Performance prediction has been a key part of the neural architecture search (NAS) process, allowing to speed up NAS algorithms by avoiding resource-consuming network training. Although many performance predictors correlate well with ground truth performance, they require training data in the form of trained networks. Recently, zero-cost proxies have been proposed as an efficient method to estimate network performance without any training. However, they are still poorly understood, exhibit biases with network properties, and their performance is limited. Inspired by the drawbacks of zero-cost proxies, we propose neural graph features (GRAF), simple to compute properties of architectural graphs. GRAF offers fast and interpretable performance prediction while outperforming zero-cost proxies and other common encodings. In combination with other zero-cost proxies, GRAF outperforms most existing performance predictors at a fraction of the cost.

翻译：性能预测一直是神经架构搜索(NAS)过程中的关键组成部分，通过避免资源密集型的网络训练来加速NAS算法。尽管许多性能预测器与真实性能高度相关，但它们需要以训练好的网络形式提供训练数据。近年来，零成本代理被提出作为一种无需任何训练即可高效估计网络性能的方法。然而，这些代理方法仍未被充分理解，存在对网络特性的偏差，且性能有限。受零成本代理缺陷的启发，我们提出了神经图特征(GRAF)——一种计算架构图简单属性的方法。GRAF在提供快速且可解释的性能预测的同时，优于零成本代理及其他常见编码方式。当与其他零成本代理结合使用时，GRAF能以极低的成本超越大多数现有性能预测器。