# Neural Architecture Performance Prediction Using Graph Neural Networks

arXiv: https://arxiv.org/abs/2010.10024 · HTML: https://mlsanity.com/paper/2010.10024/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2020.

## Built on by (most cited first, 8 of 8)

- [Parameter Prediction for Unseen Deep Architectures](https://mlsanity.com/paper/2110.13100/) (2021)
- [OmniPred: Language Models as Universal Regressors](https://mlsanity.com/paper/2402.14547/) (2024)
- [A Survey on Computationally Efficient Neural Architecture Search](https://mlsanity.com/paper/2206.01520/) (2022)
- [FLASH: Fast Neural Architecture Search with Hardware Optimization](https://mlsanity.com/paper/2108.00568/) (2021)
- [Geometric Learning in Black-Box Optimization: A GNN Framework for Algorithm Performance Prediction](https://mlsanity.com/paper/2506.16144/) (2025)
- [Accuracy Prediction for NAS Acceleration using Feature Selection and Extrapolation](https://mlsanity.com/paper/2211.12419/) (2022)
- [From Regression to Inference: Meta-Learning Predictors for Neural Architecture Search](https://mlsanity.com/paper/2605.09290/) (2026)
- [FRAME: Forensic Routing and Adaptive Multi-path Evidence Fusion for Image Manipulation Detection](https://mlsanity.com/paper/2605.12826/) (2026)

## Abstract (arXiv)

In computer vision research, the process of automating architecture engineering, Neural Architecture Search (NAS), has gained substantial interest. Due to the high computational costs, most recent approaches to NAS as well as the few available benchmarks only provide limited search spaces. In this paper we propose a surrogate model for neural architecture performance prediction built upon Graph Neural Networks (GNN). We demonstrate the effectiveness of this surrogate model on neural architecture performance prediction for structurally unknown architectures (i.e. zero shot prediction) by evaluating the GNN on several experiments on the NAS-Bench-101 dataset.