检索结果-内蒙古大学图书馆

Advances and Open Challenges in Federated Foundation Models

IEEE Communications Surveys and Tutorials 2025年

作者： Ren, Chao Yu, Han Peng, Hongyi Tang, Xiaoli Zhao, Bo Yi, Liping Tan, Alysa Ziying Gao, Yulan Li, Anran Li, Xiaoxiao Li, Zengxiang Yang, Qiang School of Electrical Engineering and Computer Science Kth Royal Institute of Technology Sweden College of Computing and Data Science Nanyang Technological University Singapore College of Computer Nankai University China School of Medicine Yale University United States Digital Research Institute of Enn Group Langfang China Department of Electrical and Computer Engineering The University of British Columbia VancouverBC Canada Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong WeBank Shenzhen China

The integration of Foundation Models (FMs) with Federated Learning (FL) presents a transformative paradigm in Artificial Intelligence (AI). This integration offers enhanced capabilities, while addressing concerns of privacy, data decentralization and computational efficiency. This paper provides a comprehensive survey of the emerging field of Federated Foundation Models (FedFM), elucidating their synergistic relationship and exploring novel methodologies, challenges, and future directions that the FL research field needs to focus on in order to thrive in the age of FMs. A systematic multi-tiered taxonomy is proposed, categorizing existing FedFM approaches for model training, aggregation, trustworthiness, and incentivization. Key challenges, including how to enable FL to deal with high complexity of computational demands, privacy considerations, contribution evaluation, and communication efficiency, are thoroughly discussed. Moreover, this paper explores the intricate challenges of communication, scalability and security inherent in training/fine-tuning FMs via FL. It highlights the potential of quantum computing to revolutionize the processes of training, inference, optimization and security. This survey also introduces the implementation requirement of FedFM and some practical FedFM applications. It highlights lessons learned with a clear understanding of our findings for FedFM. Finally, this survey not only provides insights into the current state and challenges of FedFM, but also offers a blueprint for future research directions, emphasizing the need for developing trustworthy solutions. It serves as a foundational guide for researchers and practitioners interested in contributing to this interdisciplinary and rapidly advancing field. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Dynamic Asynchronous Federated Learning in Mobile Edge computing Networks

Energy-Efficient Dynamic Asynchronous Federated Learning in ...

引用

IEEE International Conference on Communications (ICC)

作者： Guozeng Xu Xiuhua Li Hui Li Qilin Fan Xiaofei Wang Victor C. M. Leung School of Big Data & Software Engineering Chongqing University Chongqing China TKLAN College of Intelligence & Computing Tianjin University Tianjin China College of Computer Science & Software Engineering Shenzhen University Shenzhen China Department of Electrical & Computer Engineering The University of British Columbia Vancouver Canada

To break data silos and address the challenge of green communication, federated learning (FL) is widely used at network edges to train deep learning models in mobile edge computing (MEC) networks. However, many existing FL algorithms do not fully consider the dynamic environment, resulting in slower convergence of the model and larger training energy consumption. In this paper, we design a dynamic asynchronous federated learning (DAFL) model to improve the efficiency of FL in MEC networks. Specifically, we dynamically choose a certain number of mobile devices (MDs) by their arrival order to participate in the global aggregation at each epoch. Meanwhile, we analyze the energy consumption model of local update and upload update, and formulate the problem as a dynamic sequential decision problem to minimize the energy consumption, which is NP-hard. To address it, we propose an energy-efficient algorithm based on deep reinforcement learning named DDAFL, to intelligently determine the number of MDs participating in global aggregation according to the state of MEC networks at each epoch. Compared with baseline schemes, the proposed algorithm can significantly reduce energy consumption and accelerate model convergence.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting Fall Events by a Spatio-Temporal Topological Network with Multiple Wearable Sensors

Predicting Fall Events by a Spatio-Temporal Topological Netw...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiaohu Li Jiawei Liu Guorui Liao Mingrui Yin Shu Wang Guoxin Su Jun Liao Li Liu School of Big Data & Software Engineering Chongqing University Chongqing China Chongqing Aerospace Rocket Electronic Technology Co. Ltd Chongqing China College of Computer Science & Technology Zhejiang University Zhejiang China School of Materials & Energy Southwest University Chongqing China School of Computing and Information Technology University of Wollongong NSW Australia

