Towards Self-Adaptive Machine Learning-Enabled Systems Through QoS-Aware Model Switching

TL;DR

This paper introduces AdaMLS, a self-adaptive approach for machine learning-enabled systems that uses lightweight unsupervised learning to dynamically switch models, improving QoS amidst run-time uncertainties.

Contribution

It proposes AdaMLS, a novel self-adaptation method extending the MAPE-K loop with dynamic model switching to manage uncertainties in MLS.

Findings

AdaMLS outperforms naive models in QoS guarantees.

Lightweight unsupervised learning enables effective model switching.

Prototype demonstrates improved system performance in dynamic environments.

Abstract

Machine Learning (ML), particularly deep learning, has seen vast advancements, leading to the rise of Machine Learning-Enabled Systems (MLS). However, numerous software engineering challenges persist in propelling these MLS into production, largely due to various run-time uncertainties that impact the overall Quality of Service (QoS). These uncertainties emanate from ML models, software components, and environmental factors. Self-adaptation techniques present potential in managing run-time uncertainties, but their application in MLS remains largely unexplored. As a solution, we propose the concept of a Machine Learning Model Balancer, focusing on managing uncertainties related to ML models by using multiple models. Subsequently, we introduce AdaMLS, a novel self-adaptation approach that leverages this concept and extends the traditional MAPE-K loop for continuous MLS adaptation. AdaMLS employs lightweight unsupervised learning for dynamic model switching, thereby ensuring consistent QoS. Through a self-adaptive object detection system prototype, we demonstrate AdaMLS's effectiveness in balancing system and model performance. Preliminary results suggest AdaMLS surpasses naive and single state-of-the-art models in QoS guarantees, heralding the advancement towards self-adaptive MLS with optimal QoS in dynamic environments.