MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning

TL;DR

MONAS is a multi-objective neural architecture search framework that balances prediction accuracy with other constraints like power consumption, producing efficient models suitable for limited-resource environments.

Contribution

It introduces a reinforcement learning-based method for multi-objective neural architecture search considering both accuracy and resource constraints.

Findings

Models found by MONAS achieve comparable or better accuracy than state-of-the-art.

MONAS effectively balances accuracy and power consumption.

The framework produces architectures suitable for deployment in resource-limited environments.

Abstract

Recent studies on neural architecture search have shown that automatically designed neural networks perform as good as expert-crafted architectures. While most existing works aim at finding architectures that optimize the prediction accuracy, these architectures may have complexity and is therefore not suitable being deployed on certain computing environment (e.g., with limited power budgets). We propose MONAS, a framework for Multi-Objective Neural Architectural Search that employs reward functions considering both prediction accuracy and other important objectives (e.g., power consumption) when searching for neural network architectures. Experimental results showed that, compared to the state-ofthe-arts, models found by MONAS achieve comparable or better classification accuracy on computer vision applications, while satisfying the additional objectives such as peak power.