EQO: Exploring Ultra-Efficient Private Inference with Winograd-Based Protocol and Quantization Co-Optimization
arxiv(2024)
摘要
Private convolutional neural network (CNN) inference based on secure
two-party computation (2PC) suffers from high communication and latency
overhead, especially from convolution layers. In this paper, we propose EQO, a
quantized 2PC inference framework that jointly optimizes the CNNs and 2PC
protocols. EQO features a novel 2PC protocol that combines Winograd
transformation with quantization for efficient convolution computation.
However, we observe naively combining quantization and Winograd convolution is
sub-optimal: Winograd transformations introduce extensive local additions and
weight outliers that increase the quantization bit widths and require frequent
bit width conversions with non-negligible communication overhead. Therefore, at
the protocol level, we propose a series of optimizations for the 2PC inference
graph to minimize the communication. At the network level, We develop a
sensitivity-based mixed-precision quantization algorithm to optimize network
accuracy given communication constraints. We further propose a 2PC-friendly bit
re-weighting algorithm to accommodate weight outliers without increasing bit
widths. With extensive experiments, EQO demonstrates 11.7x, 3.6x, and 6.3x
communication reduction with 1.29
to state-of-the-art frameworks SiRNN, COINN, and CoPriv, respectively.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要