Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search
Autor: | Yu, Kaicheng, Ranftl, Rene, Salzmann, Mathieu |
---|---|
Rok vydání: | 2021 |
Předmět: | |
Druh dokumentu: | Working Paper |
Popis: | 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. Comment: Accepted to CVPR 2021 |
Databáze: | arXiv |
Externí odkaz: |