GENNAPE: Towards Generalized Neural Architecture Performance Estimators

TL;DR

GENNAPE is a novel neural architecture performance estimator that generalizes across unseen architectures using contrastive learning and fuzzy clustering, outperforming existing predictors in transferability and aiding efficient neural architecture search.

Contribution

It introduces a generalized, pretrained performance estimator for neural networks that effectively models unseen architectures through graph encoding, contrastive pretraining, and ensemble predictors.

Findings

GENNAPE pretrained on NAS-Bench-101 transfers well to other benchmarks.

It accurately identifies high-performance architectures in new benchmarks.

It improves architecture search results by balancing accuracy and FLOPs.

Abstract

Predicting neural architecture performance is a challenging task and is crucial to neural architecture design and search. Existing approaches either rely on neural performance predictors which are limited to modeling architectures in a predefined design space involving specific sets of operators and connection rules, and cannot generalize to unseen architectures, or resort to zero-cost proxies which are not always accurate. In this paper, we propose GENNAPE, a Generalized Neural Architecture Performance Estimator, which is pretrained on open neural architecture benchmarks, and aims to generalize to completely unseen architectures through combined innovations in network representation, contrastive pretraining, and fuzzy clustering-based predictor ensemble. Specifically, GENNAPE represents a given neural network as a Computation Graph (CG) of atomic operations which can model an arbitrary architecture. It first learns a graph encoder via Contrastive Learning to encourage network separation by topological features, and then trains multiple predictor heads, which are soft-aggregated according to the fuzzy membership of a neural network. Experiments show that GENNAPE pretrained on NAS-Bench-101 can achieve superior transferability to 5 different public neural network benchmarks, including NAS-Bench-201, NAS-Bench-301, MobileNet and ResNet families under no or minimum fine-tuning. We further introduce 3 challenging newly labelled neural network benchmarks: HiAML, Inception and Two-Path, which can concentrate in narrow accuracy ranges. Extensive experiments show that GENNAPE can correctly discern high-performance architectures in these families. Finally, when paired with a search algorithm, GENNAPE can find architectures that improve accuracy while reducing FLOPs on three families.