Federated Learning in Mobile Edge Networks: A Comprehensive Survey

Lim, Wei Yang Bryan; Luong, Nguyen Cong; Hoang, Dinh Thai; Jiao, Yutao; Liang, Ying‐Chang; Yang, Qiang; Niyato, Dusit; Miao, Yuan

doi:10.48550/arxiv.1909.11875

Cited by 31 publications

(27 citation statements)

References 132 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This sub-section discusses problem formulation whose purpose is to jointly minimize computation time and PER. From (13), it is clear that the PER has a proportional effect on DFL model error. Therefore, we get the intuition of 𝐶 𝑝 to reflect PER on a global DFL model in our system model.…”

Section: Problem Formulationmentioning

confidence: 99%

See 1 more Smart Citation

A Dispersed Federated Learning Framework for 6G-Enabled Autonomous Driving Cars

Khan¹,

Tun²,

Alsenwi³

et al. 2021

Preprint

View full text Add to dashboard Cite

Sixth-Generation (6G)-based Internet of Everything applications (e.g. autonomous driving cars) have witnessed a remarkable interest. Autonomous driving cars using federated learning (FL) has the ability to enable different smart services. Although FL implements distributed machine learning model training without the requirement to move the data of devices to a centralized server, it its own implementation challenges such as robustness, centralized server security, communication resources constraints, and privacy leakage due to the capability of a malicious aggregation server to infer sensitive information of end-devices. To address the aforementioned limitations, a dispersed federated learning (DFL) framework for autonomous driving cars is proposed to offer robust, communication resourceefficient, and privacy-aware learning. A mixed-integer non-linear (MINLP) optimization problem is formulated to jointly minimize the loss in federated learning model accuracy due to packet errors and transmission latency. Due to the NP-hard and nonconvex nature of the formulated MINLP problem, we propose the Block Successive Upper-bound Minimization (BSUM) based solution. Furthermore, the performance comparison of the proposed scheme with three baseline schemes has been carried out. Extensive numerical results are provided to show the validity of the proposed BSUM-based scheme.

show abstract

Section: Problem Formulationmentioning

confidence: 99%

“…• Privacy leakage: A malicious end-device/aggregation server can infer sensitive information of devices using the learning model updates [12], [13]. Therefore, we must ensure complete privacy preservation in FL.…”

mentioning

confidence: 99%

A Dispersed Federated Learning Framework for 6G-Enabled Autonomous Driving Cars

Khan¹,

Tun²,

Alsenwi³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The focus of these works above is DNN inference at the edge. For the edge learning that considers the DNN training, many existing works target at the fast and cost-efficient federated learning scheme in order to train a commonly-shared model across multiple devices [32]. Along a different line, we consider the fast model learning with respect to a specific end device and leverage a multitude of device-edge-cloud resources to training acceleration.…”

Section: B Edge-basedmentioning

confidence: 99%

HierTrain: Fast Hierarchical Edge AI Learning with Hybrid Parallelism in Mobile-Edge-Cloud Computing

Liu¹,

Chen²,

Zhou³

et al. 2020

Preprint

View full text Add to dashboard Cite

Nowadays, deep neural networks (DNNs) are the core enablers for many emerging edge AI applications. Conventional approaches to training DNNs are generally implemented at central servers or cloud centers for centralized learning, which is typically timeconsuming and resource-demanding due to the transmission of a large amount of data samples from the device to the remote cloud. To overcome these disadvantages, we consider accelerating the learning process of DNNs on the Mobile-Edge-Cloud Computing (MECC) paradigm. In this paper, we propose HierTrain, a hierarchical edge AI learning framework, which efficiently deploys the DNN training task over the hierarchical MECC architecture. We develop a novel hybrid parallelism method, which is the key to HierTrain, to adaptively assign the DNN model layers and the data samples across the three levels of edge device, edge server and cloud center. We then formulate the problem of scheduling the DNN training tasks at both layer-granularity and sample-granularity. Solving this optimization problem enables us to achieve the minimum training time. We further implement a hardware prototype consisting of an edge device, an edge server and a cloud server, and conduct extensive experiments on it. Experimental results demonstrate that HierTrain can achieve up to 6.9× speedup compared to the cloud-based hierarchical training approach.

show abstract

“…The server builds the global model by averaging all gradients across the network [8]. Then, the coordinating server broadcasts the new updated model to all clients [9]. Each client uploads its local model to the server and then downloads the global model to do on-device inference using a cloud-distributed model.…”

Section: Introductionmentioning

confidence: 99%

Exploiting Unlabeled Data in Smart Cities using Federated Edge Learning

Albaseer

Çiftler

Abdallah

et al. 2020

2020 International Wireless Communications and Mobile Computing (IWCMC)

View full text Add to dashboard Cite

Privacy concerns are considered one of the main challenges in smart cities as sharing sensitive data induces threatening problems in people's lives. Federated learning has emerged as an effective technique to avoid privacy infringement as well as increase the utilization of the data. However, there is a scarcity in the amount of labeled data and an abundance of unlabeled data collected in smart cities; hence there is a necessity to utilize semi-supervised learning. In this paper, we present the primary design aspects for enabling federated learning at the edge networks taking into account the problem of unlabeled data. We propose a semi-supervised federated edge learning method called FedSem that exploits unlabeled data in real-time. FedSem algorithm is divided into two phases. The first phase trains a global model using only the labeled data. In the second phase, Fedsem injects unlabeled data into the learning process using the pseudo labeling technique and the model developed in the first phase to improve the learning performance. We carried out several experiments using the traffic signs dataset as a case study. Our results show that FedSem can achieve accuracy by up to 8% by utilizing the unlabeled data in the learning process.

show abstract

Federated Learning in Mobile Edge Networks: A Comprehensive Survey

Cited by 31 publications

References 132 publications

A Dispersed Federated Learning Framework for 6G-Enabled Autonomous Driving Cars

A Dispersed Federated Learning Framework for 6G-Enabled Autonomous Driving Cars

HierTrain: Fast Hierarchical Edge AI Learning with Hybrid Parallelism in Mobile-Edge-Cloud Computing

Exploiting Unlabeled Data in Smart Cities using Federated Edge Learning

Contact Info

Product

Resources

About