Resource-Aware Pareto-Optimal Automated Machine Learning Platform
Yao Yang, Andrew Nam, Mohamad M. Nasr‐Azadani, Teresa Tung · 2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) · 2020
In this study, we introduce a novel platform Resource-Aware AutoML (RA-AutoML) which enables flexible and generalized algorithms to build machine learning models subjected to multiple objectives, as well as resource and hardware constraints. RA-AutoML intelligently conducts Hyper-Parameter Search (HPS) as well as Neural Architecture Search (NAS) to build models optimizing predefined objectives. RA-AutoML is a versatile framework that allows user to prescribe many resource/hardware constraints along with objectives demanded by the problem or even business requirements. At its core, RA-AutoML relies on our in-house search-engine algorithm, MOBOGA, which combines a modified constraint-aware Bayesian Osptimization and Genetic Algorithm to construct Pareto optimal candidates. Our experiments on CIFAR-10 dataset shows very good accuracy compared to results obtained by state-of-art neural network models, while subjected to resource constraints in the form of model size.