MTL-Split: Multi-Task Learning for Edge Devices using Split Computing

TL;DR

This paper introduces MTL-Split, a novel multi-task split computing architecture that efficiently partitions multi-task DNNs between edge devices and remote servers, addressing resource constraints in latency-sensitive applications.

Contribution

It proposes a new architecture for multi-task DNN partitioning in split computing, filling a gap in existing research on multi-task deployment in resource-constrained environments.

Findings

Encouraging results on synthetic data

Effective partitioning for real-world data

Open-source implementation available

Abstract

Split Computing (SC), where a Deep Neural Network (DNN) is intelligently split with a part of it deployed on an edge device and the rest on a remote server is emerging as a promising approach. It allows the power of DNNs to be leveraged for latency-sensitive applications that do not allow the entire DNN to be deployed remotely, while not having sufficient computation bandwidth available locally. In many such embedded systems scenarios, such as those in the automotive domain, computational resource constraints also necessitate Multi-Task Learning (MTL), where the same DNN is used for multiple inference tasks instead of having dedicated DNNs for each task, which would need more computing bandwidth. However, how to partition such a multi-tasking DNN to be deployed within a SC framework has not been sufficiently studied. This paper studies this problem, and MTL-Split, our novel proposed architecture, shows encouraging results on both synthetic and real-world data. The source code is available at https://github.com/intelligolabs/MTL-Split.