BRP-NAS: Prediction-based NAS using GCNs

TL;DR

BRP-NAS introduces a graph convolutional network-based predictor for hardware-aware neural architecture search, significantly improving prediction accuracy and efficiency, leading to better NAS performance on benchmark datasets and diverse devices.

Contribution

The paper presents a novel GCN-based performance predictor for NAS, enhancing prediction accuracy and sample efficiency, and introduces LatBench, a latency dataset for diverse devices.

Findings

Outperforms prior NAS methods on NAS-Bench-101 and NAS-Bench-201

Improves predictor accuracy and sample efficiency

Learns useful features from DARTS search space

Abstract

Neural architecture search (NAS) enables researchers to automatically explore broad design spaces in order to improve efficiency of neural networks. This efficiency is especially important in the case of on-device deployment, where improvements in accuracy should be balanced out with computational demands of a model. In practice, performance metrics of model are computationally expensive to obtain. Previous work uses a proxy (e.g., number of operations) or a layer-wise measurement of neural network layers to estimate end-to-end hardware performance but the imprecise prediction diminishes the quality of NAS. To address this problem, we propose BRP-NAS, an efficient hardware-aware NAS enabled by an accurate performance predictor-based on graph convolutional network (GCN). What is more, we investigate prediction quality on different metrics and show that sample efficiency of the predictor-based NAS can be improved by considering binary relations of models and an iterative data selection strategy. We show that our proposed method outperforms all prior methods on NAS-Bench-101 and NAS-Bench-201, and that our predictor can consistently learn to extract useful features from the DARTS search space, improving upon the second-order baseline. Finally, to raise awareness of the fact that accurate latency estimation is not a trivial task, we release LatBench -- a latency dataset of NAS-Bench-201 models running on a broad range of devices.