EQO：基于Winograd的协议与量化协同优化探索超高效私有推理
EQO: Exploring Ultra-Efficient Private Inference with Winograd-Based Protocol and Quantization Co-Optimization
AI总结：
针对基于2PC的私有CNN推理通信与延迟开销高的问题，提出EQO框架，通过协议级推理图优化、网络级混合精度量化与位重加权算法，实现通信量大幅降低且精度提升。
摘要：
基于安全两方计算（2PC）的私有卷积神经网络（CNN）推理存在通信开销与延迟过高的问题，卷积层的开销尤为突出。本文提出EQO，这是一种可协同优化CNN与2PC协议的量化2PC推理框架。EQO的核心是一种将Winograd变换与量化相结合的新型2PC协议，用于实现高效卷积计算。但我们发现，简单直接地结合量化与Winograd卷积效果不佳：Winograd变换会引入大量局部加法运算与权重离群值，导致量化位宽增加，且需要频繁进行位宽转换，带来不可忽视的通信开销。因此，在协议层面，我们针对2PC推理图提出了一系列优化方案以最小化通信量；在网络层面，我们开发了一种基于敏感度的混合精度量化算法，可在通信约束下优化网络精度；我们还进一步提出了一种适配2PC的位重加权算法，无需增加位宽即可应对权重离群值问题。大量实验表明，与当前最优框架SiRNN、COINN、CoPriv相比，EQO的通信量分别降低了11.7倍、3.6倍、6.3倍，同时精度分别提升了1.29%、1.16%、1.29%。
英文摘要：
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%, 1.16%, and 1.29% higher accuracy compared to state-of-the-art frameworks SiRNN, COINN, and CoPriv, respectively.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
