# Graph HyperNetworks for Neural Architecture Search Source: [Graph HyperNetworks for Neural Architecture Search]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:48:52.480Z Authors: Chris Zhang, Mengye Ren, Raquel Urtasun Published: 2018-10-12T22:21:05.000Z ## Abstract Neural architecture search (NAS) automatically finds the best task-specific neural network topology, outperforming many manual architecture designs. However, it can be prohibitively expensive as the search requires training thousands of different networks, while each can last for hours. In this work, we propose the Graph HyperNetwork (GHN) to amortize the search cost: given an architecture, it directly generates the weights by running inference on a graph neural network. GHNs model the topology of an architecture and therefore can predict network performance more accurately than regular hypernetworks and premature early stopping. To perform NAS, we randomly sample architectures and use the validation accuracy of networks with GHN generated weights as the surrogate search signal. GHNs are fast -- they can search nearly 10 times faster than other random search methods on CIFAR-10 and ImageNet. GHNs can be further extended to the anytime prediction setting, where they have found networks with better speed-accuracy tradeoff than the state-of-the-art manual designs. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on ImageNet OOD DEEPNETS-1M (test)](): Image Classification; ImageNet OOD DEEPNETS-1M (test); Top-5 Accuracy (RESNET): 6.9. - [Image Classification on ImageNet DEEPNETS-1M (test)](): Image Classification; ImageNet DEEPNETS-1M (test); Avg Top-5 Accuracy: 17.2. - [Image Classification on CIFAR-10 ID-TEST DEEPNETS-1M (test)](): Image Classification; CIFAR-10 ID-TEST DEEPNETS-1M (test); Avg Accuracy: 0.514. - [Image Classification on CIFAR-10 OOD DEEPNETS-1M (test)](): Image Classification; CIFAR-10 OOD DEEPNETS-1M (test); Accuracy (WIDE): 43.1. - [Image Classification on ImageNet Mobile Setting (test)](): Image Classification; ImageNet Mobile Setting (test); Top-1 Error: 27. - [Image Classification on CIFAR-10 (test)](): Image Classification; CIFAR-10 (test); Accuracy: not recorded. - [Image Classification on CIFAR-10](): Image Classification; CIFAR-10; Accuracy: not recorded. - [Image Classification on ImageNet (test)](): Image Classification; ImageNet (test); Top-1 Acc: not recorded. ## Original sources and implementation [Original paper]() [PDF]()