Literature on Neural Architecture Search

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.

1111 entries « ‹ 3 of 23 › »

2021
1011.	Ding, Z; Chen, Y; Li, N; Zhao, D; Sun, Z; Chen, C L P BNAS: Efficient Neural Architecture Search Using Broad Scalable Architecture Journal Article IEEE Transactions on Neural Networks and Learning Systems, pp. 1-15, 2021. Links \| BibTeX @article{9392299, title = {BNAS: Efficient Neural Architecture Search Using Broad Scalable Architecture}, author = {Z Ding and Y Chen and N Li and D Zhao and Z Sun and C L P Chen}, url = {https://ieeexplore.ieee.org/abstract/document/9392299}, doi = {10.1109/TNNLS.2021.3067028}, year = {2021}, date = {2021-01-01}, journal = {IEEE Transactions on Neural Networks and Learning Systems}, pages = {1-15}, keywords = {}, pubstate = {published}, tppubtype = {article} } Close https://ieeexplore.ieee.org/abstract/document/9392299 doi:10.1109/TNNLS.2021.3067028 Close
1010.	Ren, Pengzhen; Xiao, Gang; Chang, Xiaojun; Xiao, Yun; Li, Zhihui; Chen, Xiaojiang NAS-TC: Neural Architecture Search on Temporal Convolutions for Complex Action Recognition Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2104-01110, title = {NAS-TC: Neural Architecture Search on Temporal Convolutions for Complex Action Recognition}, author = {Pengzhen Ren and Gang Xiao and Xiaojun Chang and Yun Xiao and Zhihui Li and Xiaojiang Chen}, url = {https://arxiv.org/abs/2104.01110}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2104.01110}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2104.01110 Close
1009.	Dong, Heyou; Chen, Dan; Zhang, Lei; Ke, Hengjin; Li, Xiaoli Subject Sensitive EEG Discrimination with Fast Reconstructable CNN Driven by Reinforcement Learning: A Case Study of ASD Evaluation Journal Article Neurocomputing, 2021, ISSN: 0925-2312. Abstract \| Links \| BibTeX @article{DONG2021, title = {Subject Sensitive EEG Discrimination with Fast Reconstructable CNN Driven by Reinforcement Learning: A Case Study of ASD Evaluation}, author = {Heyou Dong and Dan Chen and Lei Zhang and Hengjin Ke and Xiaoli Li}, url = {https://www.sciencedirect.com/science/article/pii/S0925231221005270}, doi = {https://doi.org/10.1016/j.neucom.2021.04.009}, issn = {0925-2312}, year = {2021}, date = {2021-01-01}, journal = {Neurocomputing}, abstract = {Recent Electroencephalogram (EEG) analysis in connection with brain disorders has been tremendously benefiting from the (Deep) Neural Network technology in neuroscience research and neuro-engineering practices. However, the performance of existing hand-crafted models, such as the stability, has largely been refrained. This is the case especially in the paradigms that sensitive to the individuality of subjects and the non-stationarity of cognitive dynamics, such as Autism Spectrum Disorder (ASD) evaluation. Aiming at this problem, this study develops a Q-Learning method to enable fast reconstruction of Convolutional Neural Network (CNN) thus to support EEG discrimination adapting to the individuality of subjects under examination. The proposed method first generates a CNN model with the structure and hyper-parameters determined (i.e., Neural Architecture Search) by the customized Q-Learning algorithm, where the CNN model is treated as a discrete system to be optimized. With the sharp shift of subjects, the Q-Learning algorithm reconstructs the CNN model to reach optimization reusing the tacit knowledge learned from the previous trials. A case study has been performed to check the proposed method versus state-of-the-art counterparts based on resting-state EEG collected from 175 ASD-suspicious children with a diverse geological distribution. The observations in the case study indicate that: 1) the method outperforms the counterparts with an individual/sample accuracy of 92.63%/83.23% achieved; 2) the method can quickly reconstruct the CNN model with the group of subjects shifting from one region to another to maintain an encouraging performance while the counterparts without reconstruction may drop by about 12%.