Adapting Deep Learning models to IoT environments

Sofien Resifi (1) , Hassan Hassan (2) , Khalil Drira (1)

1 LAAS-SARA - Équipe Services et Architectures pour Réseaux Avancés
2 LAAS-IDEA - Service Informatique : Développement, Exploitation et Assistance

Deep Learning (DL) models are very efficient for many applications including, computer vision, natural language processing.... Yet DL models require important computation resources making it particularly difficult to deploy these applications in constrained environments such as the Internet of Things (IoT). Offloading DL models to the cloud is one solution to this problem but has a number of drawbacks related to the tradeoff between efficiency and latency, and other privacy issues. In this paper we try to solve this problem using two approaches, first by sharing the DL model between the cloud and the device and second by optimising the execution of the model using early exiting where inputs do not need to execute the model entirely. Both approaches are optimized automatically in order to choose the best sharing point and the best exiting point according to input. The solutions proposed could be easily generalized and are independent of applications and offer a good alternative in order to execute DL models locally.

Mots clés: Deep Learning; IoT; cloud computing; partitioning; optimization

Domaines: Réseaux et télécommunications [cs.NI]; Intelligence artificielle [cs.AI]

Sofien Resifi, Hassan Hassan, Khalil Drira. Adapting Deep Learning models to IoT environments. 5th Conference on Cloud and Internet of Things (CIoT 2022), Mar 2022, Marrakech, Morocco. ⟨10.1109/CIoT53061.2022.9766636⟩. ⟨hal-03622723⟩