Research map / Architectures and efficiency / Neural architecture search
Bridge the Gap Between Architecture Spaces via A Cross-Domain Predictor
Yuqiao Liu, Yehui Tang, Zeqiong Lv, Yunhe Wang, Yanan Sun
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 progressive subspace partition (cosine schedule) vs none (ablation) | CDP · shallow DARTS | KTau: 0.3650 -> 0.5176 | Improved |
| cosine vs linear subspace increase schedule (ablation) | CDP · shallow DARTS | KTau: 0.4949 -> 0.5176 | Improved |
| linear progressive schedule vs none (ablation) | CDP · shallow DARTS | KTau: 0.3650 -> 0.4949 | Improved |
| add small assistant space (ablation) | CDP · shallow DARTS | KTau: 0.5176 -> 0.5051 | Hurt |
| add medium assistant space (tiny DARTS) (ablation) | CDP · shallow DARTS | KTau: 0.5176 -> 0.5306 | Improved |
| LMMD instead of MMD (ablation) | CDP · shallow DARTS | KTau: 0.4549 -> 0.4969 | Improved |
| LMMD + PSP instead of LMMD alone (ablation) | CDP · shallow DARTS | KTau: 0.4969 -> 0.5306 | Improved |
| LMMD + PSP instead of DANN (ablation) | CDP · shallow DARTS | KTau: 0.4686 -> 0.5306 | Improved |
| LMMD + PSP instead of CORAL (ablation) | CDP · shallow DARTS | KTau: 0.4306 -> 0.5306 | Improved |
| CDP vs PC-DARTS at similar search cost | CDP · ImageNet | top-1 accuracy: 74.9 -> 76.9 | Improved |
| CDP vs DARTS on CIFAR-10 | CDP · CIFAR-10 | accuracy: 97.24 ± 0.09 -> 97.51 | Improved |
| CDP vs WeakNAS on ImageNet top-5 | CDP · ImageNet | top-5 accuracy: 93.2 -> 93.0 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- DARTS — DARTS-: Robustly Stepping out of Performance Collapse Without Indicators (ICLR 2021) · better on 2 of 2 shared results
- BRP-NAS — BRP-NAS: Prediction-based NAS using GCNs (NeurIPS 2020) · better on 1 of 1 shared result
- FairDARTS — Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search (ECCV 2020) · better on 1 of 1 shared result
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
- Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective (ICLR 2021 · similarity 0.92)
- Adapting Neural Architectures Between Domains (NeurIPS 2020 · similarity 0.91)
- DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search (ECCV 2020 · similarity 0.91)
- Contrastive Neural Architecture Search With Neural Architecture Comparators (CVPR 2021 · similarity 0.90)
- TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search (CVPR 2021 · similarity 0.90)
- Encodings for Prediction-based Neural Architecture Search (ICML 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.
