Saved in:
Bibliographic Details
Main Authors: Huang, Yushan, Millar, Josh, Long, Yuxuan, Zhao, Yuchen, Haddadi, Hamed
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.15905
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929295917580288
author Huang, Yushan
Millar, Josh
Long, Yuxuan
Zhao, Yuchen
Haddadi, Hamed
author_facet Huang, Yushan
Millar, Josh
Long, Yuxuan
Zhao, Yuchen
Haddadi, Hamed
contents The personalization of machine learning (ML) models to address data drift is a significant challenge in the context of Internet of Things (IoT) applications. Presently, most approaches focus on fine-tuning either the full base model or its last few layers to adapt to new data, while often neglecting energy costs. However, various types of data drift exist, and fine-tuning the full base model or the last few layers may not result in optimal performance in certain scenarios. We propose Target Block Fine-Tuning (TBFT), a low-energy adaptive personalization framework designed for resource-constrained devices. We categorize data drift and personalization into three types: input-level, feature-level, and output-level. For each type, we fine-tune different blocks of the model to achieve optimal performance with reduced energy costs. Specifically, input-, feature-, and output-level correspond to fine-tuning the front, middle, and rear blocks of the model. We evaluate TBFT on a ResNet model, three datasets, three different training sizes, and a Raspberry Pi. Compared with the $Block Avg$, where each block is fine-tuned individually and their performance improvements are averaged, TBFT exhibits an improvement in model accuracy by an average of 15.30% whilst saving 41.57% energy consumption on average compared with full fine-tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2403_15905
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Low-Energy Adaptive Personalization for Resource-Constrained Devices
Huang, Yushan
Millar, Josh
Long, Yuxuan
Zhao, Yuchen
Haddadi, Hamed
Machine Learning
Computer Vision and Pattern Recognition
The personalization of machine learning (ML) models to address data drift is a significant challenge in the context of Internet of Things (IoT) applications. Presently, most approaches focus on fine-tuning either the full base model or its last few layers to adapt to new data, while often neglecting energy costs. However, various types of data drift exist, and fine-tuning the full base model or the last few layers may not result in optimal performance in certain scenarios. We propose Target Block Fine-Tuning (TBFT), a low-energy adaptive personalization framework designed for resource-constrained devices. We categorize data drift and personalization into three types: input-level, feature-level, and output-level. For each type, we fine-tune different blocks of the model to achieve optimal performance with reduced energy costs. Specifically, input-, feature-, and output-level correspond to fine-tuning the front, middle, and rear blocks of the model. We evaluate TBFT on a ResNet model, three datasets, three different training sizes, and a Raspberry Pi. Compared with the $Block Avg$, where each block is fine-tuned individually and their performance improvements are averaged, TBFT exhibits an improvement in model accuracy by an average of 15.30% whilst saving 41.57% energy consumption on average compared with full fine-tuning.
title Towards Low-Energy Adaptive Personalization for Resource-Constrained Devices
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.15905