Towards Leveraging AutoML for Sustainable Deep Learning: A Multi-Objective HPO Approach on Deep Shift Neural Networks

TL;DR

This paper presents a multi-objective AutoML approach for deep shift neural networks that optimizes accuracy and energy efficiency, advancing sustainable deep learning practices.

Contribution

It introduces a novel combination of multi-fidelity HPO with multi-objective optimization tailored for DSNNs, enhancing model performance and resource efficiency.

Findings

Achieved over 80% accuracy with low computational cost

Demonstrated effectiveness of multi-fidelity multi-objective HPO

Accelerated development of sustainable AI models

Abstract

Deep Learning (DL) has advanced various fields by extracting complex patterns from large datasets. However, the computational demands of DL models pose environmental and resource challenges. Deep shift neural networks (DSNNs) offer a solution by leveraging shift operations to reduce computational complexity at inference. Following the insights from standard DNNs, we are interested in leveraging the full potential of DSNNs by means of AutoML techniques. We study the impact of hyperparameter optimization (HPO) to maximize DSNN performance while minimizing resource consumption. Since this combines multi-objective (MO) optimization with accuracy and energy consumption as potentially complementary objectives, we propose to combine state-of-the-art multi-fidelity (MF) HPO with multi-objective optimization. Experimental results demonstrate the effectiveness of our approach, resulting in models with over 80\% in accuracy and low computational cost. Overall, our method accelerates efficient model development while enabling sustainable AI applications.