Federated Learning in Vehicular Edge Computing: A Selective Model Aggregation Approach

By Dongdong Ye, Rong Yu, Miao Pan, Zhu Han. IEEE Access, 2020

377 citations recorded by the source corpus.

Federated learning is a newly emerged distributed machine learning paradigm, where the clients are allowed to individually train local deep neural network (DNN) models with local data and then jointly aggregate a global DNN model at the central server. Vehicular edge computing (VEC) aims at exploiting the computation and communication resources at the edge of vehicular networks. Federated learning in VEC is promising to meet the ever-increasing demands of artificial intelligence (AI) applications in intelligent connected vehicles (ICV). Considering image classification as a typical AI application in VEC, the diversity of image quality and computation capability in vehicular clients potentially affects the accuracy and efficiency of federated learning. Accordingly, we propose a selective model aggregation approach, where “fine” local DNN models are selected and sent to the central server by evaluating the local image quality and computation capability. Regarding the implementation of model selection, the central server is not aware of the image quality and computation capability in the vehicular clients, whose privacy is protected under such a federated learning framework. To overcome this information asymmetry, we employ two-dimension contract theory as a distributed framework to facilitate the interactions between the central server and vehicular clients. The formulated problem is then transformed into a tractable problem through successively relaxing and simplifying the constraints, and eventually solved by a greedy algorithm. Using two datasets, i.e., MNIST and BelgiumTSC, our selective model aggregation approach is demonstrated to outperform the original federated averaging (FedAvg) approach in terms of accuracy and efficiency. Meanwhile, our approach also achieves higher utility at the central server compared with the baseline approaches.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/8d5ed7038d9b08ad49559d7ef0abe90949e51391

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues (2020, methodology): “[108] discuss the use of FL for image classification in vehicular IoT.”
Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking Systems (2021, background): “In [43], the authors investigate the effectiveness of federated learning for image classification in Vehicular Edge Computing (VEC).”
Federated Learning in Vehicular Networks (2020, methodology): “In [7], the authors propose a selective model aggregation approach, where the data center collects the gradient data from only “fine” edge”
Federated Learning for Smart Healthcare: A Survey (2021, methodology): “For example, we can use the model averaging approach in the Federated Averaging (FedAvg) algorithm proposed by Google [19], where the gradient parameters of local models are averaged element-wise with weights proportional to the sizes of the client datasets.”
A Survey on Federated Learning for Resource-Constrained IoT Devices (2021, positive): “Ye et al. [125] proposed a selective client model aggregation-based FL framework for vehicular edge computing.”
Federated Learning in Mobile Edge Networks: A Comprehensive Survey (2019, background): “As an extension, the authors in [142] introduced a multi-dimensional contract in which each FL”
Blockchain-Federated-Learning and Deep Learning Models for COVID-19 Detection Using CT Imaging (2020, methodology): “earn from the shared model while protecting the privacy of data. In this context, the federated learning is used to secure data and aggregates the parameters for the multiple organizations[24], [25], [26], [27], [28]. The hospitals can share the dataset during training and information about their da”