# Feature Interactions on Steroids: On the Composition of ML Models

arXiv: https://arxiv.org/abs/2105.06449 · HTML: https://mlsanity.com/paper/2105.06449/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 13 May 2021.

## Builds on (most cited first, 6 of 6)

- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [From Captions to Visual Concepts and Back](https://mlsanity.com/paper/1411.4952/) (2014)
- [On Human Intellect and Machine Failures: Troubleshooting Integrative Machine Learning Systems](https://mlsanity.com/paper/1611.08309/) (2016)
- [Toward user-centric feature composition for the Internet of Things](https://mlsanity.com/paper/1510.06714/) (2015)

## Built on by (most cited first, 4 of 4)

- [What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts](https://mlsanity.com/paper/2505.13360/) (2025)
- [A Large-Scale Study of Model Integration in ML-Enabled Software Systems](https://mlsanity.com/paper/2408.06226/) (2024)
- [The More the Merrier? Navigating Accuracy vs. Energy Efficiency Design Trade-Offs in Ensemble Learning Systems](https://mlsanity.com/paper/2407.02914/) (2024)
- [Understanding the Complexity and Its Impact on Testing in ML-Enabled Systems](https://mlsanity.com/paper/2301.03837/) (2023)

## Abstract (arXiv)

The lack of specifications is a key difference between traditional software engineering and machine learning. We discuss how it drastically impacts how we think about divide-and-conquer approaches to system design, and how it impacts reuse, testing and debugging activities. Traditionally, specifications provide a cornerstone for compositional reasoning and for the divide-and-conquer strategy of how we build large and complex systems from components, but those are hard to come by for machine-learned components. While the lack of specification seems like a fundamental new problem at first sight, in fact software engineers routinely deal with iffy specifications in practice: we face weak specifications, wrong specifications, and unanticipated interactions among components and their specifications. Machine learning may push us further, but the problems are not fundamentally new. Rethinking machine-learning model composition from the perspective of the feature interaction problem, we may even teach us a thing or two on how to move forward, including the importance of integration testing, of requirements engineering, and of design.