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Close Recent Electroencephalogram (EEG) analysis in connection with brain disorders has been tremendously benefiting from the (Deep) Neural Network technology in neuroscience research and neuro-engineering practices. However, the performance of existing hand-crafted models, such as the stability, has largely been refrained. This is the case especially in the paradigms that sensitive to the individuality of subjects and the non-stationarity of cognitive dynamics, such as Autism Spectrum Disorder (ASD) evaluation. Aiming at this problem, this study develops a Q-Learning method to enable fast reconstruction of Convolutional Neural Network (CNN) thus to support EEG discrimination adapting to the individuality of subjects under examination. The proposed method first generates a CNN model with the structure and hyper-parameters determined (i.e., Neural Architecture Search) by the customized Q-Learning algorithm, where the CNN model is treated as a discrete system to be optimized. With the sharp shift of subjects, the Q-Learning algorithm reconstructs the CNN model to reach optimization reusing the tacit knowledge learned from the previous trials. A case study has been performed to check the proposed method versus state-of-the-art counterparts based on resting-state EEG collected from 175 ASD-suspicious children with a diverse geological distribution. The observations in the case study indicate that: 1) the method outperforms the counterparts with an individual/sample accuracy of 92.63%/83.23% achieved; 2) the method can quickly reconstruct the CNN model with the group of subjects shifting from one region to another to maintain an encouraging performance while the counterparts without reconstruction may drop by about 12%. Close https://www.sciencedirect.com/science/article/pii/S0925231221005270 doi:https://doi.org/10.1016/j.neucom.2021.04.009 Close
1008.	Lee, Hayeon; Hyung, Eunyoung; Hwang, Sung Ju Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets Inproceedings International Conference on Learning Representations, 2021. Links \| BibTeX @inproceedings{<LineBreak>lee2021rapid, title = {Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets}, author = {Hayeon Lee and Eunyoung Hyung and Sung Ju Hwang}, url = {https://openreview.net/forum?id=rkQuFUmUOg3}, year = {2021}, date = {2021-01-01}, booktitle = {International Conference on Learning Representations}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Close https://openreview.net/forum?id=rkQuFUmUOg3 Close
1007.	Wang, J; Zhao, J; An, J; Wang, D; Qiu, M A Linear NAS Service of ConvNets for Fast Deployment in the Edge of 5G Networks Journal Article IEEE Network, 35 (2), pp. 46-52, 2021. Links \| BibTeX @article{9387697, title = {A Linear NAS Service of ConvNets for Fast Deployment in the Edge of 5G Networks}, author = {J Wang and J Zhao and J An and D Wang and M Qiu}, url = {https://ieeexplore.ieee.org/abstract/document/9387697}, doi = {10.1109/MNET.011.1900336}, year = {2021}, date = {2021-01-01}, journal = {IEEE Network}, volume = {35}, number = {2}, pages = {46-52}, keywords = {}, pubstate = {published}, tppubtype = {article} } Close https://ieeexplore.ieee.org/abstract/document/9387697 doi:10.1109/MNET.011.1900336 Close
1006.	Shi, Xian; Zhou, Pan; Chen, Wei; Xie, Lei Darts-Conformer: Towards Efficient Gradient-Based Neural Architecture Search For End-to-End ASR Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2104-02868, title = {Darts-Conformer: Towards Efficient Gradient-Based Neural Architecture Search For End-to-End ASR}, author = {Xian Shi and Pan Zhou and Wei Chen and Lei Xie}, url = {https://arxiv.org/abs/2104.02868}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2104.02868}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2104.02868 Close
1005.	Ganepola, Vayangi Vishmi Vishara; Wirasingha, Torin Automating Generative Adversarial Networks using Neural Architecture Search: A Review Inproceedings 2021 International Conference on Emerging Smart Computing and Informatics (ESCI), pp. 577-582, 2021. Links \| BibTeX @inproceedings{9396991, title = {Automating Generative Adversarial Networks using Neural Architecture Search: A Review}, author = {Vayangi Vishmi Vishara Ganepola and Torin Wirasingha}, url = {https://ieeexplore.ieee.org/abstract/document/9396991}, doi = {10.1109/ESCI50559.2021.9396991}, year = {2021}, date = {2021-01-01}, booktitle = {2021 International Conference on Emerging Smart Computing and Informatics (ESCI)}, pages = {577-582}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Close https://ieeexplore.ieee.org/abstract/document/9396991 doi:10.1109/ESCI50559.2021.9396991 Close
1004.	Zappella, Giovanni; Salinas, David; Archambeau, Cédric A resource-efficient method for repeated HPO and NAS problems Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2103-16111, title = {A resource-efficient method for repeated HPO and NAS problems}, author = {Giovanni Zappella and David Salinas and Cédric Archambeau}, url = {https://arxiv.org/abs/2103.16111}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.16111}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2103.16111 Close
