Papers β€Ί MeCo: Zero-Shot NAS with One Data and Single Forward Pass via Minimum Eigenvalue of Correlation

MeCo: Zero-Shot NAS with One Data and Single Forward Pass via Minimum Eigenvalue of Correlation

21 Sep 2023NeurIPS 2023 11archive 2025-07-28

Neural Architecture Search (NAS) is a promising paradigm in automatic architecture engineering. Zero-shot NAS can evaluate the network without training via some specific metrics called zero-cost proxies. Though effective, the existing zero-cost proxies either invoke at least one backpropagation or depend highly on the data and labels. To alleviate the above issues, in this paper, we first reveal how the Pearson correlation matrix of the feature maps impacts the convergence rate and the generalization capacity of an over-parameterized neural network. Enlightened by the theoretical analysis, we propose a novel zero-cost proxy called π–¬π–Ύπ–’π—ˆ, which requires only one random data for a single forward pass. We further propose an optimization approach π–¬π–Ύπ–’π—ˆβ‚’β‚šβ‚œ to improve the performance of our method. We design comprehensive experiments and extensively evaluate π–¬π–Ύπ–’π—ˆ on multiple popular benchmarks. π–¬π–Ύπ–’π—ˆ achieves the highest correlation with the ground truth (e.g., 0.89 on NATS-Bench-TSS with CIFAR-10) among all the state-of-the-art proxies, which is also fully independent of the data and labels. Moreover, we integrate π–¬π–Ύπ–’π—ˆ with the existing generation method to comprise a complete NAS. The experimental results illustrate that π–¬π–Ύπ–’π—ˆ-based NAS can select the architecture with the highest accuracy and a low search cost. For instance, the best network searched by π–¬π–Ύπ–’π—ˆ-based NAS achieves 97.31% on CIFAR-10, which is 0.04% higher than the baselines under the same settings. Our code is available at https://github.com/HamsterMimi/MeCo

PaperPDFCode

Code

hamstermimi/meco officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change Β· a person checks every report against the paper or source before anything changes; decisions are listed on /corrections