{"id":17195612,"url":"https://github.com/anonymone/neural-architecture-search","last_synced_at":"2026-03-08T10:37:04.735Z","repository":{"id":185514686,"uuid":"141007516","full_name":"anonymone/Neural-Architecture-Search","owner":"anonymone","description":"This repo is about NAS","archived":false,"fork":false,"pushed_at":"2019-11-01T09:27:16.000Z","size":59,"stargazers_count":26,"open_issues_count":0,"forks_count":6,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-01-30T07:26:55.863Z","etag":null,"topics":["automl","deep-neural-networks","efficient-architecture-search","nas","neural-architecture-search","optimization","paper"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/anonymone.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2018-07-15T07:31:32.000Z","updated_at":"2022-06-30T09:21:03.000Z","dependencies_parsed_at":null,"dependency_job_id":"253b1171-643f-40ec-857e-e5b08aa7f430","html_url":"https://github.com/anonymone/Neural-Architecture-Search","commit_stats":null,"previous_names":["anonymone/neural-architecture-search"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anonymone%2FNeural-Architecture-Search","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anonymone%2FNeural-Architecture-Search/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anonymone%2FNeural-Architecture-Search/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anonymone%2FNeural-Architecture-Search/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/anonymone","download_url":"https://codeload.github.com/anonymone/Neural-Architecture-Search/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245423193,"owners_count":20612748,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["automl","deep-neural-networks","efficient-architecture-search","nas","neural-architecture-search","optimization","paper"],"created_at":"2024-10-15T01:50:58.437Z","updated_at":"2026-03-08T10:37:04.684Z","avatar_url":"https://github.com/anonymone.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Neural Architecture Search\n\n## Tabel of contents\n* [1. NAS introdction](#introduction)\n* [2. NAS reviews](#reviews)\n* [3. Papers](#papers)\n\n## Introduction\n\nThe list includes the papers related to NAS I have read. All of them are grouped into three classes ( Search Space, Seach strategy and evaluation strategy) based on my subjectivity.\n\n## Papers\n### Reviews\n|Data|Title|Venue|Notes|  \n|:---|:---:|:--:|:---:|\n|2018|[Neural Architecture Search: A Survey](https://arxiv.org/abs/1808.05377)|JMLR|-|\n|2008|[Neuroevolution: From Architectures to Learning](https://link.springer.com/article/10.1007/s12065-007-0002-4)|Evolutionary Intelligence|-|\n|1999|[Evolving Artificial Neural Networks](https://ieeexplore.ieee.org/document/784219/)|IEEE|-|\n\n### Search Space / Encoding strategies\n|Data|Title|Venue|Code|Notes|  \n|:---|:----:|:--:|:--:|:---:|\n|2018|[Neural Architecture Search Over a Graph Search Space](https://arxiv.org/abs/1812.10666)|-|-|This paper defined a search space on direct graph which is used to instruct the construction of networks.|\n|2017|[Genetic CNN](https://arxiv.org/abs/1703.01513)|ICCV|[Tensorflow](https://github.com/aqibsaeed/Genetic-CNN)|This paper proposed a binary string encoding strategy.|\n|2017/18|[Efficient Architecture Search by Network Transformation](https://arxiv.org/abs/1707.04873)|AAAI|-|This paper Proposed a popular block based network definition method.|\n|2009|[A Hypercube-based Encoding for Evolving large-scale Neural Networks](https://ieeexplore.ieee.org/document/6792316/)|IEEE Artificial Life|-|This method use a extended CPPNs to encode the ANN.