Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach

Kang, Jiawen; Xiong, Zehui; Niyato, Dusit; Yu, Han; Liang, Ying-Chang; Kim, Dong In

doi:10.1109/vts-apwcs.2019.8851649

Cited by 171 publications

(103 citation statements)

References 22 publications

(43 reference statements)

Supporting

Mentioning

101

Contrasting

Order By: Relevance

“…If both parties follow the optimal contracts, the overall system concludes to a stable and efficient mode of operation. Contract Theory has already been applied in several fields, such as vehicular networks [30], optimal charging schemes of electric vehicles in smart grid systems [31], federated learning in mobile networks [32], public safety systems [29], and cognitive radio networks [33].…”

Section: B Prosumers Contract-theoretic Utility Functionmentioning

confidence: 99%

Contract-Theoretic Demand Response Management in Smart Grid Systems

2020

View full text Add to dashboard Cite

The sheer growth of electricity demand and the rising number of electricity-hungry devices have highlighted and elevated the need of addressing the demand response management problem in residential smart grid systems. In this paper, a novel contract-theoretic demand response management (DRM) framework in residential smart grid systems is introduced based on the principles of labor economics. The residential households produce and consume electricity, acting as dynamic prosumers. Initially, the prosumers' personal electricity generation and consumption characteristics are captured by introducing the concept of prosumers' types. Then, the prosumers' and the electricity market's profit is depicted in representative utility functions. Based on the labor economics principles, Contract Theory is adopted to design the interactions among the electricity market, which offers personalized rewards to the prosumers in order to buy electricity at an announced price, and the prosumers, who offer their "effort" by paying for the purchased electricity. The contract-theoretic DRM problem is formulated as a maximization problem of the electricity market's utility, while jointly guaranteeing the optimal satisfaction of the prosumers, under the scenarios of complete and incomplete information from the electricity market's perspective regarding knowing or not the prosumers' types, respectively. The corresponding optimization problems are solved following a convex optimization approach and the optimal contracts, i.e., rewards and efforts, are determined. Detailed numerical results obtained via modeling and simulation, highlight the key operation features and superiority of the proposed framework.

show abstract

Section: B Prosumers Contract-theoretic Utility Functionmentioning

confidence: 99%

Contract-Theoretic Demand Response Management in Smart Grid Systems

2020

View full text Add to dashboard Cite

show abstract

“…Without a well-designed incentive, self-interested mobile devices will be unwilling to join federated learning tasks. In [10], Kang et al adopted the contract theory to design an effective incentive mechanism for simulating mobile devices with high-quality data participate in federated learning.…”

Section: Incentive Mechanism In Federated Learningmentioning

confidence: 99%

A Brief Survey of Data Pricing for Machine Learning

Tang¹,

Lv²,

Wu³

2020

8th International Conference on Signal, Image Processing and Pattern Recognition

View full text Add to dashboard Cite

Big data and machine learning are poised to revolutionize the field of artificial intelligence and represent a step towards building an intelligent society. Big data is considered to be the key to unlocking the next great waves of growth in productivity, the value of data is realized through machine learning. In this survey, we begin with an introduction to the general field of data pricing and distributed machine learning then progress to the main streams of data pricing and mechanism design methods. Our survey will cover several current areas of research within the field of data pricing, including the incentive mechanism design for federated learning, reinforcement learning, auction, crowdsourcing, and blockchain, especially, focus on reward function for machine learning and payment scheme. In parallel, we highlight the pricing scheme in data transactions, focusing on data evaluation via distributed machine learning. To conclude, we discuss some research challenges and future directions of data pricing for machine learning.

show abstract

“…The data collected by the local device can be analyzed locally or pre-processed on the local device. It is not necessary to upload all data collected by the local device to the cloud computing center so that traffic entering the core network can be reduced [14].…”

Section: Advantages Of Edge Computingmentioning

confidence: 99%

Edge Computing: Applications, State-of-the-Art and Challenges

Wang¹

2019

NET

View full text Add to dashboard Cite

The Internet of Things (IoT) is now infiltrating into our daily lives, providing important measurement and collection tools to inform us of every decision. Millions of sensors and devices continue to generate data and exchange important information through complex networks that support machine-to-machine communication and monitor and control critical smart world infrastructure. As a strategy to alleviate resource congestion escalation, edge computing has become a new paradigm for addressing the needs of the Internet of Things and localization computing. Compared to well-known cloud computing, edge computing migrates data calculations or storage to the edge of the network near the end-user. Thus, multiple compute nodes distributed across the network can offload computational pressure from a centralized data center and can significantly reduce latency in message exchanges. Besides, the distributed architecture balances network traffic and avoids spikes in traffic in the IoT network, reduces latency between edge/cloud servers and end-users, and reduces response time for real-time IoT applications compared to traditional cloud services. In this article, we conducted a comprehensive survey to analyze how edge computing can improve the performance of IoT networks. We classify edge calculations into different groups based on the architecture and study their performance by comparing network latency, bandwidth usage, power consumption, and overhead. Through the systematic introduction of the concept of edge computing, typical application scenarios, research status, and key technologies, it is considered that the development of edge computing is still in the initial stage. There are still many problems in practical applications that need to be solved, including optimizing edge computing performance, security, interoperability, and intelligent edge operations management services.

show abstract

Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach

Cited by 171 publications

References 22 publications

Contract-Theoretic Demand Response Management in Smart Grid Systems

Contract-Theoretic Demand Response Management in Smart Grid Systems

A Brief Survey of Data Pricing for Machine Learning

Edge Computing: Applications, State-of-the-Art and Challenges

Contact Info

Product

Resources

About