Research map / Architectures and efficiency / Neural architecture search
Auto-GAS: Automated Proxy Discovery for Training-free Generative Architecture Search
Lujun Li, Haosen Sun, Shiwen Li, Peijie Dong, Wenhan Luo, Wei Xue, Qifeng Liu, Yike Guo
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 the evolved information-aware proxy instead of existing zero-cost proxies | Auto-GAS · TransNAS-Bench-101 Autoencoding | Kendall's Tau (%): 51.28% -> 61.14% (vs NWOT) | Improved |
| use parameter-level proxies (Synflow, SNIP, Params) for generator ranking | zero-cost proxies · TransNAS-Bench-101 Autoencoding | Kendall's Tau (%): Synflow -50.91%; Params -12.97% | Hurt |
| evolve proxy with search instead of vanilla Gram-matrix (ablation) | Auto-GAS proxy · CIFAR-10 | FID: 17.88 -> 12.21 | Improved |
| include encoding operators in proxy search space (ablation) | Auto-GAS proxy · TransNAS-Bench-101 Autoencoding | Kendall's Tau (%): 51.64% -> 61.14% | Improved |
| include reduction operators in proxy search space (ablation) | Auto-GAS proxy · TransNAS-Bench-101 Autoencoding | Kendall's Tau (%): 52.78% -> 61.14% | Improved |
| include transform operators in proxy search space (ablation) | Auto-GAS proxy · TransNAS-Bench-101 Autoencoding | Kendall's Tau (%): 55.78% -> 61.14% | Improved |
| include augment operators in proxy search space (ablation) | Auto-GAS proxy · TransNAS-Bench-101 Autoencoding | Kendall's Tau (%): 58.40% -> 61.14% | Improved |
| use evolutionary proxy search instead of random search (ablation) | Auto-GAS · TransNAS-Bench-101 Autoencoding | Kendall's Tau (%): 29.49% -> 61.14% | Improved |
| use Pearson or Hamming encoding instead of Gram-matrix (ablation) | Auto-GAS proxy · CIFAR-10 | FID: 12.21 -> 12.85 (Pearson); 12.21 -> 12.35 (Hamming) | No clear effect |
| increase EA population from 16 to 64 or batch size from 20 to 40 (ablation) | Auto-GAS search · CIFAR-10 | FID: 12.21 -> 16.32 (64 individuals); 12.28 -> 16.52 (batch 40) | Hurt |
| replace Gram-matrix-based proxy by L2 norm, entropy, or variance statistics (ablation) | Auto-GAS proxy · CIFAR-10 | FID: 12.21 -> 24.62 (L2 norm) | Hurt |
| use training-free proxy search instead of training-based GAN search | Auto-GAS · GAS search cost | GPU-days: EAGAN 0.8 -> Auto-GAS 0.09 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- SNIP — SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY (ICLR 2019) · better on 1 of 1 shared result
- AutoGAN — AutoGAN: Neural Architecture Search for Generative Adversarial Networks (ICCV 2019) · 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
- Auto-DAS: Automated Proxy Discovery for Training-free Distillation-aware Architecture Search (ECCV 2024 · similarity 0.88)
- Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery (AAAI 2024 · similarity 0.81)
- Building Optimal Neural Architectures using Interpretable Knowledge (CVPR 2024 · similarity 0.80)
- Structuring Open-Ended NAS: Semi-Automated Design Knowledge Structuring with LLMs for Efficient Neural Architecture Search (NeurIPS 2026 · similarity 0.79)
- Towards Neural Architecture Search through Hierarchical Generative Modeling (ICML 2024 · similarity 0.79)
- RZ-NAS: Enhancing LLM-guided Neural Architecture Search via Reflective Zero-Cost Strategy (ICML 2025 · similarity 0.78)
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.
