Maintained by Difan Deng and Marius Lindauer.
The following list considers papers related to neural architecture search. It is by no means complete. If you miss a paper on the list, please let us know.
Please note that although NAS methods steadily improve, the quality of empirical evaluations in this field are still lagging behind compared to other areas in machine learning, AI and optimization. We would therefore like to share some best practices for empirical evaluations of NAS methods, which we believe will facilitate sustained and measurable progress in the field. If you are interested in a teaser, please read our blog post or directly jump to our checklist.
Transformers have gained increasing popularity in different domains. For a comprehensive list of papers focusing on Neural Architecture Search for Transformer-Based spaces, the awesome-transformer-search repo is all you need.
2018
A Hybrid Differential Evolution Approach to Designing Deep Convolutional Neural Networks for Image Classification Proceedings Article
In: pp. 237-250, 2018.
Evolutionary-Neural Hybrid Agents for Architecture Search Technical Report
2018.
Joint Neural Architecture Search and Quantization Technical Report
2018.
Transfer Learning with Neural AutoML Proceedings Article
In: pp. 8366-8375, 2018.
Evolving Image Classification Architectures With Enhanced Particle Swarm Optimisation Journal Article
In: vol. 6, pp. 68560-68575, 2018.
NSGA-NET - A Multi-Objective Genetic Algorithm for Neural Architecture Search Technical Report
2018.
You Only Search Once - Single Shot Neural Architecture Search via Direct Sparse Optimization Technical Report
2018.
Automatically Evolving CNN Architectures Based on Blocks Technical Report
2018.
Gradient Based Evolution to Optimize the Structure of Convolutional Neural Networks Proceedings Article
In: pp. 3438-3442, 2018.
Searching toward pareto-optimal device-aware neural architectures Proceedings Article
In: pp. 136, 2018.
Exploring Shared Structures and Hierarchies for Multiple NLP Tasks Technical Report
2018.
BlockQNN - Efficient Block-wise Neural Network Architecture Generation Technical Report
2018.
Automatically Designing CNN Architectures for Medical Image Segmentation Proceedings Article
In: pp. 98-106, 2018.
MONAS - Multi-Objective Neural Architecture Search using Reinforcement Learning Technical Report
2018.
Path-Level Network Transformation for Efficient Architecture Search Proceedings Article
In: pp. 677-686, 2018.
Lamarckian Evolution of Convolutional Neural Networks Proceedings Article
In: pp. 424-435, 2018.
Deep Learning Architecture Search by Neuro-Cell-Based Evolution with Function-Preserving Mutations Proceedings Article
In: pp. 243-258, 2018.
Constructing Deep Neural Networks by Bayesian Network Structure Learning Proceedings Article
In: pp. 3051-3062, 2018.
Efficient Neural Architecture Search with Network Morphism Technical Report
2018.
Multi-objective Architecture Search for CNNs Technical Report
2018.
GNAS - A Greedy Neural Architecture Search Method for Multi-Attribute Learning Proceedings Article
In: pp. 2049-2057, 2018.
Evolutionary architecture search for deep multitask networks Proceedings Article
In: pp. 466-473, 2018.
From Nodes to Networks - Evolving Recurrent Neural Networks Technical Report
2018.
Neural Architecture Construction using EnvelopeNets Technical Report
2018.
Transfer Automatic Machine Learning Technical Report
2018.
Neural Architecture Search with Bayesian Optimisation and Optimal Transport Proceedings Article
In: pp. 2020-2029, 2018.
Efficient Neural Architecture Search via Parameter Sharing Proceedings Article
In: pp. 4092-4101, 2018.
Effective Building Block Design for Deep Convolutional Neural Networks using Search Technical Report
2018.
Memetic evolution of deep neural networks Proceedings Article
In: pp. 505-512, 2018.
Understanding and Simplifying One-Shot Architecture Search Proceedings Article
In: pp. 549-558, 2018.
PPP-Net - Platform-aware Progressive Search for Pareto-optimal Neural Architectures Proceedings Article
In: 2018.
Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks Journal Article
In: vol. 17, no. 2, pp. 1850008:1-1850008:15, 2018.
GitGraph - from Computational Subgraphs to Smaller Architecture Search Spaces Proceedings Article
In: 2018.
N2N learning - Network to Network Compression via Policy Gradient Reinforcement Learning Proceedings Article
In: 2018.
MorphNet - Fast & Simple Resource-Constrained Structure Learning of Deep Networks Proceedings Article
In: pp. 1586-1595, 2018.
MaskConnect - Connectivity Learning by Gradient Descent Proceedings Article
In: pp. 362-378, 2018.
A Flexible Approach to Automated RNN Architecture Generation Proceedings Article
In: 2018.
A Genetic Programming Approach to Designing Convolutional Neural Network Architectures Proceedings Article
In: pp. 5369-5373, 2018.
Practical Block-Wise Neural Network Architecture Generation Proceedings Article
In: pp. 2423-2432, 2018.
Accelerating Neural Architecture Search using Performance Prediction Proceedings Article
In: 2018.
Hierarchical Representations for Efficient Architecture Search Proceedings Article
In: 2018.
Learning Transferable Architectures for Scalable Image Recognition Proceedings Article
In: pp. 8697-8710, 2018.
Simple and efficient architecture search for Convolutional Neural Networks Proceedings Article
In: 2018.
Hyperparameter optimization - a spectral approach Proceedings Article
In: 2018.
SMASH - One-Shot Model Architecture Search through HyperNetworks Proceedings Article
In: 2018.
Efficient Architecture Search by Network Transformation Proceedings Article
In: pp. 2787-2794, 2018.
Searching for Efficient Multi-Scale Architectures for Dense Image Prediction Proceedings Article
In: Bengio, Samy; Wallach, Hanna M.; Larochelle, Hugo; Grauman, Kristen; Cesa-Bianchi, Nicolò; Garnett, Roman (Ed.): Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montréal, Canada, pp. 8713–8724, 2018.
2017
Skin cancer reorganization and classification with deep neural network Technical Report
2017.