Info: Zenodo’s user support line is staffed on regular business days between Dec 23 and Jan 5. Response times may be slightly longer than normal.

Published May 29, 2020 | Version v1
Preprint Open

Parallelizing Machine Learning as a Service for the End-User

  • 1. University of Bologna, Italy
  • 2. University of Modena and Reggio-Emilia, Italy

Description

As ML applications are becoming ever more pervasive, fully-trained systems are made increasingly available to a wide public, allowing end-users to submit queries with their own data, and to efficiently retrieve results. With increasingly sophisticated such services, a new challenge is how to scale up to evergrowing user bases. In this paper, we present a distributed architecture that could be exploited to parallelize a typical ML system pipeline. We propose a case study consisting of a text mining service and discuss how the method can be generalized to many similar applications. We demonstrate the significance of the computational gain boosted by the distributed architecture by way of an extensive experimental evaluation.

Notes

This is the open access arXiv preprint also available at https://arxiv.org/abs/2005.14080. The article's final version appeared in Future Generation Computer Systems 105 (2020) 275-286, DOI: 10.1016/j.future.2019.11.042

Files

2005.14080.pdf

Files (3.1 MB)

Name Size Download all
md5:7c3b1671e3edc0bef1dec812c749bfd7
3.1 MB Preview Download

Additional details

Funding

AI4EU – A European AI On Demand Platform and Ecosystem 825619
European Commission