TY - GEN

T1 - Towards Leveraging AutoML for Sustainable Deep Learning

T2 - A Multi-Objective HPO Approach on Deep Shift Neural Networks

AU - Hennig, Leona

AU - Tornede, Tanja

AU - Lindauer, Marius

PY - 2024/4/2

Y1 - 2024/4/2

N2 - 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.

AB - 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.

KW - cs.LG

KW - cs.AI

U2 - 10.48550/arXiv.2404.01965

DO - 10.48550/arXiv.2404.01965

M3 - Conference contribution

BT - 5th Workshop on practical ML for limited/low resource settings

ER -