EdgeOL: Efficient in-situ Online Learning on Edge Devices
CoRR(2024)
摘要
Emerging applications, such as robot-assisted eldercare and object
recognition, generally employ deep learning neural networks (DNNs) models and
naturally require: i) handling streaming-in inference requests and ii) adapting
to possible deployment scenario changes. Online model fine-tuning is widely
adopted to satisfy these needs. However, fine-tuning involves significant
energy consumption, making it challenging to deploy on edge devices. In this
paper, we propose EdgeOL, an edge online learning framework that optimizes
inference accuracy, fine-tuning execution time, and energy efficiency through
both inter-tuning and intra-tuning optimizations. Experimental results show
that, on average, EdgeOL reduces overall fine-tuning execution time by 82
energy consumption by 74
over the immediate online learning strategy.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要