This is a collection of research and review papers of network architecture search (NAS). The Papers are sorted by time. Any suggestions and pull requests are welcome.

The sharing principle of these references here is for research. If any authors do not want their paper to be listed here, please feel free to contact Ewan Lee (Email: ewanlee [AT] yeah.net).

• Zhang, Xinbang, Zehao Huang, and Naiyan Wang. "You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization." arXiv preprint arXiv:1811.01567 (2018).
• Bender, Gabriel, et al. "Understanding and simplifying one-shot architecture search." International Conference on Machine Learning. 2018.
• Luo, Renqian, et al. "Neural Architecture Optimization." arXiv preprint arXiv:1808.07233 (2018).
• Tan, Mingxing, et al. "MnasNet: Platform-Aware Neural Architecture Search for Mobile." arXiv preprint arXiv:1807.11626 (2018). paper note code (PyTorch) code (Keras/Tensorflow)
• Liu, Hanxiao, Karen Simonyan, and Yiming Yang. "DARTS: Differentiable Architecture Search." arXiv preprint arXiv:1806.09055 (2018). paper note code
• Cai, Han, et al. "Path-Level Network Transformation for Efficient Architecture Search." arXiv preprint arXiv:1806.02639 (2018). paper note
• Pham, Hieu, et al. "Efficient Neural Architecture Search via Parameter Sharing." arXiv preprint arXiv:1802.03268 (2018). paper note code
• Zoph B, Vasudevan V, Shlens J, et al. Learning transferable architectures for scalable image recognition[J]. arXiv preprint arXiv:1707.07012, 2017, 2(6). paper note
• Cai, Han, et al. "Efficient architecture search by network transformation." AAAI, 2018. paper note code
• Real E, Moore S, Selle A, et al. Large-scale evolution of image classifiers[J]. arXiv preprint arXiv:1703.01041, 2017. paper note
• Baker B, Gupta O, Naik N, et al. Designing neural network architectures using reinforcement learning[J]. arXiv preprint arXiv:1611.02167, 2016. paper note code
• Zoph B, Le Q V. Neural architecture search with reinforcement learning[J]. arXiv preprint arXiv:1611.01578, 2016. paper note