Adaptive Compression-Aware Split Learning and Inference for Enhanced Network Efficiency

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mudvari, Akrit, Vainio, Antero, Ofeidis, Iason, Tarkoma, Sasu, Tassiulas, Leandros
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929230595489792
author Mudvari, Akrit
Vainio, Antero
Ofeidis, Iason
Tarkoma, Sasu
Tassiulas, Leandros
author_facet Mudvari, Akrit
Vainio, Antero
Ofeidis, Iason
Tarkoma, Sasu
Tassiulas, Leandros
contents The growing number of AI-driven applications in mobile devices has led to solutions that integrate deep learning models with the available edge-cloud resources. Due to multiple benefits such as reduction in on-device energy consumption, improved latency, improved network usage, and certain privacy improvements, split learning, where deep learning models are split away from the mobile device and computed in a distributed manner, has become an extensively explored topic. Incorporating compression-aware methods (where learning adapts to compression level of the communicated data) has made split learning even more advantageous. This method could even offer a viable alternative to traditional methods, such as federated learning techniques. In this work, we develop an adaptive compression-aware split learning method ('deprune') to improve and train deep learning models so that they are much more network-efficient, which would make them ideal to deploy in weaker devices with the help of edge-cloud resources. This method is also extended ('prune') to very quickly train deep learning models through a transfer learning approach, which trades off little accuracy for much more network-efficient inference abilities. We show that the 'deprune' method can reduce network usage by 4x when compared with a split-learning approach (that does not use our method) without loss of accuracy, while also improving accuracy over compression-aware split-learning by 4 percent. Lastly, we show that the 'prune' method can reduce the training time for certain models by up to 6x without affecting the accuracy when compared against a compression-aware split-learning approach.
format Preprint
id arxiv_https___arxiv_org_abs_2311_05739
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Adaptive Compression-Aware Split Learning and Inference for Enhanced Network Efficiency
Mudvari, Akrit
Vainio, Antero
Ofeidis, Iason
Tarkoma, Sasu
Tassiulas, Leandros
Networking and Internet Architecture
Machine Learning
The growing number of AI-driven applications in mobile devices has led to solutions that integrate deep learning models with the available edge-cloud resources. Due to multiple benefits such as reduction in on-device energy consumption, improved latency, improved network usage, and certain privacy improvements, split learning, where deep learning models are split away from the mobile device and computed in a distributed manner, has become an extensively explored topic. Incorporating compression-aware methods (where learning adapts to compression level of the communicated data) has made split learning even more advantageous. This method could even offer a viable alternative to traditional methods, such as federated learning techniques. In this work, we develop an adaptive compression-aware split learning method ('deprune') to improve and train deep learning models so that they are much more network-efficient, which would make them ideal to deploy in weaker devices with the help of edge-cloud resources. This method is also extended ('prune') to very quickly train deep learning models through a transfer learning approach, which trades off little accuracy for much more network-efficient inference abilities. We show that the 'deprune' method can reduce network usage by 4x when compared with a split-learning approach (that does not use our method) without loss of accuracy, while also improving accuracy over compression-aware split-learning by 4 percent. Lastly, we show that the 'prune' method can reduce the training time for certain models by up to 6x without affecting the accuracy when compared against a compression-aware split-learning approach.
title Adaptive Compression-Aware Split Learning and Inference for Enhanced Network Efficiency
topic Networking and Internet Architecture
Machine Learning
url https://arxiv.org/abs/2311.05739