Scalable Reinforcement-Learning-Based Neural Architecture Search for Cancer Deep Learning Research

TL;DR

This paper presents a scalable reinforcement learning method to automate neural architecture search for cancer data, resulting in efficient models with fewer parameters and comparable or better accuracy, demonstrated on high-performance computing resources.

Contribution

It introduces a reinforcement-learning-based neural architecture search tailored for cancer data, enabling automated, scalable, and efficient deep learning model development.

Findings

Models with fewer trainable parameters

Shorter training times

Achieved comparable or higher accuracy

Abstract

Cancer is a complex disease, the understanding and treatment of which are being aided through increases in the volume of collected data and in the scale of deployed computing power. Consequently, there is a growing need for the development of data-driven and, in particular, deep learning methods for various tasks such as cancer diagnosis, detection, prognosis, and prediction. Despite recent successes, however, designing high-performing deep learning models for nonimage and nontext cancer data is a time-consuming, trial-and-error, manual task that requires both cancer domain and deep learning expertise. To that end, we develop a reinforcement-learning-based neural architecture search to automate deep-learning-based predictive model development for a class of representative cancer data. We develop custom building blocks that allow domain experts to incorporate the cancer-data-specific characteristics. We show that our approach discovers deep neural network architectures that have significantly fewer trainable parameters, shorter training time, and accuracy similar to or higher than those of manually designed architectures. We study and demonstrate the scalability of our approach on up to 1,024 Intel Knights Landing nodes of the Theta supercomputer at the Argonne Leadership Computing Facility.