1003.	Liu, Hongying; Xu, Derong; Zhu, Tianwen; Shang, Fanhua; Liu, Yuanyuan; Lu, Jianhua; Yang, Ri Graph Convolutional Networks by Architecture Search for PolSAR Image Classification Journal Article Remote Sensing, 13 (7), 2021, ISSN: 2072-4292. Abstract \| Links \| BibTeX @article{rs13071404, title = {Graph Convolutional Networks by Architecture Search for PolSAR Image Classification}, author = {Hongying Liu and Derong Xu and Tianwen Zhu and Fanhua Shang and Yuanyuan Liu and Jianhua Lu and Ri Yang}, url = {https://www.mdpi.com/2072-4292/13/7/1404}, doi = {10.3390/rs13071404}, issn = {2072-4292}, year = {2021}, date = {2021-01-01}, journal = {Remote Sensing}, volume = {13}, number = {7}, abstract = {Classification of polarimetric synthetic aperture radar (PolSAR) images has achieved good results due to the excellent fitting ability of neural networks with a large number of training samples. However, the performance of most convolutional neural networks (CNNs) degrades dramatically when only a few labeled training samples are available. As one well-known class of semi-supervised learning methods, graph convolutional networks (GCNs) have gained much attention recently to address the classification problem with only a few labeled samples. As the number of layers grows in the network, the parameters dramatically increase. It is challenging to determine an optimal architecture manually. In this paper, we propose a neural architecture search method based GCN (ASGCN) for the classification of PolSAR images. We construct a novel graph whose nodes combines both the physical features and spatial relations between pixels or samples to represent the image. Then we build a new searching space whose components are empirically selected from some graph neural networks for architecture search and develop the differentiable architecture search method to construction our ASGCN. Moreover, to address the training of large-scale images, we present a new weighted mini-batch algorithm to reduce the computing memory consumption and ensure the balance of sample distribution, and also analyze and compare with other similar training strategies. Experiments on several real-world PolSAR datasets show that our method has improved the overall accuracy as much as 3.76% than state-of-the-art methods.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Close Classification of polarimetric synthetic aperture radar (PolSAR) images has achieved good results due to the excellent fitting ability of neural networks with a large number of training samples. However, the performance of most convolutional neural networks (CNNs) degrades dramatically when only a few labeled training samples are available. As one well-known class of semi-supervised learning methods, graph convolutional networks (GCNs) have gained much attention recently to address the classification problem with only a few labeled samples. As the number of layers grows in the network, the parameters dramatically increase. It is challenging to determine an optimal architecture manually. In this paper, we propose a neural architecture search method based GCN (ASGCN) for the classification of PolSAR images. We construct a novel graph whose nodes combines both the physical features and spatial relations between pixels or samples to represent the image. Then we build a new searching space whose components are empirically selected from some graph neural networks for architecture search and develop the differentiable architecture search method to construction our ASGCN. Moreover, to address the training of large-scale images, we present a new weighted mini-batch algorithm to reduce the computing memory consumption and ensure the balance of sample distribution, and also analyze and compare with other similar training strategies. Experiments on several real-world PolSAR datasets show that our method has improved the overall accuracy as much as 3.76% than state-of-the-art methods. Close https://www.mdpi.com/2072-4292/13/7/1404 doi:10.3390/rs13071404 Close
1002.	Guo, Shaopeng; Wang, Yujie; Yuan, Kun; Li, Quanquan Differentiable Network Adaption with Elastic Search Space Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2103-16350, title = {Differentiable Network Adaption with Elastic Search Space}, author = {Shaopeng Guo and Yujie Wang and Kun Yuan and Quanquan Li}, url = {https://arxiv.org/abs/2103.16350}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.16350}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2103.16350 Close
1001.	Schmidgall, Samuel Self-Constructing Neural Networks Through Random Mutation Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2103-15692, title = {Self-Constructing Neural Networks Through Random Mutation}, author = {Samuel Schmidgall}, url = {https://arxiv.org/abs/2103.15692}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.15692}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2103.15692 Close
