理性与可验证的联邦学习框架

联邦学习作为解决数据孤岛问题的有效方法,在服务器计算全部梯度的过程中,由于服务器的惰性和自利性会存在全局梯度不正确计算问题,因此需要验证全局梯度的完整性.现有的基于密码算法的方案验证开销过大.针对这些问题,提出一种理性与可验证的联邦学习框架.首先,结合博弈论,设计囚徒合约与背叛合约迫使服务器诚实.其次,所提方案使用基于复制的验证方案实现全局梯度的完整性验证,且支持客户端离线.最后,经分析证明所提方案的正确性,并经实验表明,该方案与已有的验证算法相比,客户端的计算开销降为0,一次迭代的通信轮数由原来的3轮优化到2轮,且训练开销与客户端的离线率成反比.

Rational and Verifiable Federated Learning Framework

Federated learning is an effective method to solve the problem of data silos. When the server calculates all gradients, incorrect calculation of global gradients exists due to the inertia and self-interest of the server, so it is necessary to verify the integrity of global gradients. The existing schemes based on cryptographic algorithms are overspending on verification. To solve these problems, this study proposes a rational and verifiable federated learning framework. Firstly, according to game theory, the prisoner contract and betrayal contract are designed to force the server to be honest. Secondly, the scheme uses a replication-based verification scheme to verify the integrity of the global gradient and supports the offline client side. Finally, the analysis proves the correctness of the scheme, and the experiments show that compared with the existing verification algorithms, the proposed scheme reduces the computing overhead of the client side to zero, the number of communication rounds in one iteration is optimized from three to two, and the training overhead is inversely proportional to the offline rate of the client side