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.

MTL-Split: Multi-Task Learning for Edge Devices using Split Computing / Capogrosso, Luigi; Fraccaroli, Enrico; Chakraborty, Samarjit; Fummi, Franco; Cristani, Marco. - ELETTRONICO. - (2024), pp. 1-6. (Intervento presentato al convegno DAC '24: 61st ACM/IEEE Design Automation Conference tenutosi a San Francisco, CA (USA) nel June 23 - 27, 2024) [10.1145/3649329.3655686].

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

Capogrosso, Luigi;Fummi, Franco;
2024

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.
2024
979-8-4007-0601-1
File in questo prodotto:
File Dimensione Formato  
3649329.3655686.pdf

accesso aperto

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Pubblico - Tutti i diritti riservati
Dimensione 555.69 kB
Formato Adobe PDF
555.69 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2994382