# Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search Source: [Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search]() Collection index: [llms.txt]() Data updated: 2026-01-04T05:02:37.918Z Authors: Kaicheng Yu, Rene Ranftl, Mathieu Salzmann Published: 2021-04-12T09:32:33.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on CIFAR-10 DARTS search space (test)](): Image Classification; CIFAR-10 DARTS search space (test); Best Test Error: not recorded. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()