Guided Evolution for Neural Architecture Search

Abstract

Neural Architecture Search (NAS) methods have been successfully applied to image tasks with excellent results. However, NAS methods are often complex and tend to converge to local minima as soon as generated architectures seem to yield good results. In this paper, we propose G-EA, a novel approach for guided evolutionary NAS. The rationale behind G-EA, is to explore the search space by generating and evaluating several architectures in each generation at initialization stage using a zero-proxy estimator, where only the highest-scoring network is trained and kept for the next generation. This evaluation at initialization stage allows continuous extraction of knowledge from the search space without increasing computation, thus allowing the search to be efficiently guided. Moreover, G-EA forces exploitation of the most performant networks by descendant generation while at the same time forcing exploration by parent mutation and by favouring younger architectures to the detriment of older ones. Experimental results demonstrate the effectiveness of the proposed method, showing that G-EA achieves state-of-the-art results in NAS-Bench-201 search space in CIFAR-10, CIFAR-100 and ImageNet16-120, with mean accuracies of 93.98%, 72.12% and 45.94% respectively.

arXiv commentPaper accepted at 35th Conference on Neural Information Processing Systems (NeurIPS) - New In ML. 9 pages, 2 figures, 1 table

References in corpus (7)

• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• DARTS: Differentiable Architecture Search
• Large-Scale Evolution of Image Classifiers
• PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
• One-Shot Neural Architecture Search via Self-Evaluated Template Network
• NAS evaluation is frustratingly hard
• How Powerful are Performance Predictors in Neural Architecture Search?