Transferring performance between distinct configurable systems: A case study

Luc Lesoil, Hugo Martin, Mathieu Acher, Arnaud Blouin, Jean Marc Jézéquel

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Many research studies predict the performance of configurable software using machine learning techniques, thus requiring large amounts of data. Transfer learning aims to reduce the amount of data needed to train these models and has been successfully applied on different executing environments (hardware) or software versions. In this paper we investigate for the first time the idea of applying transfer learning between distinct configurable systems. We design a study involving two video encoders (namely x264 and x265) coming from different code bases. Our results are encouraging since transfer learning outperforms traditional learning for two performance properties (out of three). We discuss the open challenges to overcome for a more general application.

Original languageEnglish
Title of host publicationProceedings - VaMoS 2022
Subtitle of host publication16th International Working Conference on Variability Modelling of Software-Intensive Systems
EditorsPaolo Arcaini, Xavier Devroey, Alessandro Fantechi
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450396042
DOIs
Publication statusPublished - 23 Feb 2022
Externally publishedYes
Event16th International Working Conference on Variability Modelling of Software-Intensive Systems, VaMoS 2022 - Virtual, Online, Italy
Duration: 23 Feb 202225 Feb 2022

Publication series

NameACM International Conference Proceeding Series

Conference

Conference16th International Working Conference on Variability Modelling of Software-Intensive Systems, VaMoS 2022
Country/TerritoryItaly
CityVirtual, Online
Period23/02/2225/02/22

Fingerprint

Dive into the research topics of 'Transferring performance between distinct configurable systems: A case study'. Together they form a unique fingerprint.

Cite this