English

Learning to Learn in Collective Adaptive Systems: Mining Design Patterns for Data-driven Reasoning

Software Engineering 2020-08-11 v1

Abstract

Engineering collective adaptive systems (CAS) with learning capabilities is a challenging task due to their multi-dimensional and complex design space. Data-driven approaches for CAS design could introduce new insights enabling system engineers to manage the CAS complexity more cost-effectively at the design-phase. This paper introduces a systematic approach to reason about design choices and patterns of learning-based CAS. Using data from a systematic literature review, reasoning is performed with a novel application of data-driven methodologies such as clustering, multiple correspondence analysis and decision trees. The reasoning based on past experience as well as supporting novel and innovative design choices are demonstrated.

Keywords

Cite

@article{arxiv.2008.03995,
  title  = {Learning to Learn in Collective Adaptive Systems: Mining Design Patterns for Data-driven Reasoning},
  author = {Mirko D'Angelo and Sona Ghahremani and Simos Gerasimou and Johannes Grohmann and Ingrid Nunes and Sven Tomforde and Evangelos Pournaras},
  journal= {arXiv preprint arXiv:2008.03995},
  year   = {2020}
}
R2 v1 2026-06-23T17:44:40.878Z