Related references
Note: Only part of the references are listed.
Article
Computer Science, Theory & Methods
Zhishu Shen et al.
ACM COMPUTING SURVEYS
(2023)
Review
Engineering, Electrical & Electronic
Zijian Liu et al.
Summary: As an important edge device of the power grid, smart meters can detect illegal behaviors such as electricity theft by analyzing large-scale consumption data. However, existing methods are limited in extracting different consumption characteristics and learning pattern differences between independent users, hindering the improvement of theft detection performance. Therefore, a novel method utilizing supervised contrastive learning is proposed for electricity theft detection.
EURASIP JOURNAL ON WIRELESS COMMUNICATIONS AND NETWORKING
(2023)
Article
Engineering, Electrical & Electronic
Wen Wu et al.
Summary: This paper proposes a novel Split learning (SL) scheme called Cluster-based Parallel SL (CPSL) to reduce training latency by parallelizing device-side model training and sequentially training the whole AI model. A resource management algorithm is also proposed to consider device heterogeneity and network dynamics. Extensive simulation results demonstrate that the proposed solution greatly reduces training latency and adapts to network dynamics compared with existing SL benchmarks.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Peiying Zhang et al.
Summary: This study proposes a service provision method based on service function chaining (SFC) to address the resource allocation challenge in the space-air-ground-integrated network (SAGIN). By using network function virtualization (NFV) and a federated learning (FL)-based algorithm, efficient resource allocation and reduced service blocking rate can be achieved.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Yi Liu et al.
Summary: This article proposes an energy-efficient space-air-ground integrated edge computing network architecture, in which IoT devices choose suitable LEO satellites or UAVs for task offloading based on their energy level, communication conditions, and computing capabilities. A constrained Markov decision process and deep reinforcement learning (DRL)-based algorithm are employed to solve the task offloading decision problem, and an adaptive federated DRL-based offloading method is proposed to consider privacy protection and communication failure.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Qingze Fang et al.
Summary: The space-air-ground integrated network (SAGIN) is crucial for next-generation mobile communication systems, enabling global data transmission and supporting data-driven artificial intelligence services. However, central training of AI models using SAGIN faces challenges of network constraints, inefficient data transmission, and privacy issues. To address these challenges, we propose the Olive Branch Learning (OBL) framework, which leverages private data from ground-layer IoT devices for local model training and utilizes air nodes and satellite constellations for model aggregation. We also design an efficient Communication and Non-IID-aware Air node-Satellite Assignment (CNASA) algorithm to enhance communication efficiency and inference performance. Extensive experiments validate the superior performance of our algorithm over benchmark policies.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Mohammad Al-Quraan et al.
Summary: Technological advancements in wireless networks have led to an increase in the number of connected devices. The surge in data volume powered by AI in wireless systems has created new opportunities for data-driven intelligent services. This article introduces federated learning (FL), a technique that brings machine learning to the edge of wireless networks, and explores its applications, challenges, and limitations. The effectiveness of FL is also examined in the context of future communication systems. The survey aims to provide a comprehensive overview of FL applications and serve as a foundation for understanding the topic.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
Mahdi Beitollahi et al.
Summary: This article introduces a new machine learning framework called federated learning (FL), which enables collaborative training of ML models by sending only model parameters instead of raw data. However, FL faces challenges in terms of communication overhead and energy consumption due to limited wireless network resources. In addition, there are privacy issues in practical implementations of FL over wireless networks. This survey discusses these challenges, proposed solutions, and the impact of wireless networks on FL performance.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Review
Computer Science, Information Systems
Rezak Aziz et al.
Summary: This paper discusses the privacy issues in federated learning and provides an overview of homomorphic encryption (HE) and differential privacy (DP) techniques for secure federated learning. The strengths and weaknesses of these techniques in different settings are discussed, with a particular focus on the trade-off between privacy and convergence, as well as the computation overheads involved.
Article
Computer Science, Hardware & Architecture
Fengxiao Tang et al.
Summary: This article introduces the advantages and potential usage directions of using federated learning in SAGIN, and provides a case study of a federated reinforcement learning-based traffic offloading approach in SAGIN.
Review
Computer Science, Information Systems
Weiwei Jiang
Summary: This paper surveys the application of graph-based deep learning methods in communication networks. By utilizing different models and solutions, state-of-the-art performance can be achieved in various communication network problems. This survey is the first comprehensive analysis covering both wired and wireless scenarios, and it also presents future research directions.
COMPUTER COMMUNICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Weiwei Jiang et al.
Summary: This study uses machine learning and deep learning models to predict drought levels and finds that no single model can achieve the best performance for all evaluation metrics, indicating the challenging nature of drought prediction.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2022)
Article
Engineering, Electrical & Electronic
Fengxiao Tang et al.
Summary: In this paper, the development of communication technology and network architecture in the future era of intelligent networks is studied. The Space-Air-Ground Integrated Networks (SAGIN) is proposed as a potential architecture to provide ubiquitous communication and drive the era of the intelligent global network. The use of blockchain and federated reinforcement learning is introduced to address the security and network performance problems in SAGIN.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Preksha Jain et al.
Summary: This article reviews the 6G wireless communication network, explores current trends and issues in existing mobile communication technologies and the 5G communication network, introduces the goals and design principles of 6G, and proposes an architectural design. It also discusses research challenges, directions, recent advancements, and possible use-cases in terms of real-time interactions of the biological, physical, and digital world.
PHYSICAL COMMUNICATION
(2022)
Review
Computer Science, Information Systems
Guanming Bao et al.
Summary: This article provides a detailed description of the critical technologies, challenges, and applications of deploying federated learning in cloud-edge collaborative architecture, and offers guidance on future research directions.
JOURNAL OF CLOUD COMPUTING-ADVANCES SYSTEMS AND APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Omar Abdel Wahab et al.
Summary: The survey aims to address the shortcomings in existing federated learning literature by providing a detailed multi-level classification scheme to assist in designing future solutions based on challenges and techniques.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2021)
Article
Computer Science, Hardware & Architecture
Nei Kato et al.
IEEE WIRELESS COMMUNICATIONS
(2020)
Article
Computer Science, Artificial Intelligence
Qiang Yang et al.
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2019)
Article
Computer Science, Information Systems
Chaoyun Zhang et al.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2019)
Article
Automation & Control Systems
Zibin Zheng et al.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2018)
