Home   Research Publications Members Related Software
IndexBrowse   BibliographiesMy selection
 Search: in   (word length ≥ 3)
      Login
Publication no #651   Download bibtex file Type :   Html | Bib | Both
Add to my selection
Self-Adaptation for Machine Learning Based Systems

Maria Casimiro, Paolo Romano, David Garlan, Gabriel A. Moreno, Eunsuk Kang and Mark Klein.


In Proceedings of the 1st International Workshop on Software Architecture and Machine Learning (SAML), Springer, Virtual, (Originally Växjö, Sweden), 14 September 2021.

Online links: PDF

Abstract
Today’s world is witnessing a shift from human-written software to machine-learned software, with the rise of systems that rely on machine learning. These systems typically operate in non-static environments, which are prone to unexpected changes, as is the case of self-driving cars and enterprise systems. In this context, machine-learned software can misbehave. Thus, it is paramount that these systems are capable of detecting problems with their machined-learned components and adapt themselves to maintain desired qualities. For instance, a fraud detection system that cannot adapt its machine-learned model to efficiently cope with emerging fraud patterns or changes in the volume of transactions is subject to losses of millions of dollars. In this paper, we take a first step towards the development of a framework aimed to self-adapt systems that rely on machine-learned components. We describe: (i) a set of causes of machine-learned component misbehavior and a set of adaptation tactics inspired by the literature on machine learning, motivating them with the aid of a running example; (ii) the required changes to the MAPE-K loop, a popular control loop for self-adaptive systems; and (iii) the challenges associated with developing this framework. We conclude the paper with a set of research questions to guide future work.

Keywords: Machine Learning, Self-adaptation.  
@InProceedings{SAML21,
      AUTHOR = {Casimiro, Maria and Romano, Paolo and Garlan, David and Moreno, Gabriel A. and Kang, Eunsuk and Klein, Mark},
      TITLE = {Self-Adaptation for Machine Learning Based Systems},
      YEAR = {2021},
      MONTH = {14 September},
      BOOKTITLE = {Proceedings of the 1st International Workshop on Software Architecture and Machine Learning (SAML)},
      SERIES = {LNCS},
      ADDRESS = {Virtual, (Originally V\"axjö, Sweden)},
      PUBLISHER = {Springer},
      PDF = {http://acme.able.cs.cmu.edu/pubs/uploads/pdf/SAML2021-paper6SAML21.pdf},
      ABSTRACT = {Today’s world is witnessing a shift from human-written software to machine-learned software, with the rise of systems that rely on machine learning. These systems typically operate in non-static environments, which are prone to unexpected changes, as is the case of self-driving cars and enterprise systems. In this context, machine-learned software can misbehave. Thus, it is paramount that these systems are capable of detecting problems with their machined-learned components and adapt themselves to maintain desired qualities. For instance, a fraud detection system that cannot adapt its machine-learned model to efficiently cope with emerging fraud patterns or changes in the volume of transactions is subject to losses of millions of dollars. In this paper, we take a first step towards the development of a framework aimed to self-adapt systems that rely on machine-learned components. We describe: (i) a set of causes of machine-learned component misbehavior and a set of adaptation tactics inspired by the literature on machine learning, motivating them with the aid of a running example; (ii) the required changes to the MAPE-K loop, a popular control loop for self-adaptive systems; and (iii) the challenges associated with developing this framework. We conclude the paper with a set of research questions to guide future work.},
      KEYWORDS = {Machine Learning, Self-adaptation}
}
    Created: 2021-08-02 12:42:30     Modified: 2021-08-23 09:48:30
Feedback: ABLE Webmaster
Last modified: Sat October 12 2019 16:15:32
        BibAdmin