# Adapting Software Architectures to Machine Learning Challenges

arXiv: https://arxiv.org/abs/2105.12422 · HTML: https://mlsanity.com/paper/2105.12422/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2021.

## Built on by (most cited first, 11 of 11)

- [A Meta-Summary of Challenges in Building Products with ML Components -- Collecting Experiences from 4758+ Practitioners](https://mlsanity.com/paper/2304.00078/) (2023)
- [Towards more Practical Threat Models in Artificial Intelligence Security](https://mlsanity.com/paper/2311.09994/) (2023)
- [Design Patterns for AI-based Systems: A Multivocal Literature Review and Pattern Repository](https://mlsanity.com/paper/2303.13173/) (2023)
- [Generating a Low-code Complete Workflow via Task Decomposition and RAG](https://mlsanity.com/paper/2412.00239/) (2024)
- [How Do Model Export Formats Impact the Development of ML-Enabled Systems? A Case Study on Model Integration](https://mlsanity.com/paper/2502.00429/) (2025)
- [Understanding the Complexity and Its Impact on Testing in ML-Enabled Systems](https://mlsanity.com/paper/2301.03837/) (2023)
- [A Case Study on AI Engineering Practices: Developing an Autonomous Stock Trading System](https://mlsanity.com/paper/2303.13216/) (2023)
- [Good Tools are Half the Work: Tool Usage in Deep Learning Projects](https://mlsanity.com/paper/2310.19124/) (2023)
- [REMEDI: Relative Feature Enhanced Meta-Learning with Distillation for Imbalanced Prediction](https://mlsanity.com/paper/2505.07245/) (2025)
- [Beyond Models: Reflections on Engineering AI-enabled Systems in a Project-Based Course](https://mlsanity.com/paper/2606.16842/) (2026)
- [Software Engineering for AI-driven Building Operation](https://mlsanity.com/paper/2608.16237/) (2026)

## Abstract (arXiv)

Unique developmental and operational characteristics of 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 for ML, (ii) semi-structured interviews with practitioners to qualitatively complement the initial findings and (iii) a survey to quantitatively validate the challenges and their solutions. 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 with 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. 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 to satisfy individual quality requirements of systems with ML components. Altogether, the results of the study can be interpreted as an empirical framework that supports the process of (re-) architecting software systems with ML components.