【Author】
Kang, Jiawen; Xiong, Zehui; Niyato, Dusit; Xie, Shengli; Zhang, Junshan
【Source】IEEE INTERNET OF THINGS JOURNAL
【Abstract】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.
【Keywords】Blockchain; contract theory; federated learning; mobile networks; reputation; security and privacy
【标题】可靠联邦学习的激励机制：一种结合声誉和合同理论的联合优化方法
【摘要】联邦学习是一种新兴的机器学习技术，可以使用来自大型节点（例如移动设备）的本地数据集进行分布式模型训练，但仅共享模型更新而不上传原始训练数据。该技术为移动设备提供了有前途的隐私保护，同时确保了高学习性能。现有的大部分工作都集中在设计高级学习算法上，以实现更好的学习性能。然而，诸如参与培训的激励机制和可靠联邦学习的工人（即移动设备）选择方案等挑战尚未得到探索。这些挑战阻碍了联邦学习的广泛采用。为了应对上述挑战，在本文中，我们首先引入声誉作为衡量移动设备可靠性和可信度的指标。然后，我们通过使用多权重主观逻辑模型设计了一种基于信誉的工人选择方案，以实现可靠的联邦学习。我们还利用区块链以分散的方式为具有不可否认性和防篡改特性的工人实现安全的声誉管理。此外，我们提出了一种将声誉与契约理论相结合的有效激励机制，以激励具有高质量数据的高声誉移动设备参与模型学习。数值结果清楚地表明，就显着提高学习精度而言，所提出的方案对于可靠的联邦学习是有效的。
【关键词】区块链；契约论；联邦学习；手机网络;名声;安全和隐私
评论