|\n|2006|[Evolutionary Design of Neural Network Architectures Using a Descriptive Encoding Language](https://ieeexplore.ieee.org/abstract/document/4016064)| IEEE TEVC| - | This paper proposed a human-readable and writable encoding method. |\n|2002|[Evolving Neural Networks through Augmenting Topologies](http://nn.cs.utexas.edu/downloads/papers/stanley.ec02.pdf)| EC| -| [NEAT: An Awesome Approach to NeuroEvolution](https://towardsdatascience.com/neat-an-awesome-approach-to-neuroevolution-3eca5cc7930f)|\n|1998| [Network Generating Attribute grammar Encoding](https://ieeexplore.ieee.org/abstract/document/682305/) | IJCNN | - | Grammar Encoding |\n|1996| [A comparison between cellular encoding and direct encoding for genetic neural networks](https://dl.acm.org/citation.cfm?id=1595547) | - | - | This paper compared the celluar encoding and direct encoding methods |\n|1996|[Evolving Graphs and Networks with Edge encoding: preliminary report](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.65.9718\u0026rep=rep1\u0026type=pdf)| The Genetic Programming Conference | - | Edge Encoding method. |\n|1994 | [Neurogenetic learning: an integrated method of designing and training neural networks using genetic algorithms](https://www.sciencedirect.com/science/article/abs/pii/0167278994902852) | Physica D | - | This paper inspired by L-System. |\n|1994| [Automatic definition of modular neural networks](https://journals.sagepub.com/doi/abs/10.1177/105971239400300202) | Adaptive behavior | - | - |\n|1990|[Designing Neural Networks Using Genetic Algorithms with Graph Generation System](http://www.complex-systems.com/abstracts/v04_i04_a06/) | The Conference on Genetic Algorithms | - | This paper proposed a graph grammatical encoding and analysed the problems of the direct encoding method.|\n\n### Search Strategies\n|Data|Title|Venue|Code|Notes|  \n|:---|:----:|:--:|:--:|:---:|\n|2018|[Reinforced Evolutionary Neural Architecture Search](https://arxiv.org/abs/1808.00193)|CVPR|[mxnet](https://github.com/yukang2017/RENAS)| EA/RL|\n|2018|[Neural Architecture Optimization](https://arxiv.org/abs/1808.07233)|NeurIPS|[Pytorch](https://github.com/renqianluo/NAO_pytorch) [Tensorflow](https://github.com/renqianluo/NAO)| Gradient Based|\n|2018|[NSGA-NET: A Multi-Objective Genetic Algorithm for Neural Architecture Search](https://arxiv.org/abs/1810.03522)|GECCO|-|This paper can be viewed as an extension of Genetic CNN in search strategy and slightly improving in encoding strategy.|\n|2017|[Large-Scale Evolution of Image Classifiers](https://arxiv.org/abs/1711.00436)|ICML|-|Google's work. Trying to prove the possibility of evolving CNN automatically.|\n|2017|[SMASH: One-Shot Model Architecture Search through HyperNetworks](https://arxiv.org/abs/1708.05344)|NeurIPS|-|Gradient Based|\n|2017|[Neural Architecture Search with Reinforcement Learning](https://arxiv.org/abs/1611.01578)|ICLR 2017|-| RL|\n|2017|[Designing Neural Network Architectures using Reinforcement Learning](https://arxiv.org/abs/1611.02167)|ICLR|-|RL|\n\n### Evaluation Strategies\n|Data|Title|Venue|Code|Notes|  \n|:---|:----:|:--:|:--:|:---:|\n|2018|[Progressive Neural Architecture Search](http://arxiv.org/abs/1712.00559)|ECCV|[Pytorch](https://github.com/chenxi116/PNASNet.pytorch) [Tensorflow](https://github.com/chenxi116/PNASNet.TF)| This paper use a predictor to evaluate the acc of each network with few real training.|\n\n### Extension\n|Data|Title|Venue|Code|Notes|  \n|:---|:----:|:--:|:--:|:---:|\n|2019|[NAS-Bench-101: Towards Reproducible Neural Architecture Search](https://arxiv.org/abs/1902.09635v1)|ICML| [Code](https://github.com/google-research/nasbench)| A Benchmark of NAS.|\n|2016|[Net2Net: Accelerating Learning via Knowledge Transfer](https://arxiv.org/abs/1511.05641)|ICLR 2016|-|This paper proposed a mehtod (similar to parameters sharing) to transfer the knowledge from previous network to a larger one.|\n\n## Useful pages\n1. [LITERATURE ON NEURAL ARCHITECTURE SEARCH](https://www.automl.org/automl/literature-on-neural-architecture-search/)\n1. [Awesome NAS](https://github.com/D-X-Y/Awesome-NAS/blob/master/README.md)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanonymone%2Fneural-architecture-search","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fanonymone%2Fneural-architecture-search","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanonymone%2Fneural-architecture-search/lists"}