Research map / Architectures and efficiency / Neural architecture search
CLOSE: Curriculum Learning on the Sharing Extent towards Better One-Shot NAS
Zixuan Zhou, Xuefei Ning, Yi Cai, Jiashu Han, Yiping Deng, Yuhan Dong, Huazhong Yang, Yu Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add WIT and SRT together (ablation) | CLOSE · NAS-Bench-301 | Kendall's Tau: 0.1104 -> 0.5168 | Improved |
| add WIT and SRT together (ablation) | CLOSE · NDS ResNet | Kendall's Tau: 0.6339 -> 0.6786 | Improved |
| add WIT alone (without SRT) (ablation) | CLOSE · NAS-Bench-301 | Kendall's Tau: 0.1104 -> 0.1047 | No clear effect |
| add SRT alone (without WIT) (ablation) | CLOSE · NAS-Bench-301 | Kendall's Tau: 0.1104 -> 0.2004 | Improved |
| use learnable GATE instead of random GLOW assignment (ablation) | CLOSE · NAS-Bench-201 | Kendall's Tau: 0.3627 -> 0.7622 | Improved |
| use learnable GATE instead of random GLOW assignment (ablation) | CLOSE · NAS-Bench-301 | Kendall's Tau: 0.2236 -> 0.5168 | Improved |
| gradually add GLOW blocks instead of fixed 2 blocks (ablation) | CLOSE · NAS-Bench-301 | Kendall's Tau: 0.4533 -> 0.5168 | Improved |
| gradually add GLOW blocks instead of fixed 2 blocks (ablation) | CLOSE · NAS-Bench-201 | Kendall's Tau: 0.7320 -> 0.7622 | Improved |
| add all blocks instead of stopping after 1 (ablation) | CLOSE · NAS-Bench-301 | Kendall's Tau: 0.3990 -> 0.5168 | Improved |
| use more curriculums (ablation) | CLOSE · NAS-Bench-301 and NDS ResNet | Kendall's Tau | Improved |
| use CLOSENet instead of vanilla supernet (ablation) | one-shot supernet · four NAS benchmarks | Kendall's Tau | Improved |
| use CLOSE-S (two-stage sharing, no GATE) instead of vanilla supernet (ablation) | one-shot supernet · NAS-Bench-201/301 | Kendall's Tau | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DARTS — DARTS-: Robustly Stepping out of Performance Collapse Without Indicators (ICLR 2021) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- One-Shot Neural Architecture Search: Maximising Diversity to Overcome Catastrophic Forgetting (TPAMI 2020 · similarity 0.91)
- Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions (AAAI 2025 · similarity 0.91)
- Few-Shot Neural Architecture Search (ICML 2021 · similarity 0.91)
- Subnet-Aware Dynamic Supernet Training for Neural Architecture Search (CVPR 2025 · similarity 0.90)
- HEP-NAS: Towards Efficient Few-shot Neural Architecture Search via Hierarchical Edge Partitioning (AAAI 2025 · similarity 0.90)
- Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach (CVPR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