A key challenge in sensor-based fall prediction is the fact that a fall event can often occur in various configurations of fall poses together with their own spatio-temporal dependencies. This leads us to define a spatio-temporal model to explicitly characterize these internal configurations of poses. In particular, we introduce a graph neural network with spatio-temporal topological structure to encode such latent relations among poses by capturing representative patterns in fall events. Moreover, a human body orientation estimator is devised to capture human low limbs information, and as a result, separate pose dependencies are globally consistent. Empirical evaluations on two benchmark datasets and one in-house dataset suggest our approach significantly outperforms the state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Constraint Boundary Wandering Framework: Enhancing Constrained Optimization with Deep Neural Networks

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Wu, Shuang Chen, Shixiang Shen, Li Zhang, Lefei Tao, Dacheng Wuhan University National Engineering Research Center for Multimedia Software School of Computer Science Wuhan430072 China University of Science and Technology of China Key Laboratory of the Ministry of Education for Mathematical Foundations and Applications of Digital Technology School of Mathematical Sciences China Shenzhen Campus of Sun Yat-sen University School of Cyber Science and Technology Shenzhen518107 China Nanyang Technological University College of Computing and Data Science 639798 Singapore

Constrained optimization problems are pervasive in various fields, and while conventional techniques offer solutions, they often struggle with scalability. Leveraging the power of deep neural networks (DNNs) in optimization, we present a novel learning-based approach, the Constraint Boundary Wandering Framework (CBWF), to address these challenges. Our contributions include introducing a boundary wandering strategy inspired by the active-set method, enhancing equality constraint feasibility, and treating the Lipschitz constant as a learnable parameter. Additionally, we evaluate the regularization term, illustrating that the nonsmooth L2 norm yields superior results. Extensive testing on synthetic datasets and the ACOPT dataset demonstrates CBWF's superiority, outperforming existing deep learning-based solvers in terms of both objective and constraint loss. © 1979-2012 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

An Inconsistency-Based Hybrid Feature Selection Approach for Enhancing Medical Classification Modeling 2nd

An Inconsistency-Based Hybrid Feature Selection Approach for...

引用

2nd International Conference on Intelligent Manufacturing and Robotics, ICIMR 2024

作者： Zhao, Rong ALDharhani, Ghassan Saleh Ratnavelu, Kuru Thambiayya, Sathiyaraj Jasser, Muhammed Basheer Majeed, Anwar P. P. Abdul Luo, Yang Institute of Computer Science and Digital Innovation UCSI University Kuala Lumpur56000 Malaysia Institute of Information Science and Technology Dalian University of Science and Technology Dalian China Faculty of Information Science and Technology UKM University Selangor Bangi43000 Malaysia Institute of Mathematical Sciences University of Malaya Kuala Lumpur56000 Malaysia Institute of Actuarial Science and Data Analytics UCSI University Kuala Lumpur56000 Malaysia Department of Data Science and Artificial Intelligence School of Computing and Artificial Intelligence Faculty of Engineering and Technology Sunway University No. 5 Jalan Universiti Bandar Sunway Selangor Petaling Jaya47500 Malaysia Faculty of Engineering and Technology Sunway University No. 5 Jalan Universiti Bandar Sunway Selangor Petaling Jaya47500 Malaysia School of Intelligent Manufacturing Ecosystem Xi’an Jiaotong-Liverpool University Suzhou Taicang215400 China

ISBN: (纸本)9789819639489

Artificial Intelligence is an essential tool for early disease recognition and supporting patient condition monitoring in the future. Timely and exact conclusions about the type of disease are significant for treatment and life extension. A combination of classification and feature selection algorithms can effectively handle complex datasets in the medical field and improve the accuracy of disease diagnosis and treatment. In this paper, we propose a new hybrid feature selection algorithm that uses inconsistency metrics as a filter method for the first step, and then feeds the resulting dataset into a wrapper method, which ultimately results in a reduced dataset. The proposed HFSIM algorithm is tested on five datasets in the medical domain from Kaggle. The obtained feature subsets are verified on three classification algorithms, KNN, LR and RF of machine learning to validate the effectiveness of the proposed algorithm. The experimental results show that the proposed algorithm obtains feature subsets with low dimensionality on most of the datasets and also has high classification accuracy after testing on the classifiers. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Smart City Air Quality Management with IoT and Bayesian Optimization for Pollution Monitoring

