Hierarchical Training of Deep Neural Networks Using Early Exiting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sepehri, Yamin, Pad, Pedram, Yüzügüler, Ahmet Caner, Frossard, Pascal, Dunbar, L. Andrea
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914803459555328
author Sepehri, Yamin
Pad, Pedram
Yüzügüler, Ahmet Caner
Frossard, Pascal
Dunbar, L. Andrea
author_facet Sepehri, Yamin
Pad, Pedram
Yüzügüler, Ahmet Caner
Frossard, Pascal
Dunbar, L. Andrea
contents Deep neural networks provide state-of-the-art accuracy for vision tasks but they require significant resources for training. Thus, they are trained on cloud servers far from the edge devices that acquire the data. This issue increases communication cost, runtime and privacy concerns. In this study, a novel hierarchical training method for deep neural networks is proposed that uses early exits in a divided architecture between edge and cloud workers to reduce the communication cost, training runtime and privacy concerns. The method proposes a brand-new use case for early exits to separate the backward pass of neural networks between the edge and the cloud during the training phase. We address the issues of most available methods that due to the sequential nature of the training phase, cannot train the levels of hierarchy simultaneously or they do it with the cost of compromising privacy. In contrast, our method can use both edge and cloud workers simultaneously, does not share the raw input data with the cloud and does not require communication during the backward pass. Several simulations and on-device experiments for different neural network architectures demonstrate the effectiveness of this method. It is shown that the proposed method reduces the training runtime for VGG-16 and ResNet-18 architectures by 29% and 61% in CIFAR-10 classification and by 25% and 81% in Tiny ImageNet classification when the communication with the cloud is done over a low bit rate channel. This gain in the runtime is achieved whilst the accuracy drop is negligible. This method is advantageous for online learning of high-accuracy deep neural networks on sensor-holding low-resource devices such as mobile phones or robots as a part of an edge-cloud system, making them more flexible in facing new tasks and classes of data.
format Preprint
id arxiv_https___arxiv_org_abs_2303_02384
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Hierarchical Training of Deep Neural Networks Using Early Exiting
Sepehri, Yamin
Pad, Pedram
Yüzügüler, Ahmet Caner
Frossard, Pascal
Dunbar, L. Andrea
Computer Vision and Pattern Recognition
Distributed, Parallel, and Cluster Computing
Machine Learning
Image and Video Processing
I.2.6; I.2.10; I.2.11
Deep neural networks provide state-of-the-art accuracy for vision tasks but they require significant resources for training. Thus, they are trained on cloud servers far from the edge devices that acquire the data. This issue increases communication cost, runtime and privacy concerns. In this study, a novel hierarchical training method for deep neural networks is proposed that uses early exits in a divided architecture between edge and cloud workers to reduce the communication cost, training runtime and privacy concerns. The method proposes a brand-new use case for early exits to separate the backward pass of neural networks between the edge and the cloud during the training phase. We address the issues of most available methods that due to the sequential nature of the training phase, cannot train the levels of hierarchy simultaneously or they do it with the cost of compromising privacy. In contrast, our method can use both edge and cloud workers simultaneously, does not share the raw input data with the cloud and does not require communication during the backward pass. Several simulations and on-device experiments for different neural network architectures demonstrate the effectiveness of this method. It is shown that the proposed method reduces the training runtime for VGG-16 and ResNet-18 architectures by 29% and 61% in CIFAR-10 classification and by 25% and 81% in Tiny ImageNet classification when the communication with the cloud is done over a low bit rate channel. This gain in the runtime is achieved whilst the accuracy drop is negligible. This method is advantageous for online learning of high-accuracy deep neural networks on sensor-holding low-resource devices such as mobile phones or robots as a part of an edge-cloud system, making them more flexible in facing new tasks and classes of data.
title Hierarchical Training of Deep Neural Networks Using Early Exiting
topic Computer Vision and Pattern Recognition
Distributed, Parallel, and Cluster Computing
Machine Learning
Image and Video Processing
I.2.6; I.2.10; I.2.11
url https://arxiv.org/abs/2303.02384