1000.	He, Yufan; Yang, Dong; Roth, Holger; Zhao, Can; Xu, Daguang DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2103-15954, title = {DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation}, author = {Yufan He and Dong Yang and Holger Roth and Can Zhao and Daguang Xu}, url = {https://arxiv.org/abs/2103.15954}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.15954}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2103.15954 Close
999.	Ge, Wanying; Panariello, Michele; Patino, Jose; Todisco, Massimiliano; Evans, Nicholas W D Partially-Connected Differentiable Architecture Search for Deepfake and Spoofing Detection Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2104-03123, title = {Partially-Connected Differentiable Architecture Search for Deepfake and Spoofing Detection}, author = {Wanying Ge and Michele Panariello and Jose Patino and Massimiliano Todisco and Nicholas W D Evans}, url = {https://arxiv.org/abs/2104.03123}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2104.03123}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2104.03123 Close
998.	Roberts, Nicholas; Khodak, Mikhail; Dao, Tri; Li, Liam; é, Christopher R; Talwalkar, Ameet Rethinking Neural Operations for Diverse Tasks Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2103-15798, title = {Rethinking Neural Operations for Diverse Tasks}, author = {Nicholas Roberts and Mikhail Khodak and Tri Dao and Liam Li and Christopher R é and Ameet Talwalkar}, url = {https://arxiv.org/abs/2103.15798}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.15798}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2103.15798 Close
997.	Yu, Kaicheng; é, Ren; Salzmann, Mathieu Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2104-05309, title = {Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search}, author = {Kaicheng Yu and Ren é and Mathieu Salzmann}, url = {https://arxiv.org/abs/2104.05309}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2104.05309}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2104.05309 Close
996.	Liu, Yukun; Li, Ta; Zhang, Pengyuan; Yan, Yonghong Improved Conformer-based End-to-End Speech Recognition Using Neural Architecture Search Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2104-05390, title = {Improved Conformer-based End-to-End Speech Recognition Using Neural Architecture Search}, author = {Yukun Liu and Ta Li and Pengyuan Zhang and Yonghong Yan}, url = {https://arxiv.org/abs/2104.05390}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2104.05390}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2104.05390 Close
995.	Cai, Shaofei; Li, Liang; Deng, Jincan; Zhang, Beichen; Zha, Zheng-Jun; Su, Li; Huang, Qingming Rethinking Graph Neural Network Search from Message-passing Technical Report 2021. Links \| BibTeX @techreport{cai2021rethinking, title = {Rethinking Graph Neural Network Search from Message-passing}, author = {Shaofei Cai and Liang Li and Jincan Deng and Beichen Zhang and Zheng-Jun Zha and Li Su and Qingming Huang}, url = {https://arxiv.org/abs/2103.14282}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2103.14282 Close
994.	Li, Yanxi ; Wen, Zean ; Wang Yunhe, ; Xu, Chang One-shot Graph Neural Architecture Search with Dynamic Search Space Inproceedings AAAI 2021, 2021. Links \| BibTeX @inproceedings{Li2021-aaai, title = {One-shot Graph Neural Architecture Search with Dynamic Search Space}, author = {Li, Yanxi and Wen, Zean and Wang, Yunhe, and Xu, Chang}, url = {https://www.aaai.org/AAAI21Papers/AAAI-3441.LiY.pdf}, year = {2021}, date = {2021-01-01}, booktitle = {AAAI 2021}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Close https://www.aaai.org/AAAI21Papers/AAAI-3441.LiY.pdf Close
993.	Wang, Chunnan; Chen, Bozhou; Li, Geng; Wang, Hongzhi FL-AGCNS: Federated Learning Framework for Automatic Graph Convolutional Network Search Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2104-04141, title = {FL-AGCNS: Federated Learning Framework for Automatic Graph Convolutional Network Search}, author = {Chunnan Wang and Bozhou Chen and Geng Li and Hongzhi Wang}, url = {https://arxiv.org/abs/2104.04141}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2104.04141}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2104.04141 Close
992.	Meng, Tianjian; Chen, Xiaohan; Jiang, Yifan; Wang, Zhangyang A Design Space Study for LISTA and Beyond Inproceedings International Conference on Learning Representations, 2021. Links \| BibTeX @inproceedings{<LineBreak>meng2021a, title = {A Design Space Study for LISTA and Beyond}, author = {Tianjian Meng and Xiaohan Chen and Yifan Jiang and Zhangyang Wang}, url = {https://openreview.net/forum?id=GMgHyUPrXa}, year = {2021}, date = {2021-01-01}, booktitle = {International Conference on Learning Representations}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Close https://openreview.net/forum?id=GMgHyUPrXa Close
