2021/04/12 by Yu, Kaicheng, Ranftl, Rene, Salzmann, Mathieu
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)
paper · doi:10.48550/arxiv.2104.05309
Weight sharing has become a de facto standard in neural architecture search because it enables the search to be done on commodity hardware. However, recent works have empirically shown a ranking disorder between the performance of stand-alone architectures and that of the corresponding shared-weight networks. This violates the main assumption of weight-sharing NAS algorithms, thus limiting their effectiveness. We tackle this issue by proposing a regularization term that aims to maximize the correlation between the performance rankings of the shared-weight network and that of the standalone architectures using a small set of landmark architectures. We incorporate our regularization term into three different NAS algorithms and show that it consistently improves performance across algorithms, search-spaces, and tasks.