Zero-Cost Proxies for Lightweight NAS
Keywords: NAS, AutoML, proxy, pruning, efficient
Abstract: Neural Architecture Search (NAS) is quickly becoming the standard methodology to design neural network models. However, NAS is typically compute-intensive because multiple models need to be evaluated before choosing the best one. To reduce the computational power and time needed, a proxy task is often used for evaluating each model instead of full training. In this paper, we evaluate conventional reduced-training proxies and quantify how well they preserve ranking between neural network models during search when compared with the rankings produced by final trained accuracy. We propose a series of zero-cost proxies, based on recent pruning literature, that use just a single minibatch of training data to compute a model's score. Our zero-cost proxies use 3 orders of magnitude less computation but can match and even outperform conventional proxies. For example, Spearman's rank correlation coefficient between final validation accuracy and our best zero-cost proxy on NAS-Bench-201 is 0.82, compared to 0.61 for EcoNAS (a recently proposed reduced-training proxy). Finally, we use these zero-cost proxies to enhance existing NAS search algorithms such as random search, reinforcement learning, evolutionary search and predictor-based search. For all search methodologies and across three different NAS datasets, we are able to significantly improve sample efficiency, and thereby decrease computation, by using our zero-cost proxies. For example on NAS-Bench-101, we achieved the same accuracy 4$\times$ quicker than the best previous result. Our code is made public at: https://github.com/mohsaied/zero-cost-nas.
One-sentence Summary: A single minibatch of data is used to score neural networks for NAS instead of performing full training.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Code: [ mohsaied/zero-cost-nas](https://github.com/mohsaied/zero-cost-nas) + [ 1 community implementation](https://paperswithcode.com/paper/?openreview=0cmMMy8J5q)
Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10), [CIFAR-100](https://paperswithcode.com/dataset/cifar-100), [ImageNet](https://paperswithcode.com/dataset/imagenet), [NAS-Bench-201](https://paperswithcode.com/dataset/nas-bench-201), [SVHN](https://paperswithcode.com/dataset/svhn)
Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2101.08134/code)
12 Replies
Loading