MPCFORMER: FAST, PERFORMANT AND PRIVATE TRANSFORMER INFERENCE WITH MPC
Dacheng Li, Hongyi Wang, Rulin Shao, Han Guo, Eric Xing, Hao Zhang
Abstract
Enabling private inference is crucial for many cloud inference services that are based on Transformer models. However, existing private inference solutions can increase the inference latency by more than 60$\times$ or significantly compromise the inference quality. In this paper, we design the framework MPCFORMER as a practical solution, using Secure Multi-Party Computation (MPC) and Knowledge Distillation (KD). Through extensive evaluations, we show that MPCFORMER significantly speeds up Transformer inference in MPC settings while achieving similar ML performance to the input model. On the IMDb dataset, it achieves similar performance to $\text{BERT}_\text{BASE}$, while being 5.3$\times$ faster. On the GLUE benchmark, it achieves 97% performance of $\text{BERT}_\text{BASE}$ with a 2.2$\times$ speedup. MPCFORMER remains effective with different trained Transformer weights such as $\text{ROBERTA}_\text{BASE}$ and larger models including $\text{BERT}_\text{LARGE}$. Code is available at https://github.com/MccRee177/MPCFormer.
BibTeX
@inproceedings{
li2023mpcformer,
title={{MPCFORMER}: {FAST}, {PERFORMANT} {AND} {PRIVATE} {TRANSFORMER} {INFERENCE} {WITH} {MPC}},
author={Dacheng Li and Hongyi Wang and Rulin Shao and Han Guo and Eric Xing and Hao Zhang},
booktitle={The Eleventh International Conference on Learning Representations },
year={2023},
url={https://openreview.net/forum?id=CWmvjOEhgH-}
}