← Back to all news
arXiv Machine Learning By Shiwen Qin, Alexander Auras, Shay B. Cohen, Elliot J. Crowley, Michael Moeller, Linus Ericsson, Jovita Lukasik

ONNX-Net: Towards Universal Representations and Instant Performance Prediction for Neural Architectures

Read the original on arXiv Machine Learning →

ONNX-Net introduces a universal representation for neural architectures using natural language descriptions, enabling instant performance prediction across diverse search spaces. The authors present ONNX-Bench, a benchmark of over 600k architecture–accuracy pairs compiled from open‑source NAS‑bench networks in ONNX format. Experiments demonstrate strong zero‑shot predictive performance with minimal pretraining, overcoming the limitations of cell‑based, graph‑encoded approaches.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Oct 28

MIDAS: Mosaic Input-Specific Differentiable Architecture Search

MIDAS is a differentiable neural architecture search method that replaces static architecture parameters with dynamic, input‑specific parameters generated through self‑attention. It localizes architecture selection to each spatial patch of the activation map and introduces a parameter‑free, topology‑aware search space that models two‑edge node topology. Evaluations on DARTS, NAS‑Bench‑201, and RDARTS show that MIDAS achieves state‑of‑the‑art accuracy on CIFAR‑10 and CIFAR‑100 and discovers optimal or near‑optimal architectures in benchmark spaces.

By Konstanty Subbotko
More like this →
arXiv Machine Learning
Oct 3

Prediction-powered Neural Architecture Search

The paper introduces PPNAS, a prediction‑powered inference method for neural architecture search that combines a small set of accurately evaluated architectures with a large set of zero‑cost proxy (ZCP) evaluations. PPNAS uses the ordinal information from ZCPs to generate pairwise ranking supervision and applies a debiasing step to reconcile discrepancies between proxy and true performance rankings. Experiments show that PPNAS achieves state‑of‑the‑art results in predictor‑based NAS under limited evaluation budgets.

By Pascal Janetzky, Yuxin Wang, Michael Klar, Stefan Feuerriegel
benchmarks
More like this →
arXiv Machine Learning
4d ago

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

DIFFNAS is a new neural architecture search framework that eliminates the need for performance predictors by using a discrete graph diffusion model conditioned on zero‑cost performance proxies such as MeCo and SWAP. The method achieves state‑of‑the‑art results on NAS‑Bench‑201 for CIFAR‑10 and CIFAR‑100, matching optimal architectures while cutting search cost by up to 17.5× compared to DiffusionNAG. Although its accuracy on the MobileNetV3 search space is lower than DiffusionNAG, the results demonstrate the potential of diffusion models combined with training‑free metrics for scalable architecture search.

By Yize Sun, Hanzhang Ma, Zixin Wu, Xuechun Li, Volker Tresp, Yunpu Ma
diffusion
More like this →