Example：10.1021/acsami.1c06204 or Chem. Rev., 2007, 107, 2411-2502
An Analysis of Super-Net Heuristics in Weight-Sharing NAS. IEEE Transactions on Pattern Analysis and Machine Intelligence (IF16.389), Pub Date : 2021-08-30, DOI: 10.1109/tpami.2021.3108480 Kaicheng Yu,Rene Ranftl,Mathieu Salzmann
Weight sharing promises to make neural architecture search (NAS) tractable even on commodity hardware. Existing methods in this space rely on a diverse set of heuristics to design and train the shared-weight backbone network, a.k.a. the super-net. Since heuristics substantially vary across different methods and have not been carefully studied, it is unclear to which extent they impact super-net training and hence the weight-sharing NAS algorithms. In this paper, we disentangle super-net training from the search algorithm, isolate 14 frequently-used training heuristics, and evaluate them over three benchmark search spaces. Our analysis uncovers that several commonly-used heuristics negatively impact the correlation between super-net and stand-alone performance, whereas simple, but often overlooked factors, such as proper hyper-parameter settings, are key to achieve strong performance. Equipped with this knowledge, we show that simple random search achieves competitive performance to complex state-of-the-art NAS algorithms when the super-net is properly trained.