Accelerating Neural Architecture Exploration Across Modalities Using Genetic Algorithms
This work addresses the computational bottleneck in NAS for researchers and practitioners, but it is incremental as it builds on existing genetic algorithm approaches.
The paper tackled the problem of reducing computational cost in neural architecture search (NAS) by proposing a method that pairs genetic algorithms with lightly trained objective predictors to accelerate multi-objective architectural exploration, achieving results in both machine translation and image classification modalities.
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.