Hardware Aware Ensemble Selection for Balancing Predictive Accuracy and Cost

TL;DR

This paper presents a hardware-aware ensemble selection method in AutoML that balances predictive accuracy with inference time, enabling more efficient deployment of models on various hardware.

Contribution

It introduces a novel ensemble selection approach that incorporates hardware efficiency metrics, allowing for Pareto-optimal trade-offs between accuracy and inference cost.

Findings

Achieves competitive accuracy while reducing inference time.

Provides a Pareto front of ensembles balancing accuracy and efficiency.

Demonstrates effectiveness on 83 classification datasets.

Abstract

Automated Machine Learning (AutoML) significantly simplifies the deployment of machine learning models by automating tasks from data preprocessing to model selection to ensembling. AutoML systems for tabular data often employ post hoc ensembling, where multiple models are combined to improve predictive accuracy. This typically results in longer inference times, a major limitation in practical deployments. Addressing this, we introduce a hardware-aware ensemble selection approach that integrates inference time into post hoc ensembling. By leveraging an existing framework for ensemble selection with quality diversity optimization, our method evaluates ensemble candidates for their predictive accuracy and hardware efficiency. This dual focus allows for a balanced consideration of accuracy and operational efficiency. Thus, our approach enables practitioners to choose from a Pareto front of accurate and efficient ensembles. Our evaluation using 83 classification datasets shows that our approach sustains competitive accuracy and can significantly improve ensembles' operational efficiency. The results of this study provide a foundation for extending these principles to additional hardware constraints, setting the stage for the development of more resource-efficient AutoML systems.