A Multi-task Supervised Compression Model for Split Computing

TL;DR

This paper introduces Ladon, a multi-task supervised compression model for split computing that improves multi-task performance and significantly reduces latency and energy consumption on resource-constrained devices.

Contribution

Ladon is the first multi-task-head supervised compression model tailored for multi-task split computing, enhancing performance and efficiency.

Findings

Outperformed or matched lightweight baselines on benchmark datasets.

Reduced end-to-end latency by up to 95.4%.

Lowered energy consumption by up to 88.2%.

Abstract

Split computing ($\neq$ split learning) is a promising approach to deep learning models for resource-constrained edge computing systems, where weak sensor (mobile) devices are wirelessly connected to stronger edge servers through channels with limited communication capacity. State-of-theart work on split computing presents methods for single tasks such as image classification, object detection, or semantic segmentation. The application of existing methods to multitask problems degrades model accuracy and/or significantly increase runtime latency. In this study, we propose Ladon, the first multi-task-head supervised compression model for multi-task split computing. Experimental results show that the multi-task supervised compression model either outperformed or rivaled strong lightweight baseline models in terms of predictive performance for ILSVRC 2012, COCO 2017, and PASCAL VOC 2012 datasets while learning compressed representations at its early layers. Furthermore, our models reduced end-to-end latency (by up to 95.4%) and energy consumption of mobile devices (by up to 88.2%) in multi-task split computing scenarios.