Efficient Sample Alignment with Fast Polynomial Interpolation for Vertical Federated Learning
Jingwei Liu, Tiezheng Ma, Huachong Zhang, Wei Yong Liu, Qingqi Pei · 2023
Sample alignment technique is a key component of vertical federated learning. One of the important solutions for sample alignment is known as private set intersection (PSI). It requires multiple participants to collaboratively compute the intersection from their samples while preserving data security and privacy. However, with a growing number of participants and samples, the communication and computation overhead of the multiparty PSI protocol becomes heavy, which severely impacts the performance of vertical federated learning. To improve the efficiency of sample alignment, this paper proposes a distributed multiparty PSI protocol based on fast Fourier transform (FFT) polynomial interpolation and oblivious pseudo-random function (OPRF). The scheme reduces communication complexity by FFT polynomial interpolation. Meanwhile, it employs OPRF to resist collusion attacks. We evaluate the performance of the scheme in two scenarios: without collusion and arbitrary collusion. The experimental results indicate that the scheme is a practical and efficient solution for sample alignment in vertical federated learning.