Incentive Mechanism Design for Joint Resource Allocation in Blockchain-Based Federated Learning
Incentive Mechanism Design for Joint Resource Allocation in Blockchain-Based Federated Learning
复制标题
基于区块链的联邦学习中联合资源分配的激励机制设计
DOI：
10.1109/tpds.2023.3253604
复制
发表时间：
2022-02
影响因子：
5.3
通讯作者：
Zhilin Wang;Qin Hu;Ruinian Li;Minghui Xu;Zehui Xiong
中科院分区：
文献类型：
--
作者：
Zhilin Wang;Qin Hu;Ruinian Li;Minghui Xu;Zehui Xiong
基于区块链的联邦学习（BCFL）最近因其去中心化和原始数据隐私保护等优点而受到极大关注。然而，很少有研究关注参与设备的资源分配（即，在BCFL系统中。特别是，在FL客户端也是区块链矿工的BCFL框架中，客户端必须训练本地模型，将训练好的模型更新广播到区块链网络，然后进行挖掘以生成新的区块。由于每个客户端具有有限的计算资源，因此需要仔细解决将计算资源分配给训练和挖掘的问题。在本文中，我们设计了一种激励机制，以帮助模型所有者（MO）（即，BCFL任务发布者）为每个客户端分配用于训练和挖掘的适当奖励，然后客户端将使用两阶段Stackelberg游戏基于这些奖励来确定分配给每个子任务的计算能力的量。在分析MO和客户的效用后，我们将博弈模型转化为两个优化问题，依次求解，得到MO和客户的最优策略。此外，考虑到每个客户端的本地培训相关信息可能不被其他人知道的事实，我们扩展了具有不完全信息场景的解析解的博弈模型。大量的实验结果证明了我们提出的方案的有效性。
Blockchain-based federated learning (BCFL) has recently gained tremendous attention because of its advantages, such as decentralization and privacy protection of raw data. However, there has been few studies focusing on the allocation of resources for the participated devices (i.e., clients) in the BCFL system. Especially, in the BCFL framework where the FL clients are also the blockchain miners, clients have to train the local models, broadcast the trained model updates to the blockchain network, and then perform mining to generate new blocks. Since each client has a limited amount of computing resources, the problem of allocating computing resources to training and mining needs to be carefully addressed. In this paper, we design an incentive mechanism to help the model owner (MO) (i.e., the BCFL task publisher) assign each client appropriate rewards for training and mining, and then the client will determine the amount of computing power to allocate for each subtask based on these rewards using the two-stage Stackelberg game. After analyzing the utilities of the MO and clients, we transform the game model into two optimization problems, which are sequentially solved to derive the optimal strategies for both the MO and clients. Further, considering the fact that local training related information of each client may not be known by others, we extend the game model with analytical solutions to the incomplete information scenario. Extensive experimental results demonstrate the validity of our proposed schemes.