Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Exploring ML testing in practice - Lessons learned from an interactive rapid review with Axis Communications

Song, Qunying LU orcid ; Borg, Markus LU ; Engström, Emelie LU orcid ; Ardö, Håkan and Rico, Sergio LU orcid (2022) 2022 IEEE/ACM 1st International Conference on AI Engineering – Software Engineering for AI (CAIN)
Abstract
There is a growing interest in industry and academia in machine learning (ML) testing. We believe that industry and academia need to learn together to produce rigorous and relevant knowledge. In this study, we initiate a collaboration between stakeholders from one case company, one research institute, and one university. To establish a common view of the problem domain, we applied an interactive rapid review of the state of the art. Four researchers from Lund University and RISE Research Institutes and four practitioners from Axis Communications reviewed a set of 180 primary studies on ML testing. We developed a taxonomy for the communication around ML testing challenges and results and identified a list of 12 review questions relevant for... (More)
There is a growing interest in industry and academia in machine learning (ML) testing. We believe that industry and academia need to learn together to produce rigorous and relevant knowledge. In this study, we initiate a collaboration between stakeholders from one case company, one research institute, and one university. To establish a common view of the problem domain, we applied an interactive rapid review of the state of the art. Four researchers from Lund University and RISE Research Institutes and four practitioners from Axis Communications reviewed a set of 180 primary studies on ML testing. We developed a taxonomy for the communication around ML testing challenges and results and identified a list of 12 review questions relevant for Axis Communications. The three most important questions (data testing, metrics for assessment, and test generation) were mapped to the literature, and an in-depth analysis of the 35 primary studies matching the most important question (data testing) was made. A final set of the five best matches were analysed and we reflect on the criteria for applicability and relevance for the industry. The taxonomies are helpful for communication but not final. Furthermore, there was no perfect match to the case company’s investigated review question (data testing). However, we extracted relevant approaches from the five studies on a conceptual level to support later context-specific improvements. We found the interactive rapid review approach useful for triggering and aligning communication between the different stakeholders. (Less)
Please use this url to cite or link to this publication:
author
; ; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
AI Engineering, Machine Learning Testing, Interactive Rapid Review, Taxonomy
host publication
2022 IEEE/ACM 1st International Conference on AI Engineering – Software Engineering for AI (CAIN)
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
2022 IEEE/ACM 1st International Conference on AI Engineering – Software Engineering for AI (CAIN)
conference location
Pittsburg, United States
conference dates
2022-05-16 - 2022-05-17
external identifiers
  • scopus:85128924924
ISBN
978-1-6654-5206-9
978-1-4503-9275-4
project
WASP: Wallenberg AI, Autonomous Systems and Software Program at Lund University
Software testing of autonomous systems
language
English
LU publication?
yes
id
1eb11df2-93f5-4998-91ba-497ae2fc1c44
alternative location
https://ieeexplore.ieee.org/document/9796447
date added to LUP
2022-08-23 13:12:52
date last changed
2024-11-12 22:20:00
@inproceedings{1eb11df2-93f5-4998-91ba-497ae2fc1c44,
  abstract     = {{There is a growing interest in industry and academia in machine learning (ML) testing. We believe that industry and academia need to learn together to produce rigorous and relevant knowledge. In this study, we initiate a collaboration between stakeholders from one case company, one research institute, and one university. To establish a common view of the problem domain, we applied an interactive rapid review of the state of the art. Four researchers from Lund University and RISE Research Institutes and four practitioners from Axis Communications reviewed a set of 180 primary studies on ML testing. We developed a taxonomy for the communication around ML testing challenges and results and identified a list of 12 review questions relevant for Axis Communications. The three most important questions (data testing, metrics for assessment, and test generation) were mapped to the literature, and an in-depth analysis of the 35 primary studies matching the most important question (data testing) was made. A final set of the five best matches were analysed and we reflect on the criteria for applicability and relevance for the industry. The taxonomies are helpful for communication but not final. Furthermore, there was no perfect match to the case company’s investigated review question (data testing). However, we extracted relevant approaches from the five studies on a conceptual level to support later context-specific improvements. We found the interactive rapid review approach useful for triggering and aligning communication between the different stakeholders.}},
  author       = {{Song, Qunying and Borg, Markus and Engström, Emelie and Ardö, Håkan and Rico, Sergio}},
  booktitle    = {{2022 IEEE/ACM 1st International Conference on AI Engineering – Software Engineering for AI (CAIN)}},
  isbn         = {{978-1-6654-5206-9}},
  keywords     = {{AI Engineering; Machine Learning Testing; Interactive Rapid Review; Taxonomy}},
  language     = {{eng}},
  month        = {{05}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Exploring ML testing in practice - Lessons learned from an interactive rapid review with Axis Communications}},
  url          = {{https://lup.lub.lu.se/search/files/123042444/2203.16225.pdf}},
  year         = {{2022}},
}