mlsanityData to 7 Oct 2026

SEval-NAS: A Search-Agnostic Evaluation for Neural Architecture Search

arXiv 2603.00099 ↗First posted 17 Feb 2026cs.LG cs.AI cs.NEcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural architecture search (NAS) automates the discovery of neural networks that meet specified criteria, yet its evaluation procedures are often hardcoded, limiting the ability to introduce new metrics. This issue is especially pronounced in hardware-aware NAS, where objectives depend on target devices such as edge hardware. To address this limitation, we propose SEval-NAS, a metric-evaluation mechanism that converts architectures to strings, embeds them as vectors, and predicts performance metrics. Using NATS-Bench and HW-NAS-Bench, we evaluated accuracy, latency, and memory. Kendall's τ correlations showed stronger latency and memory predictions than accuracy, indicating the suitability of SEval-NAS as a hardware cost predictor. We further integrated SEval-NAS into FreeREA to evaluate metrics not originally included. The method successfully ranked FreeREA-generated architectures, maintained search time, and required minimal algorithmic changes. Our implementation is available at: https://github.com/Analytics-Everywhere-Lab/neural-architecture-search

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 34 references that are in the map. First posted on arXiv 17 Feb 2026.

Builds on

23 of 34 references.

References · 23

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  3. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  4. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  5. 2017Progressive Neural Architecture Searchcited by 483
  6. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
  7. 2020NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Searchcited by 412
  8. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 374
  9. 2020A Comprehensive Survey of Neural Architecture Search: Challenges and Solutionscited by 253
  10. 2020Neural Architecture Search without Trainingcited by 241
  11. 2021Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspectivecited by 168
  12. 2018Neural Architecture Optimizationcited by 164
11 more
  1. 2023EvoPrompting: Language Models for Code-Level Neural Architecture Searchcited by 129
  2. 2017Genetic CNNcited by 124
  3. 2020NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Sizecited by 98
  4. 2021HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmarkcited by 83
  5. 2018SqueezeNext: Hardware-Aware Neural Network Designcited by 61
  6. 2023Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edgecited by 15
  7. 2018IRLAS: Inverse Reinforcement Learning for Architecture Searchcited by 10
  8. 2022FreeREA: Training-Free Evolution-based Architecture Searchcited by 10
  9. 2023Transfer-Once-For-All: AI Model Optimization for Edgecited by 4
  10. 2023Hardware Aware Evolutionary Neural Architecture Search using Representation Similarity Metriccited by 3
  11. 2024Achieving Pareto Optimality using Efficient Parameter Reduction for DNNs in Resource-Constrained Edge Environmentcited by 1

Built on by

Not cited yet.