# Adaptive Composition of Machine Learning as a Service (MLaaS) for IoT Environments

arXiv: https://arxiv.org/abs/2506.11054 · HTML: https://mlsanity.com/paper/2506.11054/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 32 references that are in the map.
- First posted on arXiv 22 May 2025.

## Builds on (most cited first, 8 of 8)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Measure Contribution of Participants in Federated Learning](https://mlsanity.com/paper/1909.08525/) (2019)
- [Client Selection in Federated Learning: Principles, Challenges, and Opportunities](https://mlsanity.com/paper/2211.01549/) (2022)
- [Composing Energy Services in a Crowdsourced IoT Environment](https://mlsanity.com/paper/2111.07528/) (2021)
- [Long-term IaaS Selection using Performance Discovery](https://mlsanity.com/paper/2011.00644/) (2020)
- [Multi-Criteria Client Selection and Scheduling with Fairness Guarantee for Federated Learning Service](https://mlsanity.com/paper/2312.14941/) (2023)
- [Towards Fair, Robust and Efficient Client Contribution Evaluation in Federated Learning](https://mlsanity.com/paper/2402.04409/) (2024)

## Built on by (most cited first, 3 of 3)

- [Machine Learning as a Service (MLaaS) Dataset Generator Framework for IoT Environments](https://mlsanity.com/paper/2601.12305/) (2026)
- [Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments](https://mlsanity.com/paper/2606.07685/) (2026)
- [Performance Drift Detection in Machine Learning as a Service (MLaaS) for IoT Environments](https://mlsanity.com/paper/2608.18555/) (2026)

## Abstract (arXiv)

The dynamic nature of Internet of Things (IoT) environments challenges the long-term effectiveness of Machine Learning as a Service (MLaaS) compositions. The uncertainty and variability of IoT environments lead to fluctuations in data distribution, e.g., concept drift and data heterogeneity, and evolving system requirements, e.g., scalability demands and resource limitations. This paper proposes an adaptive MLaaS composition framework to ensure a seamless, efficient, and scalable MLaaS composition. The framework integrates a service assessment model to identify underperforming MLaaS services and a candidate selection model to filter optimal replacements. An adaptive composition mechanism is developed that incrementally updates MLaaS compositions using a contextual multi-armed bandit optimization strategy. By continuously adapting to evolving IoT constraints, the approach maintains Quality of Service (QoS) while reducing the computational cost associated with recomposition from scratch. Experimental results on a real-world dataset demonstrate the efficiency of our proposed approach.