991.	Lankford, Séamus Open-Source Neural Architecture Search with Ensemble and Pre-trained Networks Journal Article International Journal of Modeling and Optimization, 11 (2), pp. 33-41, 2021. Links \| BibTeX @article{lankford2021IJMO, title = {Open-Source Neural Architecture Search with Ensemble and Pre-trained Networks}, author = {Séamus Lankford}, url = {http://www.ijmo.org/vol11/774-Q304.pdf}, year = {2021}, date = {2021-01-01}, journal = {International Journal of Modeling and Optimization}, volume = {11}, number = {2}, pages = {33-41}, keywords = {}, pubstate = {published}, tppubtype = {article} } Close http://www.ijmo.org/vol11/774-Q304.pdf Close
990.	Liu, Aoming; Huang, Zehao; Huang, Zhiwu; Wang, Naiyan Direct Differentiable Augmentation Search Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2104-04282, title = {Direct Differentiable Augmentation Search}, author = {Aoming Liu and Zehao Huang and Zhiwu Huang and Naiyan Wang}, url = {https://arxiv.org/abs/2104.04282}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2104.04282}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2104.04282 Close
989.	Tashiro, Kyosuke; Takeda, Koji; Tanaka, Kanji; Tomoe, Hiroki TaylorMade VDD: Domain-adaptive Visual Defect Detector for High-mix Low-volume Production of Non-convex Cylindrical Metal Objects Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2104-04203, title = {TaylorMade VDD: Domain-adaptive Visual Defect Detector for High-mix Low-volume Production of Non-convex Cylindrical Metal Objects}, author = {Kyosuke Tashiro and Koji Takeda and Kanji Tanaka and Hiroki Tomoe}, url = {https://arxiv.org/abs/2104.04203}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2104.04203}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2104.04203 Close
988.	Peter, David; Roth, Wolfgang; Pernkopf, Franz End-to-end Keyword Spotting using Neural Architecture Search and Quantization Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2104-06666, title = {End-to-end Keyword Spotting using Neural Architecture Search and Quantization}, author = {David Peter and Wolfgang Roth and Franz Pernkopf}, url = {https://arxiv.org/abs/2104.06666}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2104.06666}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2104.06666 Close
987.	Mundt, Martin; Pliushch, Iuliia; Ramesh, Visvanathan Neural Architecture Search of Deep Priors: Towards Continual Learning without Catastrophic Interference Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2104-06788, title = {Neural Architecture Search of Deep Priors: Towards Continual Learning without Catastrophic Interference}, author = {Martin Mundt and Iuliia Pliushch and Visvanathan Ramesh}, url = {https://arxiv.org/abs/2104.06788}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2104.06788}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2104.06788 Close
986.	Ottelander, Tom Den; Dushatskiy, Arkadiy; Virgolin, Marco; Bosman, Peter A N Local Search is a Remarkably Strong Baseline for Neural Architecture Search Inproceedings Ishibuchi, Hisao; Zhang, Qingfu; Cheng, Ran; Li, Ke; Li, Hui; Wang, Handing; Zhou, Aimin (Ed.): Evolutionary Multi-Criterion Optimization - 11th International Conference, EMO 2021, Shenzhen, China, March 28-31, 2021, Proceedings, pp. 465–479, Springer, 2021. Links \| BibTeX @inproceedings{DBLP:conf/emo/OttelanderDVB21, title = {Local Search is a Remarkably Strong Baseline for Neural Architecture Search}, author = {Tom Den Ottelander and Arkadiy Dushatskiy and Marco Virgolin and Peter A N Bosman}, editor = {Hisao Ishibuchi and Qingfu Zhang and Ran Cheng and Ke Li and Hui Li and Handing Wang and Aimin Zhou}, url = {https://doi.org/10.1007/978-3-030-72062-9_37}, doi = {10.1007/978-3-030-72062-9_37}, year = {2021}, date = {2021-01-01}, booktitle = {Evolutionary Multi-Criterion Optimization - 11th International Conference, EMO 2021, Shenzhen, China, March 28-31, 2021, Proceedings}, volume = {12654}, pages = {465--479}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Close https://doi.org/10.1007/978-3-030-72062-9_37 doi:10.1007/978-3-030-72062-9_37 Close
985.	Wang, Rui; Wei, Zhihua; Ji, Shouling; Hong, Zhen EfficientTDNN: Efficient Architecture Search for Speaker Recognition in the Wild Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2103-13581, title = {EfficientTDNN: Efficient Architecture Search for Speaker Recognition in the Wild}, author = {Rui Wang and Zhihua Wei and Shouling Ji and Zhen Hong}, url = {https://arxiv.org/abs/2103.13581}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.13581}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2103.13581 Close
