Surprisingly Strong Performance Prediction with Neural Graph Features
This work addresses the need for efficient performance prediction in neural architecture search, offering a more accurate and cost-effective method than current approaches.
The paper tackles the problem of predicting neural network performance without training data, proposing neural graph features (GRAF) that outperform existing zero-cost proxies and other encodings while being fast and interpretable.
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.