VF 2 Boost: Very Fast Vertical Federated Gradient Boosting for Cross-Enterprise Learning
Authors:
Open Access
- 9 June 2021
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 563-576
Abstract
With the ever-evolving concerns on privacy protection, vertical federated learning (FL), where participants own non-overlapping features for the same set of instances, is becoming a heated topic since it enables multiple enterprises to strengthen the machine learning models collaboratively with privacy guarantees. Nevertheless, to achieve privacy preservation, vertical FL algorithms involve complicated training routines and time-consuming cryptography operations, leading to slow training speed. This paper explores the efficiency of the gradient boosting decision tree (GBDT) algorithm under the vertical FL setting. Specifically, we introduce VF^2Boost, a novel and efficient vertical federated GBDT system. Significant solutions are developed to tackle the major bottlenecks. First, to handle the deficiency caused by frequent mutual-waiting in federated training, we propose a concurrent training protocol to reduce the idle periods. Second, to speed up the cryptography operations, we analyze the characteristics of the algorithm and propose customized operations. Empirical results show that our system can be 12.8-18.9 times faster than the existing vertical federated implementations and support much larger datasets.Keywords
This publication has 43 references indexed in Scilit:
- Controlled-Channel Attacks: Deterministic Side Channels for Untrusted Operating Systems2015
- PLANETProceedings of the VLDB Endowment, 2009
- Fully homomorphic encryption using ideal lattices2009
- Optimization of Collective Communication Operations in MPICHThe International Journal of High Performance Computing Applications, 2005
- Privacy-Preserving Inter-database Operations2004
- Efficient Private Matching and Set Intersection2004
- Space-efficient online computation of quantile summariesACM SIGMOD Record, 2001
- A Public Key Cryptosystem and a Signature Scheme Based on Discrete Logarithms2000
- On optimistic methods for concurrency controlACM Transactions on Database Systems, 1981
- A method for obtaining digital signatures and public-key cryptosystemsCommunications of the ACM, 1978