984.	Zhao, Huan; Yao, Quanming; -, Wei Search to aggregate neighborhood for graph neural network Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2104-06608, title = {Search to aggregate neighborhood for graph neural network}, author = {Huan Zhao and Quanming Yao and Wei -}, url = {https://arxiv.org/abs/2104.06608}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2104.06608}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2104.06608 Close
983.	Abed, H; Gyires-Tóth, B Efficient Neural Architecture Search for Long Short-Term Memory Networks Inproceedings 2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI), pp. 000287-000292, 2021. Links \| BibTeX @inproceedings{9378612, title = {Efficient Neural Architecture Search for Long Short-Term Memory Networks}, author = {H Abed and B Gyires-Tóth}, url = {https://ieeexplore.ieee.org/abstract/document/9378612}, doi = {10.1109/SAMI50585.2021.9378612}, year = {2021}, date = {2021-01-01}, booktitle = {2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)}, pages = {000287-000292}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Close https://ieeexplore.ieee.org/abstract/document/9378612 doi:10.1109/SAMI50585.2021.9378612 Close
982.	Gracheva, Ekaterina Trainless Model Performance Estimation for Neural Architecture Search Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2103-08312, title = {Trainless Model Performance Estimation for Neural Architecture Search}, author = {Ekaterina Gracheva}, url = {https://arxiv.org/abs/2103.08312}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.08312}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2103.08312 Close
981.	Wu, Xuan; Zhang, Xiuyi; Jia, Linhan; Chen, Liang; Liang, Yanchun; Zhou, You; Wu, Chunguo Neural Architecture Search based on Cartesian Genetic Programming Coding Method Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2103-07173, title = {Neural Architecture Search based on Cartesian Genetic Programming Coding Method}, author = {Xuan Wu and Xiuyi Zhang and Linhan Jia and Liang Chen and Yanchun Liang and You Zhou and Chunguo Wu}, url = {https://arxiv.org/abs/2103.07173}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.07173}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2103.07173 Close
980.	Choi, Kwanghee; Choe, Minyoung; Lee, Hyelee Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised Learning Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2103-08157, title = {Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised Learning}, author = {Kwanghee Choi and Minyoung Choe and Hyelee Lee}, url = {https://arxiv.org/abs/2103.08157}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.08157}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2103.08157 Close
979.	Luo, Xiangzhong; Liu, Di; Huai, Shuo; Liu, Weichen HSCoNAS: Hardware-Software Co-Design of Efficient DNNs via Neural Architecture Search Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2103-08325, title = {HSCoNAS: Hardware-Software Co-Design of Efficient DNNs via Neural Architecture Search}, author = {Xiangzhong Luo and Di Liu and Shuo Huai and Weichen Liu}, url = {https://arxiv.org/abs/2103.08325}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.08325}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2103.08325 Close
978.	Wang, Ruochen; Cheng, Minhao; Chen, Xiangning; Tang, Xiaocheng; Hsieh, Cho-Jui Rethinking Architecture Selection in Differentiable NAS Inproceedings International Conference on Learning Representations, 2021. Links \| BibTeX @inproceedings{<LineBreak>wang2021rethinking, title = {Rethinking Architecture Selection in Differentiable NAS}, author = {Ruochen Wang and Minhao Cheng and Xiangning Chen and Xiaocheng Tang and Cho-Jui Hsieh}, url = {https://openreview.net/forum?id=PKubaeJkw3}, year = {2021}, date = {2021-01-01}, booktitle = {International Conference on Learning Representations}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Close https://openreview.net/forum?id=PKubaeJkw3 Close
977.	-, Sian; -, Wei Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2103-07289, title = {Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator}, author = {Sian - and Wei -}, url = {https://arxiv.org/abs/2103.07289}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.07289}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2103.07289 Close
