A General-Purpose Transferable Predictor for Neural Architecture Search

TL;DR

This paper introduces a universal neural performance predictor for NAS that leverages graph representations and contrastive learning to transfer across search spaces, outperforming existing methods and enabling effective architecture search.

Contribution

We propose a general-purpose NAS predictor using computation graph representations and contrastive learning, enabling transferability across diverse search spaces.

Findings

Achieves high SRCC on NAS-Bench-101, 201, and 301.

Outperforms several zero-cost proxies in predicting performance.

Successfully finds high-accuracy architectures, including MobileNetV3 on ImageNet.

Abstract

Understanding and modelling the performance of neural architectures is key to Neural Architecture Search (NAS). Performance predictors have seen widespread use in low-cost NAS and achieve high ranking correlations between predicted and ground truth performance in several NAS benchmarks. However, existing predictors are often designed based on network encodings specific to a predefined search space and are therefore not generalizable to other search spaces or new architecture families. In this paper, we propose a general-purpose neural predictor for NAS that can transfer across search spaces, by representing any given candidate Convolutional Neural Network (CNN) with a Computation Graph (CG) that consists of primitive operators. We further combine our CG network representation with Contrastive Learning (CL) and propose a graph representation learning procedure that leverages the structural information of unlabeled architectures from multiple families to train CG embeddings for our performance predictor. Experimental results on NAS-Bench-101, 201 and 301 demonstrate the efficacy of our scheme as we achieve strong positive Spearman Rank Correlation Coefficient (SRCC) on every search space, outperforming several Zero-Cost Proxies, including Synflow and Jacov, which are also generalizable predictors across search spaces. Moreover, when using our proposed general-purpose predictor in an evolutionary neural architecture search algorithm, we can find high-performance architectures on NAS-Bench-101 and find a MobileNetV3 architecture that attains 79.2% top-1 accuracy on ImageNet.