检索结果-内蒙古大学图书馆

Wireless Federated Learning With Hybrid Local and Centralized Training: A Latency Minimization design

IEEE Journal on Selected Topics in Signal Processing 2023年第1期17卷 248-263页

作者： Huang, Ning Dai, Minghui Wu, Yuan Quek, Tony Q. S. Shen, Xuemin State Key Lab of Internet of Things for Smart City China University of Macau Department of Computer and Information Science China University of Macau State Key Laboratory of Internet of Things for Smart City The Department of Computer and Information Science China Zhuhai Um Science and Technology Research Institute Zhuhai519031 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore National Cheng Kung University Taiwan University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

Wireless federated learning (FL) is a collaborative machine learning (ML) framework in which wireless client-devices independently train their ML models and send the locally trained models to the FL server for aggregation. In this paper, we consider the coexistence of privacy-sensitive client-devices and privacy-insensitive yet computing-resource constrained client-devices, and propose an FL framework with a hybrid centralized training and local training. Specifically, the privacy-sensitive client-devices perform local ML model training and send their local models to the FL server. Each privacy-insensitive client-device can have two options, i.e., (i) conducting a local training and then sending its local model to the FL server, and (ii) directly sending its local data to the FL server for the centralized training. The FL server, after collecting the data from the privacy-insensitive client-devices (which choose to upload the local data), conducts a centralized training with the received datasets. The global model is then generated by aggregating (i) the local models uploaded by the client-devices and (ii) the model trained by the FL server centrally. Focusing on this hybrid FL framework, we firstly analyze its convergence feature with respect to the client-devices' selections of local training or centralized training. We then formulate a joint optimization of client-devices' selections of the local training or centralized training, the FL training configuration (i.e., the number of the local iterations and the number of the global iterations), and the bandwidth allocations to the client-devices, with the objective of minimizing the overall latency for reaching the FL convergence. Despite the non-convexity of the joint optimization problem, we identify its layered structure and propose an efficient algorithm to solve it. Numerical results demonstrate the advantage of our proposed FL framework with the hybrid local and centralized training as well as our proposed alg

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Bring game characters to the social space: Developing storytelling community AI agents driven by LLMs

引用

Entertainment Computing 2025年

作者： Yuqian Sun Hanyi Wang Pok Man Chan Morteza Tabibi Yan Zhang Huan Lu Yuheng Chen Chang Hee Lee Ali Asadipour Computer Science Research Centre Royal College of Art Rausing Research & Innovation Building 15 Parkgate Road London SW11 4NL United Kingdom Independent United States Independent Hong Kong China Independent China rct.ai US Affective Systems and Cognition Lab Industrial Design Department College of Engineering KAIST Daejeon South Korea

AI agents driven by Large Language Models (LLMs) are now ubiquitous in our daily life, so can they bring characters from games into reality? We address the integration of storytelling and AI agents driven by LLMs to develop engaging and believable fictional characters in community settings. Motivated by the potential of fictional characters to enhance social interactions, we introduce Storytelling Community AI Agents (SCAs) and the concept of story engineering to transform fictional game characters into ”live” social entities within player communities. Our story engineering process includes three steps: (1) Character and story creation, defining the SC’s personality and worldview, (2) Presenting Live Stories to the Community, allowing the agent to recount challenges and seek suggestions, and (3) Communication with community members, enabling interaction between the agent and users. We employed the LLM GPT-3 to drive our SCAs, “David” and “Catherine,” and evaluated their performance in an online gaming community, “DE (Alias),” on Discord. Our mixed-method analysis, based on questionnaires (N=15) and interviews (N=8) with community members, reveals that storytelling significantly enhances the engagement and believability of AI agents in community settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Socially engaged arts practice in HCI

Socially engaged arts practice in HCI

引用

32nd Annual ACM Conference on Human Factors in Computing Systems, CHI EA 2014

作者： Clarke, Rachel Heitlinger, Sara Briggs, Jo Crivellaro, Clara Light, Ann Culture Lab. School of Computing Science Newcastle University United Kingdom Media and Art Technology Electronic Engineering and Computer Science Queen Mary University of London United Kingdom Media and Communication Design Northumbria University United Kingdom

ISBN: (纸本)9781450324748

Socially engaged methods are increasingly being used within HCI research, yet arts practice in this context has been little explored. HCI research that aligns with socially engaged arts practices encourages debate around societal challenges;for example discussion of issues surrounding the role of digital technology in sustainability, inclusion, community, identity and the politics of participation. Building on existing research, this workshop will bring together a diverse group of HCI researchers, artists and other creators whose work or interests align with socially engaged arts practice, to foster critical exploration and creative collaboration.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Gameplay design patterns for believable non-player characters

Gameplay design patterns for believable non-player character...