Smart City Air Quality Management with IoT and Bayesian Opti...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Shanmuganathan V Mohsin Abbas Pradeep Kumar K P Srinivasan A. Vijay S. Sakthivel Padaiyatchi Department of Networking and Communications School of Computing SRM Institute of Science and Technology Kattankulathur India College of Engineering University of Technology Bahrain Salmabad Kingdom of Bahrain Department of Agricultural Engineering Nandha Engineering College Erode India Department of Electronics and Communication Engineering Sona College of Technology Salem India Department of Artificial Intelligence and Data Science St. Joseph's College of Engineering Chennai India Department of Electrical and Electronics Engineering Nehru Institute of Engineering and Technology Coimbatore India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

The rapid urbanization happening around the globe is having a huge effect on the environment. Cities in the poor world are particularly vulnerable to air pollution. In light of this issue, several nations are mandating that cities implement plans to enhance air quality, and the new global air quality recommendations from the World Health Organization (WHO) are adding fuel to the fire. Inadequate outreach, few observations, disconnected city operations, and inconsistent protocols are some of the issues that hinder these deployments, as does the absence of collaborative UAQM governance. The proposed approach consists of three phases, which are data preparation, feature selection, and training. When it comes to categorical preprocessing, there are two typical ways to deal with missing values are after removing rows with missing values, use KNN Imputer to fill in the blanks. One goal of feature selection methods is to make analysis easier and faster by reducing the target dataset's dimensionality. Training the model was done using BO. With an average accuracy rate of 93.14 percent, the proposed model beats out the alternatives, including SVM and RBF.

关键词： Training Support vector machines Smart cities Atmospheric modeling Nearest neighbor methods Feature extraction Air pollution Bayes methods Integrated circuit modeling Optimization

来源：评论

学校读者我要写书评

暂无评论

When Large Language Models Meet Citation: A Survey

arXiv

引用

arXiv 2023年

作者： Zhang, Yang Wang, Yufei Wang, Kai Sheng, Quan Z. Yao, Lina Mahmood, Adnan Zhang, Wei Emma Zhao, Rongying School of Computing Faculty of Science and Engineering Macquarie University Sydney Australia School of Information Management Wuhan University Wuhan China School of Computer Science and Engineering Nanyang Technological University Singapore CSIRO’s Data61 Sydney Australia Computer Science and Engineering University of New South Wales Sydney Australia School of Computer and Mathematical Sciences The University of Adelaide Adelaide Australia

Citations in scholarly work serve the essential purpose of acknowledging and crediting the original sources of knowledge that have been incorporated or referenced. Depending on their surrounding textual context, these citations are used for different motivations and purposes. Large Language Models (LLMs) could be helpful in capturing these fine-grained citation information via the corresponding textual context, thereby enabling a better understanding towards the literature. Furthermore, these citations also establish connections among scientific papers, providing high-quality inter-document relationships and human-constructed knowledge. Such information could be incorporated into LLMs pre-training and improve the text representation in LLMs. Therefore, in this paper, we offer a preliminary review of the mutually beneficial relationship between LLMs and citation analysis. Specifically, we review the application of LLMs for in-text citation analysis tasks, including citation classification, citation-based summarization, and citation recommendation. We then summarize the research pertinent to leveraging citation linkage knowledge to improve text representations of LLMs via citation prediction, network structure information, and inter-document relationship. We finally provide an overview of these contemporary methods and put forth potential promising avenues in combining LLMs and citation analysis for further investigation. Copyright © 2023, The Authors. All rights reserved.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

Extended Abstract of Graph4Web: A Relation-Aware Graph Attention Network for Web Service Classification

Extended Abstract of Graph4Web: A Relation-Aware Graph Atten...

