Combining Cloud and Mobile Computing for Machine Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xu, Ruiqi, Zhang, Tianchi
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911783575355392
author Xu, Ruiqi
Zhang, Tianchi
author_facet Xu, Ruiqi
Zhang, Tianchi
contents Although the computing power of mobile devices is increasing, machine learning models are also growing in size. This trend creates problems for mobile devices due to limitations like their memory capacity and battery life. While many services, like ChatGPT and Midjourney, run all the inferences in the cloud, we believe a flexible and fine-grained task distribution is more desirable. In this work, we consider model segmentation as a solution to improving the user experience, dividing the computation between mobile devices and the cloud in a way that offloads the compute-heavy portion of the model while minimizing the data transfer required. We show that the division not only reduces the wait time for users but can also be fine-tuned to optimize the workloads of the cloud. To achieve that, we design a scheduler that collects information about network quality, client device capability, and job requirements, making decisions to achieve consistent performance across a range of devices while reducing the work the cloud needs to perform.
format Preprint
id arxiv_https___arxiv_org_abs_2402_04880
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Combining Cloud and Mobile Computing for Machine Learning
Xu, Ruiqi
Zhang, Tianchi
Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Machine Learning
Although the computing power of mobile devices is increasing, machine learning models are also growing in size. This trend creates problems for mobile devices due to limitations like their memory capacity and battery life. While many services, like ChatGPT and Midjourney, run all the inferences in the cloud, we believe a flexible and fine-grained task distribution is more desirable. In this work, we consider model segmentation as a solution to improving the user experience, dividing the computation between mobile devices and the cloud in a way that offloads the compute-heavy portion of the model while minimizing the data transfer required. We show that the division not only reduces the wait time for users but can also be fine-tuned to optimize the workloads of the cloud. To achieve that, we design a scheduler that collects information about network quality, client device capability, and job requirements, making decisions to achieve consistent performance across a range of devices while reducing the work the cloud needs to perform.
title Combining Cloud and Mobile Computing for Machine Learning
topic Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2402.04880