# Continuous Management of Machine Learning-Based Application Behavior

arXiv: https://arxiv.org/abs/2311.12686 · HTML: https://mlsanity.com/paper/2311.12686/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 59 references that are in the map.
- First posted on arXiv 21 Nov 2023.

## Builds on (most cited first, 15 of 15)

- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Deep Partition Aggregation: Provable Defense against General Poisoning Attacks](https://mlsanity.com/paper/2006.14768/) (2020)
- [Intrinsic Certified Robustness of Bagging against Data Poisoning Attacks](https://mlsanity.com/paper/2008.04495/) (2020)
- [FAHT: An Adaptive Fairness-aware Decision Tree Classifier](https://mlsanity.com/paper/1907.07237/) (2019)
- [Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation](https://mlsanity.com/paper/2202.02628/) (2022)
- [FARF: A Fair and Adaptive Random Forests Classifier](https://mlsanity.com/paper/2108.07403/) (2021)
- [META-DES: A Dynamic Ensemble Selection Framework using Meta-Learning](https://mlsanity.com/paper/1810.01270/) (2018)
- [On Collective Robustness of Bagging Against Data Poisoning](https://mlsanity.com/paper/2205.13176/) (2022)
- [Fairness-enhancing interventions in stream classification](https://mlsanity.com/paper/1907.07223/) (2019)
- [Online Fairness-Aware Learning with Imbalanced Data Streams](https://mlsanity.com/paper/2108.06231/) (2021)
- [Trust-Based Cloud Machine Learning Model Selection For Industrial IoT and Smart City Services](https://mlsanity.com/paper/2008.05042/) (2020)
- [On the Robustness of Random Forest Against Untargeted Data Poisoning: An Ensemble-Based Approach](https://mlsanity.com/paper/2209.14013/) (2022)
- [Rethinking Certification for Trustworthy Machine Learning-Based Applications](https://mlsanity.com/paper/2305.16822/) (2023)

## Abstract (arXiv)

Modern applications are increasingly driven by Machine Learning (ML) models whose non-deterministic behavior is affecting the entire application life cycle from design to operation. The pervasive adoption of ML is urgently calling for approaches that guarantee a stable non-functional behavior of ML-based applications over time and across model changes. To this aim, non-functional properties of ML models, such as privacy, confidentiality, fairness, and explainability, must be monitored, verified, and maintained. Existing approaches mostly focus on i) implementing solutions for classifier selection according to the functional behavior of ML models, ii) finding new algorithmic solutions, such as continuous re-training. In this paper, we propose a multi-model approach that aims to guarantee a stable non-functional behavior of ML-based applications. An architectural and methodological approach is provided to compare multiple ML models showing similar non-functional properties and select the model supporting stable non-functional behavior over time according to (dynamic and unpredictable) contextual changes. Our approach goes beyond the state of the art by providing a solution that continuously guarantees a stable non-functional behavior of ML-based applications, is ML algorithm-agnostic, and is driven by non-functional properties assessed on the ML models themselves. It consists of a two-step process working during application operation, where model assessment verifies non-functional properties of ML models trained and selected at development time, and model substitution guarantees continuous and stable support of non-functional properties. We experimentally evaluate our solution in a real-world scenario focusing on non-functional property fairness.