Partitioning Convolutional Neural Networks to Maximize the Inference Rate on Constrained IoT Devices

Fabíola Martins Campos de Oliveira and Edson Borin
Additional contact information
Fabíola Martins Campos de Oliveira: Institute of Computing, University of Campinas, Campinas 13083-852, SP, Brazil
Edson Borin: Institute of Computing, University of Campinas, Campinas 13083-852, SP, Brazil

Future Internet, 2019, vol. 11, issue 10, 1-30

Abstract: Billions of devices will compose the IoT system in the next few years, generating a huge amount of data. We can use fog computing to process these data, considering that there is the possibility of overloading the network towards the cloud. In this context, deep learning can treat these data, but the memory requirements of deep neural networks may prevent them from executing on a single resource-constrained device. Furthermore, their computational requirements may yield an unfeasible execution time. In this work, we propose Deep Neural Networks Partitioning for Constrained IoT Devices, a new algorithm to partition neural networks for efficient distributed execution. Our algorithm can optimize the neural network inference rate or the number of communications among devices. Additionally, our algorithm accounts appropriately for the shared parameters and biases of Convolutional Neural Networks. We investigate the inference rate maximization for the LeNet model in constrained setups. We show that the partitionings offered by popular machine learning frameworks such as TensorFlow or by the general-purpose framework METIS may produce invalid partitionings for very constrained setups. The results show that our algorithm can partition LeNet for all the proposed setups, yielding up to 38% more inferences per second than METIS.

Keywords: Internet of Things; convolutional neural networks; graph partitioning; distributed systems; resource-efficient inference (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/1999-5903/11/10/209/pdf (application/pdf)
https://www.mdpi.com/1999-5903/11/10/209/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:11:y:2019:i:10:p:209-:d:272094

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().