976.	Lakhmiri, Dounia; é, S Use of static surrogates in hyperparameter optimization Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2103-07963, title = {Use of static surrogates in hyperparameter optimization}, author = {Dounia Lakhmiri and S é}, url = {https://arxiv.org/abs/2103.07963}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.07963}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2103.07963 Close
975.	Inkawhich, Matthew; Inkawhich, Nathan; Davis, Eric; Li, Hai; Chen, Yiran The Untapped Potential of Off-the-Shelf Convolutional Neural Networks Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2103-09891, title = {The Untapped Potential of Off-the-Shelf Convolutional Neural Networks}, author = {Matthew Inkawhich and Nathan Inkawhich and Eric Davis and Hai Li and Yiran Chen}, url = {https://arxiv.org/abs/2103.09891}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.09891}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2103.09891 Close
974.	Chen, Zhiqiang; Xu, Ting-Bing; Liao, Weijian; Li, Zhengcheng; Li, Jinpeng; Liu, Cheng-Lin; He, Huiguang SNAP: Shaping neural architectures progressively via information density criterion Journal Article Pattern Recognition, 116 , pp. 107923, 2021, ISSN: 0031-3203. Abstract \| Links \| BibTeX @article{CHEN2021107923, title = {SNAP: Shaping neural architectures progressively via information density criterion}, author = {Zhiqiang Chen and Ting-Bing Xu and Weijian Liao and Zhengcheng Li and Jinpeng Li and Cheng-Lin Liu and Huiguang He}, url = {https://www.sciencedirect.com/science/article/pii/S0031320321001102}, doi = {https://doi.org/10.1016/j.patcog.2021.107923}, issn = {0031-3203}, year = {2021}, date = {2021-01-01}, journal = {Pattern Recognition}, volume = {116}, pages = {107923}, abstract = {Excellent neural network architecture is built on the specific target task and device. As the target task or device is different, the neural architecture we need will be different, too. Rather than redesigning or searching a brand new one, adjusting the existing architecture automatically is an alternative yet efficient way. To this end, we propose a method to Shape the existing Neural Architectures Progressively (SNAP) to adapt the target task and device better. Inspired by the streamline of water drop shaped by air resistance, we define an information density criterion (play the role of resistance) to drive the network architecture reducing the size of the part with the lowest information density. Iteratively, a more adaptive architecture will be obtained progressively in a greedy way. Theoretically, we prove that the greedy strategy is reasonable and can shape a better architecture. Because of the small adjustment of architecture each time, new architecture can inherit the parameters in old architecture to avoid retraining it from scratch. So the proposed method is very efficient in no need of high computation cost. Experimental results show that proposed method can effectively improve the given network by adjusting its architecture. And it can generate different architectures for different tasks and devices to adapt them well. Compared with search-based auto-generated neural architectures, our approach can achieve comparable or even better performance in no need of tremendous computation resources.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Close Excellent neural network architecture is built on the specific target task and device. As the target task or device is different, the neural architecture we need will be different, too. Rather than redesigning or searching a brand new one, adjusting the existing architecture automatically is an alternative yet efficient way. To this end, we propose a method to Shape the existing Neural Architectures Progressively (SNAP) to adapt the target task and device better. Inspired by the streamline of water drop shaped by air resistance, we define an information density criterion (play the role of resistance) to drive the network architecture reducing the size of the part with the lowest information density. Iteratively, a more adaptive architecture will be obtained progressively in a greedy way. Theoretically, we prove that the greedy strategy is reasonable and can shape a better architecture. Because of the small adjustment of architecture each time, new architecture can inherit the parameters in old architecture to avoid retraining it from scratch. So the proposed method is very efficient in no need of high computation cost. Experimental results show that proposed method can effectively improve the given network by adjusting its architecture. And it can generate different architectures for different tasks and devices to adapt them well. Compared with search-based auto-generated neural architectures, our approach can achieve comparable or even better performance in no need of tremendous computation resources. Close https://www.sciencedirect.com/science/article/pii/S0031320321001102 doi:https://doi.org/10.1016/j.patcog.2021.107923 Close
