CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search
CoRA-NAS combines zero-cost proxy ranking with low-cost learning-curve refinement, achieving the best worst-space Spearman correlation across NAS benchmarks.
The paper proposes CoRA-NAS, a two-stage neural architecture search framework pairing a static ranking prior (CoRA-Rank) with learning-curve refinement (CoRA-Refine) that extrapolates early validation curves for sampled anchors and propagates residual corrections with an ExtraTrees model at about 1% of full training cost. Across NAS-Bench-201, NAS-Bench-101, TransNAS-Bench-101, and NATS-SSS it achieves mean Spearman correlations of 0.946, 0.715, 0.786, and 0.894 respectively, with the best worst-space correlation of 0.715 among compared methods. On NAS-Bench-201/CIFAR-100 its selected architecture reaches 73.32% accuracy versus a 73.37% ground-truth best.
- CoRA-Rank aggregates proxies via equal-weight log-rank consensus
- CoRA-Refine uses about 1% of the cost of fully training candidates
- Mean Spearman 0.946 on NAS-Bench-201, 0.715 on NAS-Bench-101
- Selected architecture reaches 73.32% on NAS-Bench-201/CIFAR-100
- Organizations
- arXiv
From the original article
1 min read at arxiv.orgZero-cost proxies rank architectures cheaply, but their reliability varies across search spaces. We introduce CoRA-NAS (COarse Ranking + Anchor-residual), a two-stage framework combining a static ranking prior with low-cost learning-curve refinement. CoRA-Rank aggregates capacity and structure-at-initialization proxies through an equal-weight log-rank consensus and a target-free consensus gate.
By Yifan Yang · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.