Efficient Sample-based Neural Architecture Search with Learnable Predictor

By Han Shi, Renjie Pi, Hang Xu, Zhenguo Li, James T. Kwok, Tong Zhang. 2019

14 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. Julien N. Siems
2. Arber Zela
3. Willie Neiswanger
4. Lucas Zimmer
5. Colin White
6. Frank Hutter
7. Jovita Lukasik
8. Xuanyi Dong

Citations in the corpus

• BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search (2019, methodology): “The two best-performing neural predictors are an ensemble of GCNs, and an ensemble of feedforward neural networks with the path encoding, with the latter having a slight edge.”
• NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search (2020, background): “Shi et al. (2019) and Wen et al. (2019) trained a Graph Convolutional Network (GCN) on a subset of NAS-Bench-101 (Ying et al., 2019) showing its effectiveness in predicting the performance of unseen architectures.”