cs.LGOct 30, 2026

DIFFNAS: Predictor-Free Neural Architecture Search via Diffusion Model and Zero-Cost Evaluation

Authors: Yize Sun, Hanzhang Ma, Zixin Wu, Xuechun Li, Volker Tresp, Yunpu Ma

Organizations: Ludwig-Maximilians-Universität München (LMU Munich), Germany · Munich Center for Machine Learning (MCML), Germany · Paderborn University, Germany · Faculty of Computer Science, University of Duisburg-Essen, Germany

Abstract

Neural Architecture Search (NAS) has advanced the automated design of deep networks, but remains computationally expensive due to reliance on model training or performance predictors. We introduce DIFFNAS, a predictor-free NAS framework that leverages a discrete graph diffusion model guided by zero-cost performance proxies. Unlike prior diffusion-based NAS methods that require learned performance predictors, DIFFNAS conditions the generative process on training-free metrics such as MeCo and SWAP, enabling efficient architecture search with minimal computational overhead. Experiments on NAS-Bench-201 show that DIFFNAS finds the optimal architectures for CIFAR-10 and CIFAR-100 (94.37% and 73.51%) without a pretrained predictor, while reducing search cost by up to 17.5x compared to DiffusionNAG. On the MobileNetV3 search space, its accuracy is lower than that of DiffusionNAG. These results highlight the promise of diffusion models combined with zero-cost proxies for scalable and effective architecture search.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. LP-NAS: Linear Programming-based Neural Architecture Search

    Aug 14, 2026Abhishek Shukla, Ankur Sinha, Faiz HamidNeural Architecture Search

  2. Prediction-powered Neural Architecture Search

    Oct 1, 2026Pascal Janetzky, Yuxin Wang, Michael Klar +1Neural Architecture SearchPrediction-Powered Inference

  3. G-ICSO-NAS: Shifting Gears between Gradient and Swarm for Robust Neural Architecture Search

    Apr 1, 2026Xingbang Du, Enzhi Zhang, Rui Zhong +2Evolutionary NASNeural Architecture Search