Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2022
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2210.17180 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911906655109120 |
|---|---|
| author | Chen, Yaofo Guo, Yong Liao, Daihai Lv, Fanbing Song, Hengjie Kwok, James Tin-Yau Tan, Mingkui |
| author_facet | Chen, Yaofo Guo, Yong Liao, Daihai Lv, Fanbing Song, Hengjie Kwok, James Tin-Yau Tan, Mingkui |
| contents | Neural Architecture Search (NAS) aims to automatically find effective architectures within a predefined search space. However, the search space is often extremely large. As a result, directly searching in such a large search space is non-trivial and also very time-consuming. To address the above issues, in each search step, we seek to limit the search space to a small but effective subspace to boost both the search performance and search efficiency. To this end, we propose a novel Neural Architecture Search method via Dominative Subspace Mining (DSM-NAS) that finds promising architectures in automatically mined subspaces. Specifically, we first perform a global search, i.e ., dominative subspace mining, to find a good subspace from a set of candidates. Then, we perform a local search within the mined subspace to find effective architectures. More critically, we further boost search performance by taking well-designed/ searched architectures to initialize candidate subspaces. Experimental results demonstrate that DSM-NAS not only reduces the search cost but also discovers better architectures than state-of-the-art methods in various benchmark search spaces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2210_17180 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Automated Dominative Subspace Mining for Efficient Neural Architecture Search Chen, Yaofo Guo, Yong Liao, Daihai Lv, Fanbing Song, Hengjie Kwok, James Tin-Yau Tan, Mingkui Computer Vision and Pattern Recognition Neural Architecture Search (NAS) aims to automatically find effective architectures within a predefined search space. However, the search space is often extremely large. As a result, directly searching in such a large search space is non-trivial and also very time-consuming. To address the above issues, in each search step, we seek to limit the search space to a small but effective subspace to boost both the search performance and search efficiency. To this end, we propose a novel Neural Architecture Search method via Dominative Subspace Mining (DSM-NAS) that finds promising architectures in automatically mined subspaces. Specifically, we first perform a global search, i.e ., dominative subspace mining, to find a good subspace from a set of candidates. Then, we perform a local search within the mined subspace to find effective architectures. More critically, we further boost search performance by taking well-designed/ searched architectures to initialize candidate subspaces. Experimental results demonstrate that DSM-NAS not only reduces the search cost but also discovers better architectures than state-of-the-art methods in various benchmark search spaces. |
| title | Automated Dominative Subspace Mining for Efficient Neural Architecture Search |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2210.17180 |