An Empirical Study of Software Architecture for Machine Learning

Specific developmental and operational characteristics of machine learning (ML) components, as well as their inherent uncertainty, demand robust engineering principles are used to ensure their quality. We aim to determine how software systems can be (re-) architected to enable robust integration of ML components. Towards this goal, we conducted a mixed-methods empirical study consisting of (i) a systematic literature review to identify the challenges and their solutions in software architecture forML, (ii) semi-structured interviews with practitioners to qualitatively complement the initial findings, and (iii) a survey to quantitatively validate the challenges and their solutions. In total, we compiled and validated twenty challenges and solutions for (re-) architecting systems with ML components. Our results indicate, for example, that traditional software architecture challenges (e.g., component coupling) also play an important role when using ML components; along new ML specific challenges (e.g., the need for continuous retraining). Moreover, the results indicate that ML heightened decision drivers, such as privacy, play a marginal role compared to traditional decision drivers, such as scalability or interoperability. Using the survey, we were able to establish a link between architectural solutions and software quality attributes; which enabled us to provide twenty architectural tactics used for satisfying individual quality requirements of systems with ML components. Altogether, the results can be interpreted as an empirical framework that supports the process of (re-) architecting software systems with ML components.