Incentive Mechanism for Reliable Federated Learning: A Joint Optimization Approach to Combining Reputation and Contract Theory
By Jiawen Kang, Zehui Xiong, Dusist Niyato, Shengli Xie, Junshan Zhang. 2019
793 citations recorded by the source corpus.
Federated learning is an emerging machine learning technique that enables distributed model training using local datasets from large-scale nodes, e.g., mobile devices, but shares only model updates without uploading the raw training data. This technique provides a promising privacy preservation for mobile devices while simultaneously ensuring high learning performance. The majority of existing work has focused on designing advanced learning algorithms with an aim to achieve better learning performance. However, the challenges, such as incentive mechanisms for participating in training and worker (i.e., mobile devices) selection schemes for reliable federated learning, have not been explored yet. These challenges have hindered the widespread adoption of federated learning. To address the above challenges, in this article, we first introduce reputation as the metric to measure the reliability and trustworthiness of the mobile devices. We then design a reputation-based worker selection scheme for reliable federated learning by using a multiweight subjective logic model. We also leverage the blockchain to achieve secure reputation management for workers with nonrepudiation and tamper-resistance properties in a decentralized manner. Moreover, we propose an effective incentive mechanism combining reputation with contract theory to motivate high-reputation mobile devices with high-quality data to participate in model learning. Numerical results clearly indicate that the proposed schemes are efficient for reliable federated learning in terms of significantly improving the learning accuracy.
Subfields: Artificial Intelligence, Computer Networks and Communications, Information Systems, Federated & Distributed Learning, Game & Decision Theory
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
- Qiang Yang
- Martin Jaggi
- Jakub Konecný
- Peter Richtárik
- Yang Liu
- Peter Kairouz
- Philip S. Yu
- Ananda Theertha Suresh
In Computer Networks and Communications
- H. Vincent Poor
- Khaled Ben Letaief
- Medhi Bennis
- Sebastian U. Stich
- Dusist Niyato
- Shuguang Cui
- Yuanming Shi
- Mingzhe Chen
In Information Systems
- Dusist Niyato
- Zehui Xiong
- Jiawen Kang
- Dinh C. Nguyen
- Pubudu N. Pathirana
- Ming Ding
- Prateek Mittal
- Aruna Prasad Seneviratne
In Federated & Distributed Learning
In Game & Decision Theory
Citations in the corpus
- Advances and Open Problems in Federated Learning (2019, background): “[225, 224]), but is particularly relevant in the cross-silo setting, where participants may also be business competitors.”
- Privacy-Preserving Traffic Flow Prediction: A Federated Learning Approach (2020, neutral): “[35] used a multiweight subjective logic model”
- Survey on 6G Frontiers: Trends, Applications, Requirements, Technologies and Future Research (2021, methodology): “[223] proposed an incentive FL mechanism using contract theory to allows highly-reputed devices to engage in the training task.”
- Federated Learning for 6G: Applications, Challenges, and Opportunities (2021, background): “One of the most promising distributed machine-learning frameworks is federated learning (FL) [2–19].”
- Federated Learning for Smart Healthcare: A Survey (2021, methodology): “The application of blockchain and game theory for the design of a reliable FL algorithm is studied in [56].”
- A Full Dive Into Realizing the Edge-Enabled Metaverse: Visions, Enabling Technologies, and Challenges (2022, neutral): “2) Federated Learning: Federated learning [236], [237],”
- Federated Learning in Smart City Sensing: Challenges and Opportunities (2020, positive): “Reputation models have been proposed by [145,146] to ensure reliability and trustworthiness of mobile devices.”
- Federated Learning in Vehicular Edge Computing: A Selective Model Aggregation Approach (2020, methodology): “Ek is regarded as a constant for all the vehicular clients [14], [24].”
- Reliable Federated Learning for Mobile Networks (2019, methodology): “The con-a sortium blockchains are specific blockchains that perform the consensus process on pre-selected miners with mild cost in a short time [1], [7].”
- A Survey on Federated Learning: The Journey From Centralized to Distributed On-Site Learning and Beyond (2021, background): “[62] proposed a reputation-based selection of reliable workers to defend against unreliable ones, which chooses the candidates with high-accuracy and efficient training data.”
- Federated Learning in Mobile Edge Networks: A Comprehensive Survey (2019, background): “a reputation-based participant selection scheme for reliable FL [60].”
- Blockchain for 5G and Beyond Networks: A State of the Art Survey (2019, background): “The study in [191] considers a reputation scheme which selects reliable mobile devices (workers) for federated learning”
- Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues (2020, background): “[52] introduce a reputation-based client selection mechanism for FL in mobile networks.”
- Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking Systems (2021, background): “For example, the problem of selecting reliable mobile devices is tackled in [124].”