引用

IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

作者： Kunsong Zhao Jin Liu Zhou Xu Xiao Liu Lei Xue Zhiwen Xie Yuxuan Zhou Xin Wang School of Computer Science Wuhan University Wuhan China Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) China School of Big Data and Software Engineering Chongqing University Chongqing China School of Information Technology Deakin University Geelong Australia Department of Computing The Hong Kong Polytechnic University Hong Kong China College of Engineering and Computer Science Syracuse University Syracuse USA

Software reuse, as a means to develop new software products with similar functions by virtue of existing software components, has become a popular way during the software development process. In particular, as the service-oriented architecture became popular, web services turned into an indispensable part in modem software development Web services provide a basic composition with high cohesion and loose coupling to support responses among heterogeneous software components, which is the valuable resources for software reuse. The popular web service repositories, such as Programmable Web, contain a mass of web services for beginners and developers to choose from. Nevertheless, the large number of web services also makes it difficult to select the suitable services. Thus, the key to reuse software components lies in how to find appropriate web services from repositories to meet developers requirements in specific application scenarios.

关键词： Couplings Web services Modems Service-oriented architecture Software reusability

来源：评论

学校读者我要写书评

暂无评论

Robin: A Novel Method to Produce Robust Interpreters for Deep Learning-Based Code Classifiers

Robin: A Novel Method to Produce Robust Interpreters for Dee...

引用

IEEE International Conference on Automated Software engineering (ASE)

作者： Zhen Li Ruqian Zhang Deqing Zou Ning Wang Yating Li Shouhuai Xu Chen Chen Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Cluster and Grid Computing Lab National Engineering Research Center for Big Data Technology and System Hubei Engineering Research Center on Big Data Security Department of Computer Science University of Colorado Colorado Springs USA Center for Research in Computer Vision University of Central Florida USA School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Deep learning has been widely used in source code classification tasks, such as code classification according to their functionalities, code authorship attribution, and vulnerability detection. Unfortunately, the black-box nature of deep learning makes it hard to interpret and understand why a classifier (i.e., classification model) makes a particular prediction on a given example. This lack of interpretability (or explainability) might have hindered their adoption by practitioners because it is not clear when they should or should not trust a classifier's prediction. The lack of interpretability has motivated a number of studies in recent years. However, existing methods are neither robust nor able to cope with out-of-distribution examples. In this paper, we propose a novel method to produce Robust interpreters for a given deep learning-based code classifier; the method is dubbed Robin. The key idea behind Robin is a novel hybrid structure combining an interpreter and two approximators, while leveraging the ideas of adversarial training and data augmentation. Experimental results show that on average the interpreter produced by Robin achieves a 6.11% higher fidelity (evaluated on the classifier), 67.22% higher fidelity (evaluated on the approximator), and 15.87x higher robustness than that of the three existing interpreters we evaluated. Moreover, the interpreter is 47.31% less affected by out-of-distribution examples than that of LEMNA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lightweight Task-Oriented Semantic Communication Empowered by Large-Scale AI Models

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Liu, Chuanhong Guo, Caili Yang, Yang Chen, Mingzhe Quek, Tony Q. S. Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing100876 China Beijing University of Posts and Telecommunications Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing100876 China University of Miami Department of Electrical and Computer Engineering Institute for Data Science and Computing Coral GablesFL United States Singapore University of Technology and Design Dept. of Information Systems Technology and Design 487372 Singapore

Recent studies have focused on leveraging large-scale artificial intelligence (LAI) models to improve semantic representation and compression capabilities. However, the substantial computational demands of LAI models pose significant challenges for real-time communication scenarios. To address this, this paper proposes utilizing knowledge distillation (KD) techniques to extract and condense knowledge from LAI models, effectively reducing model complexity and computation latency. Nevertheless, the inherent complexity of LAI models leads to prolonged inference times during distillation, while their lack of channel awareness compromises the distillation performance. These limitations make standard KD methods unsuitable for task-oriented semantic communication scenarios. To address these issues, we propose a fast distillation method featuring a pre-stored compression mechanism that eliminates the need for repetitive inference, significantly improving efficiency. Furthermore, a channel adaptive module is incorporated to dynamically adjust the transmitted semantic information based on varying channel conditions, enhancing communication reliability and adaptability. In addition, an information bottleneck-based loss function is derived to guide the fast distillation process. Simulation results verify that the proposed scheme outperform baselines in term of task accuracy, model size, computation latency, and training data requirements. © 1967-2012 IEEE.

关键词： NP-hard

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：