PEng4NN: An Accurate Performance Estimation Engine for Efficient Automated Neural Network Architecture Search

TL;DR

PEng4NN is a performance estimation engine that accelerates neural architecture search by early accuracy prediction, significantly reducing training time while maintaining high model performance across diverse datasets.

Contribution

It introduces a novel early accuracy prediction strategy integrated into NAS, enabling substantial training epoch reduction without sacrificing model quality.

Findings

Achieves 61% to 82% reduction in training epochs.

Increases NAS throughput by 2.5 to 5 times.

Maintains comparable accuracy distributions between predicted and ground truth best models.

Abstract

Neural network (NN) models are increasingly used in scientific simulations, AI, and other high performance computing (HPC) fields to extract knowledge from datasets. Each dataset requires tailored NN model architecture, but designing structures by hand is a time-consuming and error-prone process. Neural architecture search (NAS) automates the design of NN architectures. NAS attempts to find well-performing NN models for specialized datsets, where performance is measured by key metrics that capture the NN capabilities (e.g., accuracy of classification of samples in a dataset). Existing NAS methods are resource intensive, especially when searching for highly accurate models for larger and larger datasets. To address this problem, we propose a performance estimation strategy that reduces the resources for training NNs and increases NAS throughput without jeopardizing accuracy. We implement our strategy via an engine called PEng4NN that plugs into existing NAS methods; in doing so, PEng4NN predicts the final accuracy of NNs early in the training process, informs the NAS of NN performance, and thus enables the NAS to terminate training NNs early. We assess our engine on three diverse datasets (i.e., CIFAR-100, Fashion MNIST, and SVHN). By reducing the training epochs needed, our engine achieves substantial throughput gain; on average, our engine saves 61% to 82% of training epochs, increasing throughput by a factor of 2.5 to 5 compared to a state-of-the-art NAS method. We achieve this gain without compromising accuracy, as we demonstrate with two key outcomes. First, across all our tests, between 74% and 97% of the ground truth best models lie in our set of predicted best models. Second, the accuracy distributions of the ground truth best models and our predicted best models are comparable, with the mean accuracy values differing by at most .7 percentage points across all tests.