Accelerating Neural Architecture Exploration Across Modalities Using Genetic Algorithms

TL;DR

This paper demonstrates how genetic algorithms combined with lightweight objective predictors can efficiently explore neural architectures across different modalities like image classification and machine translation.

Contribution

It introduces a method that accelerates neural architecture search across multiple modalities using genetic algorithms and lightweight predictors.

Findings

Effective in both image classification and machine translation.

Reduces computational cost of architecture exploration.

Outperforms some existing NAS methods in efficiency.

Abstract

Neural architecture search (NAS), the study of automating the discovery of optimal deep neural network architectures for tasks in domains such as computer vision and natural language processing, has seen rapid growth in the machine learning research community. While there have been many recent advancements in NAS, there is still a significant focus on reducing the computational cost incurred when validating discovered architectures by making search more efficient. Evolutionary algorithms, specifically genetic algorithms, have a history of usage in NAS and continue to gain popularity versus other optimization approaches as a highly efficient way to explore the architecture objective space. Most NAS research efforts have centered around computer vision tasks and only recently have other modalities, such as the rapidly growing field of natural language processing, been investigated in depth. In this work, we show how genetic algorithms can be paired with lightly trained objective predictors in an iterative cycle to accelerate multi-objective architectural exploration in a way that works in the modalities of both machine translation and image classification.