Optimizing Machine Learning Inference Queries for Multiple Objectives

Ziyu Li; Mariette Schonfeld; Rihan Hai; Alessandro Bozzon; Asterios Katsifodimos

doi:10.1109/ICDEW58674.2023.00017

Optimizing Machine Learning Inference Queries for Multiple Objectives

Ziyu Li^*, Mariette Schonfeld, Rihan Hai, Alessandro Bozzon, Asterios Katsifodimos

^*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

12 Downloads (Pure)

Abstract

Given a set of pre-trained Machine Learning (ML) models, can we solve complex analytic tasks that make use of those models by formulating ML inference queries? Can we mitigate different tradeoffs, e.g., high accuracy, low execution costs and memory footprint, when optimizing the queries? In this work we present different multi-objective ML inference query optimization strategies, and compare them on their usability, applicability, and complexity. We formulate Mixed-Integer-Programming-based (MIP) optimizers for ML inference queries that makes use of different objectives to find Pareto-optimal inference query plans.

Original language	English
Title of host publication	Proceedings - 2023 IEEE 39th International Conference on Data Engineering Workshops, ICDEW 2023
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	74-78
Number of pages	5
ISBN (Electronic)	9798350322446
DOIs	https://doi.org/10.1109/ICDEW58674.2023.00017
Publication status	Published - 2023
Event	39th IEEE International Conference on Data Engineering Workshops, ICDEW 2023 - Anaheim, United States Duration: 3 Apr 2023 → 7 Apr 2023

Publication series

Name	Proceedings - 2023 IEEE 39th International Conference on Data Engineering Workshops, ICDEW 2023

Conference

Conference	39th IEEE International Conference on Data Engineering Workshops, ICDEW 2023
Country/Territory	United States
City	Anaheim
Period	3/04/23 → 7/04/23

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Access to Document

10.1109/ICDEW58674.2023.00017

Optimizing_Machine_Learning_Inference_Queries_for_Multiple_ObjectivesFinal published version, 971 KB

Cite this

Li, Z., Schonfeld, M., Hai, R., Bozzon, A., & Katsifodimos, A. (2023). Optimizing Machine Learning Inference Queries for Multiple Objectives. In Proceedings - 2023 IEEE 39th International Conference on Data Engineering Workshops, ICDEW 2023 (pp. 74-78). (Proceedings - 2023 IEEE 39th International Conference on Data Engineering Workshops, ICDEW 2023). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICDEW58674.2023.00017

Li, Ziyu ; Schonfeld, Mariette ; Hai, Rihan et al. / Optimizing Machine Learning Inference Queries for Multiple Objectives. Proceedings - 2023 IEEE 39th International Conference on Data Engineering Workshops, ICDEW 2023. Institute of Electrical and Electronics Engineers (IEEE), 2023. pp. 74-78 (Proceedings - 2023 IEEE 39th International Conference on Data Engineering Workshops, ICDEW 2023).

@inproceedings{f010bcb0a98d485cb8914137c4fa0b63,

title = "Optimizing Machine Learning Inference Queries for Multiple Objectives",

abstract = "Given a set of pre-trained Machine Learning (ML) models, can we solve complex analytic tasks that make use of those models by formulating ML inference queries? Can we mitigate different tradeoffs, e.g., high accuracy, low execution costs and memory footprint, when optimizing the queries? In this work we present different multi-objective ML inference query optimization strategies, and compare them on their usability, applicability, and complexity. We formulate Mixed-Integer-Programming-based (MIP) optimizers for ML inference queries that makes use of different objectives to find Pareto-optimal inference query plans.",

author = "Ziyu Li and Mariette Schonfeld and Rihan Hai and Alessandro Bozzon and Asterios Katsifodimos",

note = "Green Open Access added to TU Delft Institutional Repository {\textquoteleft}You share, we take care!{\textquoteright} – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.; 39th IEEE International Conference on Data Engineering Workshops, ICDEW 2023 ; Conference date: 03-04-2023 Through 07-04-2023",

