Research map / Architectures and efficiency / Neural architecture search
Neural Architecture Search With Random Labels
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 |
|---|---|---|---|
| Use random labels and angle-based fitness instead of ground-truth labels and validation accuracy | NAS-Bench-201 search · ImageNet16-120 | test accuracy: 40.80 -> 43.70 | Helped |
| Use angle fitness rather than validation-accuracy fitness with random-label training (ablation) | NAS-Bench-201 search · CIFAR-10 | test accuracy: 80.60 -> 93.45 | Helped |
| Use angle fitness rather than validation-accuracy fitness with random-label training (ablation) | NAS-Bench-201 search · CIFAR-100 | test accuracy: 52.84 -> 70.71 | Helped |
| Use angle fitness rather than validation-accuracy fitness with random-label training (ablation) | NAS-Bench-201 search · ImageNet16-120 | test accuracy: 28.37 -> 43.70 | Helped |
| Shuffle ground-truth labels once before training rather than uniformly sample fixed random labels (ablation) | RLNAS · ImageNet16-120 | test accuracy: 43.70±1.25 -> 43.81±1.12 | No clear effect |
| Resample random labels in each iteration rather than assign fixed random labels once (ablation) | RLNAS · ImageNet16-120 | test accuracy: 43.70±1.25 -> 27.51±1.04 | Hurt |
| Shuffle ground-truth labels in every training iteration rather than assign fixed random labels once (ablation) | RLNAS · CIFAR-100 | test accuracy: 70.71±0.36 -> 61.59±6.57 | Hurt |
| Search the DARTS architecture directly on ImageNet rather than search on CIFAR-10 and transfer | RLNAS · ImageNet | Top-1 accuracy: 75.6 -> 75.9 | Helped |
| Search with random labels rather than UnNAS jigsaw pretext labels | DARTS search space · ImageNet | Top-1 accuracy: 76.2 -> 76.7 | Helped |
Closest papers by meaning
- Evaluating The Search Phase of Neural Architecture Search (ICLR 2020 · similarity 0.91)
- Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions (AAAI 2025 · similarity 0.91)
- Understanding Architectures Learnt by Cell-based Neural Architecture Search (ICLR 2020 · similarity 0.91)
- Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective (ICLR 2021 · similarity 0.90)
- Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach (CVPR 2024 · similarity 0.89)
- einspace: Searching for Neural Architectures from Fundamental Operations (NeurIPS 2024 · 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.