.png){kind=icon}
返回
DReP: Deep ReLU pruning for fast private inference
.png){kind=icon}
PRE
AI
DOI：10.1016/j.sysarc.2024.103156.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
With increasing concerns about privacy issues in deep learning, privacy -preserving neural network inference has been receiving growing attention from the community, but the implementation lacks practicality due to high latency and high cost. It is suited for latency -efficient private inference (PI) to reduce ReLU in neural networks. Existing methods of ReLU reduction for efficient PI usually disregard the benefits of pre -trained models and may introduce more complexities in the era of large models. In this paper, we propose a novel method called DReP, which leverages the output states of neurons to perform deep pruning of ReLU in neural networks for Non -Retraining and Non -Redesign (NTND) scenarios. DReP is based on the identify of a consistent correlation between the average neuronal output states and the importance of ReLUs, and enables deep pruning of ReLU in addition to structured ReLU pre -pruning methods. Notably, DReP does not require modification of the network model structure or extensive retraining, aligning with the requirements of NTND applications. Experimental results demonstrate that our method reduces the number of ReLUs in the original network by 16.66 x while maintaining network accuracy. Moreover, when compared with state-of-the-art NTND methods, our approach achieves a pruning rate improvement of 1.57 x similar to 2 . 32x while preserving comparable privacy inference accuracy.
Keyword:
Neural network
Private inference
ReLU pruning
Non-retraining and non-redesign
期刊
IF:
4.1
论文数:
3.0K
被引数:
4.2K
机构
引用论文
.png){kind=icon}
Private Inference for Deep Neural Networks: A Secure, Adaptive, and Efficient Realization深度神经网络的私有推理: 一种安全、自适应和高效的实现
PREAI
分享收藏Optimizing deep neural networks on intelligent edge accelerators via flexible-rate filter pruning
PREAI
分享收藏The power of obfuscation techniques in malicious JavaScript code: A measurement study恶意JavaScript代码中混淆技术的功能: 一项测量研究
OAAI
OAAI分享收藏Developing Wind and/or Solar Powered Crop Irrigation Systems for the Great Plains为大平原开发风能和/或太阳能作物灌溉系统
PREAI
分享收藏
查看更多内容