Research map / Architectures and efficiency / Neural architecture search
MeCo: Zero-Shot NAS with One Data and Single Forward Pass via Minimum Eigenvalue of Correlation
Tangyu Jiang, Haodi Wang, Rongfang Bie
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 |
|---|---|---|---|
| increase fixed channel number n from 4 to 8 (ablation) | MeCoopt · NATS-Bench-TSS CIFAR-10 | Spearman rho: 0.87 -> 0.90 | Improved |
| increase fixed channel number n from 4 to 8 (ablation) | MeCoopt · NATS-Bench-SSS ImageNet16-120 | Spearman rho: 0.84 -> 0.89 | Improved |
| increase fixed channel number n from 4 to 8 (ablation) | MeCoopt · NATS-Bench-TSS CIFAR-100 | Spearman rho: 0.88 -> 0.89 | Improved |
| apply MeCoopt channel optimization on top of MeCo (ablation) | MeCo · NATS-Bench-SSS CIFAR-100 | Spearman rho: -0.87 -> 0.83 | Improved |
| use random Gaussian data instead of real data (ablation) | MeCo · NATS-Bench-TSS CIFAR-10 | Spearman rho: 0.894 -> 0.87 | No clear effect |
| use MeCo instead of NTK under random data | NTK · NATS-Bench-TSS CIFAR-10 | Spearman rho: 0.78 -> 0.87 | Improved |
| vary input sample numbers from 1 to 5 (ablation) | MeCo · NATS-Bench-TSS and SSS | Spearman rho: fluctuates around 0.01 | No clear effect |
| increase random data size from 16 to 256 (ablation) | MeCo · NATS-Bench-TSS | Spearman rho | Mixed |
| use MeCo instead of ZiCo as proxy in Zero-Cost-PT | ZiCo · DARTS-CNN CIFAR-10 | test error (%): 2.80 ± 0.03 -> 2.69± 0.05 | Improved |
| use MeCo instead of ZiCo as proxy in Zero-Cost-PT | ZiCo · DARTS-CNN CIFAR-100 | test error (%): 19.54 ± 0.28 -> 19.33 ± 0.25 | Improved |
| use MeCo instead of ZiCo | ZiCo · MobileNet-V3 ImageNet-1K | Top-1 accuracy (%): 77.1 -> 77.8 | Improved |
| use MeCo instead of ZiCo | ZiCo · NAS-Bench-301 CIFAR-10 | Spearman rho: 0.66 -> 0.7±0.01 | Improved |
Later papers that compared with this method
1 later accepted paper reports MeCo as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Zero-Shot Neural Network Evaluation With Sample-Wise Activation Patterns (TPAMI 2026 · better on 2 of 3 shared results)
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.
- ZiCo — ZiCo: Zero-shot NAS via inverse Coefficient of Variation on Gradients (ICLR 2023) · better on 8 of 8 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
- Accelerating Zero-Shot NAS With Feature Map-Based Proxy and Operation Scoring Function (TPAMI 2025 · similarity 0.95)
- ParZC: Parametric Zero-Cost Proxies for Efficient NAS (AAAI 2025 · similarity 0.90)
- Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions (AAAI 2025 · similarity 0.89)
- Revisiting Neural Networks for Few-Shot Learning: A Zero-Cost NAS Perspective (ICML 2025 · similarity 0.88)
- L-SWAG: Layer-Sample Wise Activation with Gradients Information for Zero-Shot NAS on Vision Transformers (CVPR 2025 · similarity 0.88)
- AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search (CVPR 2024 · similarity 0.87)
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.