引用

3rd Digital Games Research Association International Conference: "Situated Play", DiGRA 2007

作者： Lankoski, Petri Björk, Staffan Media Lab. University of Art and Design Helsinki Hämeentie 135 C FI-00560 Helsinki Finland Interaction Design Collegium Computer Science and Engineering Chalmers University of Technology and Göteborg University SE-412 96 Göteborg Sweden

Descriptions of humans require several qualities for people to experience them as believable: human body;selfawareness, intentional states, and self impelled actions;expression of emotions;ability to use natural language;and persistent traits. Based on these we analyze non-player character Claudette Perrick in The Elders Scroll IV: Oblivion to detect how these qualities can be created in the interactive environment of a game. We derive the gameplay design patterns Awareness of Surrounding, Visual Body Damage, Dissectible Bodies, Initiative, Own Agenda, Sense of Self, Emotional Attachment, Contextual Conversational Responses, and Goal-Driven Personal Development, which point to design choices that can be made when designing believable non-player characters in games. © 2007 Authors & Digital Games Research Association (DiGRA).

关键词： Game design

来源：评论

学校读者我要写书评

暂无评论

Collaborative Learning of Gesture Recognition and 3D Hand Pose Estimation with Multi-order Feature Analysis 16th

Collaborative Learning of Gesture Recognition and 3D Hand Po...

引用

16th European Conference on computer Vision, ECCV 2020

作者： Yang, Siyuan Liu, Jun Lu, Shijian Er, Meng Hwa Kot, Alex C. Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore Singapore School of Computer Science and Engineering Nanyang Technological University Singapore Singapore

ISBN: (纸本)9783030585792

Gesture recognition and 3D hand pose estimation are two highly correlated tasks, yet they are often handled separately. In this paper, we present a novel collaborative learning network for joint gesture recognition and 3D hand pose estimation. The proposed network exploits joint-aware features that are crucial for both tasks, with which gesture recognition and 3D hand pose estimation boost each other to learn highly discriminative features. In addition, a novel multi-order multi-stream feature analysis method is introduced which learns posture and multi-order motion information from the intermediate feature maps of videos effectively and efficiently. Due to the exploitation of joint-aware features in common, the proposed technique is capable of learning gesture recognition and 3D hand pose estimation even when only gesture or pose labels are available, and this enables weakly supervised network learning with much reduced data labeling efforts. Extensive experiments show that our proposed method achieves superior gesture recognition and 3D hand pose estimation performance as compared with the state-of-the-art. © 2020, Springer Nature Switzerland AG.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Memetic three-dimensional gabor feature extraction for hyperspectral imagery classification

Memetic three-dimensional gabor feature extraction for hyper...

引用

3rd International Conference on Swarm Intelligence, ICSI 2012

作者： Zhu, Zexuan Shen, Linlin Sun, Yiwen He, Shan Ji, Zhen City Key Laboratory of Embedded System Design College of Computer Science and Software Engineering Shenzhen University Shenzhen 518060 China Shenzhen Key Lab. of Biomedical Engineering School of Medicine Shenzhen University 518060 China School of Computer Science University of Birmingham Edgbaston Birmingham B15 2TT United Kingdom

ISBN: (纸本)9783642309755

This paper proposes a three-dimensional Gabor feature extraction for pixel-based hyperspectral imagery classification using a memetic algorithm. The proposed algorithm named MGFE combines 3-D Gabor wavelet feature generation and feature selection together to capture the signal variances of hyperspectral imagery, thereby extracting the discriminative 3-D Gabor features for accurate classification. MGFE is characterized with a novel fitness evaluation function based on independent feature relevance and a pruning local search for eliminating redundant features. The experimental results on two real-world hyperspectral imagery datasets show that MGFE succeeds in obtaining significantly improved classification accuracy with parsimonious feature selection. © 2012 Springer-Verlag.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

LibAMM: Empirical Insights into Approximate Computing for Accelerating Matrix Multiplication 38

LibAMM: Empirical Insights into Approximate Computing for Ac...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zeng, Xianzhi Jiang, Wenchao Zhang, Shuhao National Engineering Research Center for Big DataTechnology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Nanyang Technological University Singapore Singapore University of Technology and Design Singapore