year = "2023",

doi = "10.1109/ICDEW58674.2023.00017",

language = "English",

series = "Proceedings - 2023 IEEE 39th International Conference on Data Engineering Workshops, ICDEW 2023",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "74--78",

booktitle = "Proceedings - 2023 IEEE 39th International Conference on Data Engineering Workshops, ICDEW 2023",

address = "United States",

}

Li, Z, Schonfeld, M, Hai, R , Bozzon, A & Katsifodimos, A 2023, Optimizing Machine Learning Inference Queries for Multiple Objectives. in Proceedings - 2023 IEEE 39th International Conference on Data Engineering Workshops, ICDEW 2023. Proceedings - 2023 IEEE 39th International Conference on Data Engineering Workshops, ICDEW 2023, Institute of Electrical and Electronics Engineers (IEEE), pp. 74-78, 39th IEEE International Conference on Data Engineering Workshops, ICDEW 2023, Anaheim, United States, 3/04/23. https://doi.org/10.1109/ICDEW58674.2023.00017

Optimizing Machine Learning Inference Queries for Multiple Objectives. / Li, Ziyu; Schonfeld, Mariette; Hai, Rihan et al.
Proceedings - 2023 IEEE 39th International Conference on Data Engineering Workshops, ICDEW 2023. Institute of Electrical and Electronics Engineers (IEEE), 2023. p. 74-78 (Proceedings - 2023 IEEE 39th International Conference on Data Engineering Workshops, ICDEW 2023).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Optimizing Machine Learning Inference Queries for Multiple Objectives

AU - Li, Ziyu

AU - Schonfeld, Mariette

AU - Hai, Rihan

AU - Bozzon, Alessandro

AU - Katsifodimos, Asterios

N1 - Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2023

Y1 - 2023

N2 - Given a set of pre-trained Machine Learning (ML) models, can we solve complex analytic tasks that make use of those models by formulating ML inference queries? Can we mitigate different tradeoffs, e.g., high accuracy, low execution costs and memory footprint, when optimizing the queries? In this work we present different multi-objective ML inference query optimization strategies, and compare them on their usability, applicability, and complexity. We formulate Mixed-Integer-Programming-based (MIP) optimizers for ML inference queries that makes use of different objectives to find Pareto-optimal inference query plans.

AB - Given a set of pre-trained Machine Learning (ML) models, can we solve complex analytic tasks that make use of those models by formulating ML inference queries? Can we mitigate different tradeoffs, e.g., high accuracy, low execution costs and memory footprint, when optimizing the queries? In this work we present different multi-objective ML inference query optimization strategies, and compare them on their usability, applicability, and complexity. We formulate Mixed-Integer-Programming-based (MIP) optimizers for ML inference queries that makes use of different objectives to find Pareto-optimal inference query plans.

UR - http://www.scopus.com/inward/record.url?scp=85163841187&partnerID=8YFLogxK

U2 - 10.1109/ICDEW58674.2023.00017

DO - 10.1109/ICDEW58674.2023.00017

M3 - Conference contribution

AN - SCOPUS:85163841187

T3 - Proceedings - 2023 IEEE 39th International Conference on Data Engineering Workshops, ICDEW 2023

SP - 74

EP - 78

BT - Proceedings - 2023 IEEE 39th International Conference on Data Engineering Workshops, ICDEW 2023

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 39th IEEE International Conference on Data Engineering Workshops, ICDEW 2023

Y2 - 3 April 2023 through 7 April 2023

ER -

Li Z, Schonfeld M, Hai R , Bozzon A , Katsifodimos A. Optimizing Machine Learning Inference Queries for Multiple Objectives. In Proceedings - 2023 IEEE 39th International Conference on Data Engineering Workshops, ICDEW 2023. Institute of Electrical and Electronics Engineers (IEEE). 2023. p. 74-78. (Proceedings - 2023 IEEE 39th International Conference on Data Engineering Workshops, ICDEW 2023). doi: 10.1109/ICDEW58674.2023.00017

Optimizing Machine Learning Inference Queries for Multiple Objectives

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this