Research map / Architectures and efficiency / Neural architecture search
Semi-Supervised Neural Architecture Search
Read the paperCheck 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 |
|---|---|---|---|
| add semi-supervised training with unlabeled architectures | NAO (300 queries) · NASBench-101 | test accuracy (%): 93.69 -> 93.89 | Helped |
| add semi-supervised training with unlabeled architectures | NAO (2000 queries) · NASBench-101 | test accuracy (%): 93.90 -> 94.02 | Helped |
| add semi-supervised predictor to regularized evolution | RE (2000 queries) · NASBench-101 | test accuracy (%): 93.96 -> 94.03 | Helped |
| increase number of unlabeled architectures M from 0 to 10000 (ablation) | SemiNAS, N=100 · NASBench-101 | test accuracy | Helped |
| up-sample labeled architectures (ratio 1 to 100) (ablation) | SemiNAS, N=100, M=10000 · NASBench-101 | test accuracy | Mixed |
| use SemiNAS instead of NAO | NAO · ImageNet 600M FLOPS | top-1 error (%): 24.5 -> 23.5 | Helped |
| use SemiNAS instead of NAO | NAO · LJSpeech low-resource | intelligibility rate (%): 94 -> 97 | Helped |
| use SemiNAS instead of NAO | NAO · LJSpeech robustness | sentence error rate (%): 19 -> 15 | Helped |
| use SemiNAS searched architecture instead of human-designed Transformer TTS | Transformer TTS · LJSpeech low-resource | intelligibility rate (%): 88 -> 97 | Helped |
| use SemiNAS searched architecture instead of Transformer TTS | Transformer TTS · LJSpeech robustness | sentence error rate (%): 22 -> 15 | Helped |
Closest papers by meaning
- A Semi-Supervised Assessor of Neural Architectures (CVPR 2020 · similarity 0.92)
- Generic Neural Architecture Search via Regression (NeurIPS 2021 · similarity 0.91)
- Stronger NAS with Weaker Predictors (NeurIPS 2021 · similarity 0.91)
- NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search (ICLR 2020 · similarity 0.91)
- NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks (NeurIPS 2022 · similarity 0.90)
- Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions (AAAI 2025 · similarity 0.89)
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.