本文剖析了端云协同智能计算的应用价值,凝练了端学习效率优化、端少样本过拟合、端模型定制化、分布差异下虚假关联学习、通信开销与计算效率平衡等方面的技术难题;系统梳理了端云协同智能计算中主流方法研究进展,涉及作为应用基石的高效计算硬件、以端为中心的协同计算、以云为中心的协同计算、端云双向协同计算、可信端云协同智能计算等主要方向;总结了推荐系统、自动驾驶、安防系统、教育模式等端云协同智能计算的垂直领域应用情况。着眼端云协同智能计算的未来发展,需重点研究云资源在端模型个性化中的应用策略、端云协同多目标优化算法、端-端与云协同计算的优化策略。

关键词：端云协同大小模型协同计算端计算可信协同机器学习

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Analysis of Potential Disruptive Technologies in the Electronics and Information Field Towards the Intelligent Society

引用

Engineering 2021年第8期7卷 1051-1056页

作者： Yueguang Lyu Yaxin Zhang Yang Liu Weifang Chen Xilin Zhang Wenyuan Xu Changju Wu Lan Wang Hongxin Zeng Xuan Sheng Rui Yang Zenghui Wang kun kuang Wu Fei Chinese Academy of Engineering Beijing 100088China Yangtze Delta Region Institute(Huzhou) University of Electronic Science and Technology of ChinaHuzhou 313001China School of Electronic Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China Institute of Systems Engineering Beijing 100091China School of Aeronautics and Astronautics Zhejiang UniversityHangzhou 310027China School of Automation Engineering University of Electronic Science and Technology of ChinaChengdu 611731China College of Electrical Engineering Zhejiang UniversityHangzhou 310027China University of Michigan-Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong UniversityShanghai 200240China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of ChinaChengdu 611731China College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China

1.Introduction In the era of the new century,driven by the development of the intelligent society,the integration of the field of electronics and information with various technical fields and industries has accelerated and become the major driving force for a new round of technological revolution and industrial transformation.This has advanced the profound adjustment of global technology,industry,and division of labor as well as reshaping the innovation and competitiveness of countries around the world.Electronics information has received the most concentrated research and development investment worldwide and has been actively advancing and playing a leading role in dissemination.Naturally,it has become an important strategic area in which the world’s scientific and technological powers seek economic advances and competitive advantages.

关键词： competitive driving technological

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：