Neural architecture search: Difference between revisions

Revision as of 10:21, 4 March 2022

Revision as of 10:27, 4 March 2022

Line 43:

==NAS Benchmarks==

NAS research is often very computationally expensive which makes it difficult to reproduce experiments and imposes a barrier-to-entry to researchers without access to large-scale computation<ref name=":1">Ying, C., Klein, A., Christiansen, E., Real, E., Murphy, K., & Hutter, F. (2019, May). Nas-bench-101: Towards reproducible neural architecture search. In International Conference on Machine Learning (pp. 7105-7114). PMLR.</ref>. Tabular or surrogate NAS benchmarks facilitates more efficient, effective and reproducible research on NAS.

Following is the list of the most popular NAS benchmarks:

# NAS-Bench-101 <ref name=":1" />

# NAS-Bench-101 <ref>Ying, C., Klein, A., Christiansen, E., Real, E., Murphy, K., & Hutter, F. (2019, May). Nas-bench-101: Towards reproducible neural architecture search. In International Conference on Machine Learning (pp. 7105-7114). PMLR.</ref>

# NAS-Bench-201 <ref>Dong, X., & Yang, Y. (2020). Nas-bench-201: Extending the scope of reproducible neural architecture search. arXiv preprint arXiv:2001.00326.</ref>

# NAS-Bench-1shot1<ref>Zela, A., Siems, J., & Hutter, F. (2020). Nas-bench-1shot1: Benchmarking and dissecting one-shot neural architecture search. arXiv preprint arXiv:2001.10422.</ref>