Research map / Architectures and efficiency / Neural architecture search
Loss Functions for Predictor-based Neural Architecture Search
Han Ji, Yuqi Feng, Jiahao Fan, 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 |
|---|---|---|---|
| use PW loss (ListMLE then WARP) instead of single MSE loss (ablation) | PWLNAS · NAS-Bench-101 | test error (%): 6.06 -> 5.80 | Improved |
| use PW loss instead of best single loss HR (ablation) | PWLNAS · NAS-Bench-101 | test error (%): 5.83 -> 5.80 | Improved |
| use PW loss (HR then MAPE) instead of MSE (ablation) | PWLNAS · DARTS CIFAR-10 | test error (%): 2.74 -> 2.47 | Improved |
| use PW loss instead of MAPE (ablation) | PWLNAS · DARTS CIFAR-10 | test error (%): 2.53 -> 2.47 | Improved |
| use PW loss instead of WARP (ablation) | PWLNAS · TransNAS-Bench-101 Micro Class Scene | accuracy: 54.76 -> 54.83 | Improved |
| use PW loss instead of MSE (ablation) | PWLNAS · TransNAS-Bench-101 Micro Jigsaw | accuracy: 94.76 -> 94.88 | Improved |
| use WARP loss instead of MSE for PINAT predictor | PINAT · NAS-Bench-201 (1% data) | N@10: 146.60 -> 3.78 | Improved |
| use WARP loss instead of HR for MLP-based AP predictor | AP · NAS-Bench-201 (1% data) | N@10: 23.58 -> 113.20 | Hurt |
| use ListMLE instead of MSE for AP predictor | AP · NAS-Bench-201 (1% data) | N@10: 250.94 -> 22.74 | Improved |
| combine MSE with SR ranking loss versus single ranking loss | GCN predictor · NAS-Bench-101/201/TransNAS/Graph | Precision@0.5, N@10, Kendall Tau | Hurt |
| increase training data portion | GCN predictor with regression/ranking losses · several NAS search spaces | Precision@0.5 and N@10 | Hurt |
| use GT or exp(GT) weights instead of rank-based weights in weighted losses (ablation) | WARP and EW · NAS-Bench-201 (1% data) | Precision@T and N@K | Improved |
Closest papers by meaning
- How Powerful are Performance Predictors in Neural Architecture Search? (NeurIPS 2021 · similarity 0.92)
- Speedy Performance Estimation for Neural Architecture Search (NeurIPS 2021 · similarity 0.90)
- Understanding and Accelerating Neural Architecture Search With Training-Free and Theory-Grounded Metrics (TPAMI 2023 · similarity 0.89)
- Encodings for Prediction-based Neural Architecture Search (ICML 2024 · similarity 0.89)
- Evaluating The Search Phase of Neural Architecture Search (ICLR 2020 · similarity 0.89)
- Per-Architecture Training-Free Metric Optimization for Neural Architecture Search (NeurIPS 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.
