MixPath: A Unified Approach for One-shot Neural Architecture Search

The expressiveness of search space is a key concern in neural architecture search (NAS). Previous block-level approaches mainly focus on searching networks that chain one operation after another. Incorporating multi-path search space with the one-shot doctrine remains untackled. In this paper, we investigate the supernet behavior under the multi-path setting, which we call MixPath. For a sampled training, simply switching multiple paths on and off incurs severe feature inconsistency which deteriorates the convergence. To remedy this effect, we employ what we term as \emph{shadow batch normalizations} (SBN) to follow various path patterns. Experiments performed on CIFAR-10 show that our approach is effective regardless of the number of allowable paths. Further experiments are conducted on ImageNet to have a fair comparison with the latest NAS methods. Our code will be available https://github.com/xiaomi-automl/MixPath.git .