EdgeOL: Efficient in-situ Online Learning on Edge Devices
This addresses energy and time inefficiencies in online learning for edge applications like robotics and object recognition, representing an incremental improvement.
The paper tackles the problem of inefficient online learning on edge devices by proposing EdgeOL, which reduces fine-tuning execution time by 64%, energy consumption by 52%, and improves inference accuracy by 1.75% on average.
Emerging applications, such as robot-assisted eldercare and object recognition, generally employ deep learning neural networks (DNNs) 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, an inappropriate fine-tuning scheme could involve 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 64%, energy consumption by 52%, and improves average inference accuracy by 1.75% over the immediate online learning strategy