mlsanityData to 14 Oct 2026

CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search

arXiv 2609.11884 ↗First posted 10 Sep 2026cs.LG cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Zero-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. CoRA-Refine samples anchors across this prior, extrapolates their early validation curves, and propagates a learned residual correction with an ExtraTrees model. The refinement uses approximately 1% of the cost of fully training the candidate set. Fully trained architecture-accuracy labels are not used to fit the ranker. One configuration is used across spaces, with space-specific architecture encodings. Across NAS-Bench-201, NAS-Bench-101, TransNAS-Bench-101, and NATS-SSS, CoRA-Refine achieves mean Spearman correlations of 0.946, 0.715, 0.786, and 0.894, respectively. Its worst-space correlation of 0.715 is the highest among the compared methods. On NAS-Bench-201/CIFAR-100, its selected architecture reaches 73.32% accuracy, near the reported ground-truth best of 73.37%. On the pure size space, refinement recovers the static prior's shortfall relative to parameter count, while remaining tied with the strongest capacity proxies within noise. The resulting framework combines cross-space ranking robustness with low-cost architecture selection.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 40 of its 47 references that are in the map. First posted on arXiv 10 Sep 2026.

Builds on

40 of 47 references.

References · 40

  1. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  2. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 812
  3. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  4. 2016Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimizationcited by 699
  5. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
  6. 2020Pruning neural networks without any data by iteratively conserving synaptic flowcited by 479
  7. 2020Picking Winning Tickets Before Training by Preserving Gradient Flowcited by 471
  8. 2018BOHB: Robust and Efficient Hyperparameter Optimization at Scalecited by 470
  9. 2020NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Searchcited by 416
  10. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 414
  11. 2019NAS-Bench-101: Towards Reproducible Neural Architecture Searchcited by 344
  12. 2020Neural Architecture Search without Trainingcited by 244
28 more
  1. 2021Zero-Cost Proxies for Lightweight NAScited by 199
  2. 2019BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Searchcited by 179
  3. 2021Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspectivecited by 169
  4. 2020NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Sizecited by 98
  5. 2021How Powerful are Performance Predictors in Neural Architecture Search?cited by 90
  6. 2021Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognitioncited by 73
  7. 2020NAS-Bench-NLP: Neural Architecture Search Benchmark for Natural Language Processingcited by 60
  8. 2021TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Searchcited by 58
  9. 2023ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradientscited by 58
  10. 2020Evaluating Efficient Performance Estimators of Neural Architecturescited by 55
  11. 2023Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networkscited by 37
  12. 2022NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxiescited by 36
  13. 2024AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Searchcited by 28
  14. 2020Speedy Performance Estimation for Neural Architecture Searchcited by 24
  15. 2021NAS-Bench-x11 and the Power of Learning Curvescited by 20
  16. 2021GradSign: Model Performance Inference with Theoretical Insightscited by 19
  17. 2023Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discoverycited by 13
  18. 2024SWAP-NAS: Sample-Wise Activation Patterns for Ultra-fast NAScited by 11
  19. 2021RANK-NOSH: Efficient Predictor-Based Architecture Search via Non-Uniform Successive Halvingcited by 9
  20. 2026Breaking Semantic-Aware Watermarks via LLM-Guided Coherence-Preserving Semantic Injectioncited by 8
  21. 2026SLICE: Semantic Latent Injection via Compartmentalized Embedding for Image Watermarkingcited by 7
  22. 2025L-SWAG: Layer-Sample Wise Activation with Gradients information for Zero-Shot NAS on Vision Transformerscited by 5
  23. 2024Robustifying and Boosting Training-Free Neural Architecture Searchcited by 4
  24. 2026SHIFT: Stochastic Hidden-Trajectory Deflection for Removing Diffusion-based Watermarkcited by 4
  25. 2026LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localizationcited by 4
  26. 2021FEAR: A Simple Lightweight Method to Rank Architecturescited by 3
  27. 2025Dextr: Zero-Shot Neural Architecture Search with Singular Value Decomposition and Extrinsic Curvaturecited by 1
  28. 2025Are LLMs Better GNN Helpers? Rethinking Robust Graph Learning under Deficiencies with Iterative Refinementcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026RiPPLE: Cross-Space Performance Prediction from Early Training for Neural Architecture Searchcited by 0