Differentially Private Asynchronous Federated Learning for Mobile Edge Computing in Urban Informatics

Lu, Yunlong; Huang, Xiaotao; Dai, Yueyue; Maharjan, Sabita; Zhang, Yan

doi:10.1109/tii.2019.2942179

Cited by 326 publications

(137 citation statements)

References 16 publications

Supporting

Mentioning

135

Contrasting

Unclassified

Order By: Relevance

“…In [28] [29], the authors proposed a privacy-preserved data sharing scheme in industrial IoT (IIoT). In [30], a secure and robust federated learning scheme with differential privacy has been proposed for urban informatics.…”

Section: B Edge Intelligence For Iotmentioning

confidence: 99%

Blockchain-Based Incentive Energy-Knowledge Trading in IoT: Joint Power Transfer and AI Design

Lin

Bashir

et al. 2022

IEEE Internet Things J.

View full text Add to dashboard Cite

Recently, edge artificial intelligence techniques (e.g., federated edge learning) are emerged to unleash the potential of big data from Internet of Things (IoT). By learning knowledge on local devices, data privacy-preserving and quality of service (QoS) are guaranteed. Nevertheless, the dilemma between the limited on-device battery capacities and the high energy demands in learning is not resolved. When the on-device battery is exhausted, the edge learning process will have to be interrupted. In this paper, we propose a novel Wirelessly Powered Edge intelliGence (WPEG) framework, which aims to achieve a stable, robust, and sustainable edge intelligence by energy harvesting (EH) methods. Firstly, we build a permissioned edge blockchain to secure the peer-to-peer (P2P) energy and knowledge sharing in our framework. To maximize edge intelligence efficiency, we then investigate the wirelessly-powered multi-agent edge learning model and design the optimal edge learning strategy. Moreover, by constructing a two-stage Stackelberg game, the underlying energy-knowledge trading incentive mechanisms are also proposed with the optimal economic incentives and power transmission strategies. Finally, simulation results show that our incentive strategies could optimize the utilities of both parties compared with classic schemes, and our optimal learning design could realize the optimal learning efficiency.

show abstract

Section: B Edge Intelligence For Iotmentioning

confidence: 99%

Blockchain-Based Incentive Energy-Knowledge Trading in IoT: Joint Power Transfer and AI Design

Lin

Bashir

et al. 2022

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…The FL framework presented better latency reduction performance than an OFDM framework. The effectiveness of FL schemes for mobile edge computing was also demonstrated in [88], [91]. In [88], FL edge caching was employed for urban infrastructures and urban informatics, with the consideration of urban vehicular networks.…”

Section: F Edge Cachingmentioning

confidence: 99%

“…The effectiveness of FL schemes for mobile edge computing was also demonstrated in [88], [91]. In [88], FL edge caching was employed for urban infrastructures and urban informatics, with the consideration of urban vehicular networks. It was demonstrated that FL edge caching can introduce considerable benefits to realize edge intelligence in urban informatics.…”

Section: F Edge Cachingmentioning

confidence: 99%

“…It was demonstrated that FL edge caching can introduce considerable benefits to realize edge intelligence in urban informatics. Furthermore, the FL framework in [88] was able to achieve high accuracy and communication efficiency while preserving the privacy of user data.…”

Section: F Edge Cachingmentioning

confidence: 99%

“…FL is an emerging technique that trains distributed ML models with the locally distributed datasets, without sending raw data to a centralized server [88], [142]. The technique was first presented by Google in 2016 [143].…”

Section: ) Fl-based Edge Cachingmentioning

confidence: 99%

See 2 more Smart Citations

A Classification of the Enabling Techniques for Low Latency and Reliable Communications in 5G and Beyond: AI-Enabled Edge Caching

Mutalemwa

Shin

2020

IEEE Access

View full text Add to dashboard Cite

Exploring human behavior patterns and socio‐demographic factors based on American Time Use Survey

Ling

Liu

Lyu

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary As human activities in mobile environments are facing an ever‐increasing range of data, it is of great research importance to explore in depth the salient features of data that discriminate human behavior patterns and socio‐demographic factors. However, human activity behavior that consists of a series of complex spatio‐temporal activity processes is difficult to model. In this article, we develop a framework to perform activity behavior pattern mining and recognition, and the proposed framework has been applied to the American Time Use Survey to explore representative activity behavior patterns and socio‐demographic factors. The main contributions are as follows: (1) A method of activity behavior similarity is presented based on daily activities and activity sequences. (2) An activity sequence similarity algorithm with O(p(m−p)) is proposed by line segment tree, greedy algorithm, and dynamic programming. (3) Representative activity behavior patterns and socio‐demographic factors are derived by clustering analysis and mining. (4) The activity behavior pattern is recognized by activity behavior features or socio‐demographic features. Through the experiments, we find that different daily activity behavior patterns are associated with specific socio‐demographic factors.

show abstract

Differentially Private Asynchronous Federated Learning for Mobile Edge Computing in Urban Informatics

Cited by 326 publications

References 16 publications

Blockchain-Based Incentive Energy-Knowledge Trading in IoT: Joint Power Transfer and AI Design

Blockchain-Based Incentive Energy-Knowledge Trading in IoT: Joint Power Transfer and AI Design

A Classification of the Enabling Techniques for Low Latency and Reliable Communications in 5G and Beyond: AI-Enabled Edge Caching

Exploring human behavior patterns and socio‐demographic factors based on American Time Use Survey

Contact Info

Product

Resources

About