Research map / Architectures and efficiency / Neural architecture search
Improving One-Shot NAS by Suppressing the Posterior Fading
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| progressively shrink the search space while updating a partial-model pool (ablation) | One-Shot NAS training and search · ImageNet | top-1 accuracy: 77.1% -> 78.1% | Helped |
| replace PC-NAS search with Evolution Algorithm search (ablation) | One-Shot-trained large-space supergraph · ImageNet | top-1 accuracy: 77.1% -> 75.9% | Hurt |
| increase warm-up epochs from 100 to 150 (ablation) | PC-NAS-S · ImageNet | top-1 accuracy: less than 0.1% | No clear effect |
| increase partial-model pool size (ablation) | PC-NAS-S · ImageNet | top-1 accuracy | Helped |
| increase evaluation number (ablation) | PC-NAS-S · ImageNet | top-1 accuracy | Helped |
| further increase partial-model pool size or evaluation number beyond the tested choices (ablation) | PC-NAS-S · ImageNet | top-1 accuracy | No clear effect |
Closest papers by meaning
- Posterior-Guided Neural Architecture Search (AAAI 2020 · similarity 0.92)
- Overcoming Multi-Model Forgetting in One-Shot NAS With Diversity Maximization (CVPR 2020 · similarity 0.91)
- Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS (NeurIPS 2020 · similarity 0.90)
- Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions (AAAI 2025 · similarity 0.88)
- Subnet-Aware Dynamic Supernet Training for Neural Architecture Search (CVPR 2025 · similarity 0.87)
- HEP-NAS: Towards Efficient Few-shot Neural Architecture Search via Hierarchical Edge Partitioning (AAAI 2025 · similarity 0.87)
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.