Optimizing ML Inference Queries Under Constraints

Conference Paper (2023)
Author(s)

Ziyu Li (TU Delft - Web Information Systems)

W. Sun (TU Delft - Web Information Systems)

R. Hai (TU Delft - Web Information Systems)

A. Bozzon (TU Delft - Human-Centred Artificial Intelligence)

A Katsifodimos (TU Delft - Web Information Systems)

Research Group
Web Information Systems
Copyright
© 2023 Z. Li, W. Sun, R. Hai, A. Bozzon, A Katsifodimos
DOI related publication
https://doi.org/10.1007/978-3-031-34444-2_4
More Info
expand_more
Publication Year
2023
Language
English
Copyright
© 2023 Z. Li, W. Sun, R. Hai, A. Bozzon, A Katsifodimos
Research Group
Web Information Systems
Pages (from-to)
51-66
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

The proliferation of pre-trained ML models in public Web-based model zoos facilitates the engineering of ML pipelines to address complex inference queries over datasets and streams of unstructured content. Constructing optimal plan for a query is hard, especially when constraints (e.g. accuracy or execution time) must be taken into consideration, and the complexity of the inference query increases. To address this issue, we propose a method for optimizing ML inference queries that selects the most suitable ML models to use, as well as the order in which those models are executed. We formally define the constraint-based ML inference query optimization problem, formulate it as a Mixed Integer Programming (MIP) problem, and develop an optimizer that maximizes accuracy given constraints. This optimizer is capable of navigating a large search space to identify optimal query plans on various model zoos.

Files

978_3_031_34444_2_4.pdf
(pdf | 0.86 Mb)
- Embargo expired in 25-12-2023
License info not available