Matrix multiplication (MM) is pivotal in fields from deep learning to scientific computing, driving the quest for improved computational efficiency. Accelerating MM encompasses strategies like complexity reduction, parallel and distributed computing, hardware acceleration, and approximate computing techniques, namely AMM algorithms. Amidst growing concerns over the resource demands of large language models (LLMs), AMM has garnered renewed focus. However, understanding the nuances that govern AMM's effectiveness remains incomplete. This study delves into AMM by examining algorithmic strategies, operational specifics, dataset characteristics, and their application in real-world tasks. Through comprehensive testing across diverse datasets and scenarios, we analyze how these factors affect AMM's performance, uncovering that the selection of AMM approaches significantly influences the balance between efficiency and accuracy, with factors like memory access playing a pivotal role. Additionally, dataset attributes are shown to be vital for the success of AMM in applications. Our results advocate for tailored algorithmic approaches and careful strategy selection to enhance AMM's effectiveness. To aid in the practical application and ongoing research of AMM, we introduce LibAMM -a toolkit offering a wide range of AMM algorithms, benchmarks, and tools for experiment management. LibAMM aims to facilitate research and application in AMM, guiding future developments towards more adaptive and context-aware computational solutions. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A trust evaluation fluctuation model in the e-commerce 27

A trust evaluation fluctuation model in the e-commerce

引用

27th Chinese Control and Decision Conference, CCDC 2015

作者： Jing, Zhang Yu, Shengjun Fan, Hongbo Hui, Rong Computer Technology Application Key Lab of Yunnan Province Kunming University of Science and Technology Kunming China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Faculty of Art and Design Kunming Metallurgy College Kunming Yunnan China

ISBN: (纸本)9781479970179

E-commerce is becoming the main shopping way. The trust decision-making is the most important factor which decides whether the transaction is successful or not. How to offer people an accurate and objective trust is a basic issue that scholars must face and solve. Volatility can measure the stability of a set of data and help us avoid risk to some extent. In order to prevent fraud and deception, this paper proposes a trust evaluation fluctuation model based on historical rating data. A new reward and punishment mechanism is added into the model. The results of simulation experiments prove the practicality and validity of the model. © 2015 IEEE.

关键词： decision-making fraud and deception trust volatility

来源：评论

学校读者我要写书评

暂无评论

DCET-Net: Dual-Stream Convolution Expanded Transformer for Breast Cancer Histopathological Image Classification

DCET-Net: Dual-Stream Convolution Expanded Transformer for B...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Zou, Ying Chen, Shannan Sun, Qiule Liu, Bin Zhang, Jianxin Dalian University Key Lab of Advanced Design and Intelligent Computing Ministry of Education Dalian China Dalian University of Technology School of Information and Communication Engineering Dalian China Dalian China Dalian Minzu University School of Computer Science and Engineering Dalian China

ISBN: (纸本)9781665401265

Researches on breast cancer histopathological image classification have achieved a great breakthrough using deep backbones of Convolutional Neural Networks (CNNs) in recent years. However, due to the inductive bias of locality, CNNs are unable to effectively extract the global feature information of breast cancer histopathological images, limiting the improvement of the classification results. To overcome this shortcoming, this paper reasonably introduces an extra backbone stream of a pure transformer, which consists of a self-attention mechanism to capture global receptive fields of histopathological images, thereby compensating the locality characteristic of CNNs backbone. Based on two backbone streams of CNN and transformer, a dual-stream network called DCET-Net is proposed, which considers local features and global ones simultaneously, and progressively combines them from these two streams to form the final representations for classification. DCET-Net is extensively evaluated on the representative BreakHis histopathological image dataset, and experimental results demonstrate that it is highly competitive with the state-of-the-art CNN methods in breast cancer histopathological image classification task. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Agent-based and discrete-event modeling: A quantitative comparison

Agent-based and discrete-event modeling: A quantitative comp...

引用

7th AIAA Aviation Technology, Integration, and Operations Conference

作者： Yu, Tai-Tuck Scanlan, J.P. Wills, G.B. University of Southampton Southampton Hampshire SO17 1BJ United Kingdom Computational Engineering and Design Group School of Engineering Sciences University of Southampton University Road Department of Design School of Engineering Sciences University of Southampton University Road Learning Societies Lab. School of Electronics and Computer Science University of Southampton University Road

ISBN: (纸本)1563479087

Although agent-based modeling is widely regarded as a concept well-suited to the simulation of logistics systems, there has not been any quantitative comparison with discreteevent modeling or other more established concepts. As a timely check on the rising popularity of this paradigm for modeling complex systems, this paper describes a study comparing an agent-based model with a traditional discrete-event model, each of which has been implemented to a common specification. The model scenario is based on an existing application - the global repair operation of a fleet of civil aircraft high-bypass turbofan engines. Initial results, including metrics for runtime, and software size, structure, and complexity highlight the basic similarities and differences between the models. Future estimation of model maintainability will further quantify their benefits and drawbacks. It is hoped that characterizing the paradigms more fully will enable a modeler to match various parts of a model more appropriately to its problem domain.

关键词： Intelligent agents

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：