Research map / Architectures and efficiency / Neural architecture search
Performance-Aware Mutual Knowledge Distillation for Improving Neural Architecture Search
Pengtao Xie, Xuefeng Du
Check 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 performance-aware mutual distillation | Darts1st · CIFAR-100 | test error (%): 20.52±0.31 -> 17.61±0.16 | Improved |
| Add performance-aware mutual distillation | Darts1st · CIFAR-10 | test error (%): 3.00±0.14 -> 2.38±0.03 | Improved |
| Add performance-aware mutual distillation | Pdarts · CIFAR-100 | test error (%): 17.43±0.15 -> 15.82±0.11 | Improved |
| Add performance-aware mutual distillation | Pcdarts · CIFAR-10 | test error (%): 2.57±0.07 -> 2.46±0.05 | Improved |
| Add performance-aware mutual distillation | Pcdarts · CIFAR-100 | test error (%): 17.01±0.06 -> 15.89±0.07 | Improved |
| Add performance-aware mutual distillation | Prdarts · CIFAR-100 | test error (%): 16.48±0.06 -> 16.05±0.04 | Improved |
| Add PAMKD | Pcdarts · ImageNet | top-1 test error (%): 24.2 -> 22.8 | Improved |
| Add PAMKD | Pcdarts · ImageNet | top-5 test error (%): 7.3 -> 6.4 | Improved |
| Add PAMKD | Drnas · NAS-Bench-201 CIFAR-10 | test accuracy: 94.36±0.00 -> 94.83±0.07 | Improved |
| Add PAMKD | Drnas · NAS-Bench-201 ImageNet-16-120 | test accuracy: 46.34±0.00 -> 47.59±0.09 | Improved |
| Use performance scrutiny instead of unrestricted MKD (ablation) | Darts1st mutual distillation · CIFAR-100 | test error (%): 18.25±0.10 -> 17.61±0.16 | Improved |
| Use performance scrutiny instead of unrestricted KDCL (ablation) | Darts1st mutual distillation · CIFAR-10 | test error (%): 2.68±0.06 -> 2.38±0.03 | 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.
- Drnas — DrNAS: Dirichlet Neural Architecture Search (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
- Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets (ICLR 2023 · similarity 0.90)
- Search to Distill: Pearls Are Everywhere but Not the Eyes (CVPR 2020 · similarity 0.90)
- Towards Oracle Knowledge Distillation with Neural Architecture Search (AAAI 2020 · similarity 0.90)
- MNGNAS: Distilling Adaptive Combination of Multiple Searched Networks for One-Shot Neural Architecture Search (TPAMI 2023 · similarity 0.89)
- Neural Collapse Inspired Knowledge Distillation (AAAI 2025 · similarity 0.87)
- DA-KD: Difficulty-Aware Knowledge Distillation for Efficient Large Language Models (ICML 2025 · similarity 0.86)
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.
