# HyperNAS: Enhancing Architecture Representation for NAS Predictor via Hypernetwork

arXiv: https://arxiv.org/abs/2509.18151 · HTML: https://mlsanity.com/paper/2509.18151/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2025.

## Built on by (most cited first, 2 of 2)

- [Universal Hypernetworks for Arbitrary Models](https://mlsanity.com/paper/2604.02215/) (2026)
- [Towards Code-Oriented LM Embeddings for Surrogate-Assisted Neural Architecture Search](https://mlsanity.com/paper/2605.15649/) (2026)

## Abstract (arXiv)

Time-intensive performance evaluations significantly impede progress in Neural Architecture Search (NAS). To address this, neural predictors leverage surrogate models trained on proxy datasets, allowing for direct performance predictions for new architectures. However, these predictors often exhibit poor generalization due to their limited ability to capture intricate relationships among various architectures. In this paper, we propose HyperNAS, a novel neural predictor paradigm for enhancing architecture representation learning. HyperNAS consists of two primary components: a global encoding scheme and a shared hypernetwork. The global encoding scheme is devised to capture the comprehensive macro-structure information, while the shared hypernetwork serves as an auxiliary task to enhance the investigation of inter-architecture patterns. To ensure training stability, we further develop a dynamic adaptive multi-task loss to facilitate personalized exploration on the Pareto front. Extensive experiments across five representative search spaces, including ViTs, demonstrate the advantages of HyperNAS, particularly in few-shot scenarios. For instance, HyperNAS strikes new state-of-the-art results, with 97.60% top-1 accuracy on CIFAR-10 and 82.4% top-1 accuracy on ImageNet, using at least 5.0× fewer samples.