Keywords: AutoML, Neural Architecture Search, Zero-Cost Proxies
TL;DR: We create a benchmark suite for zero-cost proxies, and we use it to show how to effectively combine them to improve performance.
Abstract: Zero-cost proxies (ZC proxies) are a recent architecture performance prediction technique aiming to significantly speed up algorithms for neural architecture search (NAS). Recent work has shown that these techniques show great promise, but certain aspects, such as evaluating and exploiting their complementary strengths, are under-studied. In this work, we create NAS-Bench-Suite: we evaluate 13 ZC proxies across 28 tasks, creating by far the largest dataset (and unified codebase) for ZC proxies, enabling orders-of-magnitude faster experiments on ZC proxies, while avoiding confounding factors stemming from different implementations. To demonstrate the usefulness of NAS-Bench-Suite, we run a large-scale analysis of ZC proxies, including a bias analysis, and the first information-theoretic analysis which concludes that ZC proxies capture substantial complementary information. Motivated by these findings, we present a procedure to improve the performance of ZC proxies by reducing biases such as cell size, and we also show that incorporating all 13 ZC proxies into the surrogate models used by NAS algorithms can improve their predictive performance by up to 42%. Our code and datasets are available at https://github.com/automl/naslib/tree/zerocost.
Supplementary Material: pdf
Contribution Process Agreement: Yes
In Person Attendance: Yes
Dataset Url: https://github.com/automl/naslib/tree/zerocost
License: Apache License 2.0
Author Statement: Yes
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 7 code implementations](https://www.catalyzex.com/paper/arxiv:2210.03230/code)