Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS

By Han Shi, Renjie Pi, Hang Xu, Zhenguo Li, James T. Kwok, Tong Zhang. 2020

147 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Xiaodan Liang
2. Hang Xu
3. Xiaojun Chang
4. Bochao Wang
5. Zhenguo Li
6. Changlin Li
7. Wei Zhang
8. Lanqing Hong

Citations in the corpus

• VEGA: Towards an End-to-End Configurable AutoML Pipeline (2020, background): “Neural architecture search (NAS) (Tan & Le, 2019; Jiang et al., 2020; Shi et al., 2020), hyperparameter optimization (HPO) (Falkner et al., 2018) and data augmentation (Cubuk et al., 2018) have made great progress in many tasks.”
• BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search (2021, methodology): “proaches [43, 7, 69] and sampler-based approaches [51, 60] jointly optimize the weight of the supernet and the factors (or agent) used to choose the architecture; for their part, oneshot approaches4 [21, 14, 6, 4] optimize the supernet before performing a search with the frozen supernet weights.”