973.	Li, Chaojian; Yu, Zhongzhi; Fu, Yonggan; Zhang, Yongan; Zhao, Yang; You, Haoran; Yu, Qixuan; Wang, Yue; Lin, Yingyan HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark Inproceedings ICLR 2021, 2021. Links \| BibTeX @inproceedings{DBLP:journals/corr/abs-2103-10584, title = {HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark}, author = {Chaojian Li and Zhongzhi Yu and Yonggan Fu and Yongan Zhang and Yang Zhao and Haoran You and Qixuan Yu and Yue Wang and Yingyan Lin}, url = {https://arxiv.org/abs/2103.10584}, year = {2021}, date = {2021-01-01}, booktitle = {ICLR 2021}, journal = {CoRR}, volume = {abs/2103.10584}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Close https://arxiv.org/abs/2103.10584 Close
972.	Pyeon, Myeongjang; Moon, Jihwan; Hahn, Taeyoung; Kim, Gunhee SEDONA: Search for Decoupled Neural Networks toward Greedy Block-wise Learning Inproceedings International Conference on Learning Representations, 2021. Links \| BibTeX @inproceedings{<LineBreak>pyeon2021sedona, title = {SEDONA: Search for Decoupled Neural Networks toward Greedy Block-wise Learning}, author = {Myeongjang Pyeon and Jihwan Moon and Taeyoung Hahn and Gunhee Kim}, url = {https://openreview.net/forum?id=XLfdzwNKzch}, year = {2021}, date = {2021-01-01}, booktitle = {International Conference on Learning Representations}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Close https://openreview.net/forum?id=XLfdzwNKzch Close
971.	Zhou, Allan; Knowles, Tom; Finn, Chelsea Meta-learning Symmetries by Reparameterization Inproceedings International Conference on Learning Representations, 2021. Links \| BibTeX @inproceedings{<LineBreak>zhou2021metalearning, title = {Meta-learning Symmetries by Reparameterization}, author = {Allan Zhou and Tom Knowles and Chelsea Finn}, url = {https://openreview.net/forum?id=-QxT4mJdijq}, year = {2021}, date = {2021-01-01}, booktitle = {International Conference on Learning Representations}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Close https://openreview.net/forum?id=-QxT4mJdijq Close
970.	Mehrotra, Abhinav; Ramos, Alberto Gil C P; Bhattacharya, Sourav; Ł, ; Vipperla, Ravichander; Chau, Thomas; Abdelfattah, Mohamed S; Ishtiaq, Samin; Lane, Nicholas Donald NAS-Bench-ASR: Reproducible Neural Architecture Search for Speech Recognition Inproceedings International Conference on Learning Representations, 2021. Links \| BibTeX @inproceedings{<LineBreak>mehrotra2021nasbenchasr, title = {NAS-Bench-ASR: Reproducible Neural Architecture Search for Speech Recognition}, author = {Abhinav Mehrotra and Alberto Gil C P Ramos and Sourav Bhattacharya and Ł and Ravichander Vipperla and Thomas Chau and Mohamed S Abdelfattah and Samin Ishtiaq and Nicholas Donald Lane}, url = {https://openreview.net/forum?id=CU0APx9LMaL}, year = {2021}, date = {2021-01-01}, booktitle = {International Conference on Learning Representations}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Close https://openreview.net/forum?id=CU0APx9LMaL Close
969.	Zhou, Daquan; Jin, Xiaojie; Lian, Xiaochen; Yang, Linjie; Xue, Yujing; Hou, Qibin; Feng, Jiashi AutoSpace: Neural Architecture Search with Less Human Interference Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2103-11833, title = {AutoSpace: Neural Architecture Search with Less Human Interference}, author = {Daquan Zhou and Xiaojie Jin and Xiaochen Lian and Linjie Yang and Yujing Xue and Qibin Hou and Jiashi Feng}, url = {https://arxiv.org/abs/2103.11833}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.11833}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2103.11833 Close
968.	Li, Changlin; Tang, Tao; Wang, Guangrun; Peng, Jiefeng; Wang, Bing; Liang, Xiaodan; Chang, Xiaojun BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2103-12424, title = {BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search}, author = {Changlin Li and Tao Tang and Guangrun Wang and Jiefeng Peng and Bing Wang and Xiaodan Liang and Xiaojun Chang}, url = {https://arxiv.org/abs/2103.12424}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.12424}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2103.12424 Close
967.	Yan, Bin; Peng, Houwen; Wu, Kan; Wang, Dong; Fu, Jianlong; Lu, Huchuan LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search Inproceedings CVPR2021, 2021. Links \| BibTeX @inproceedings{DBLP:journals/corr/abs-2104-14545, title = {LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search}, author = {Bin Yan and Houwen Peng and Kan Wu and Dong Wang and Jianlong Fu and Huchuan Lu}, url = {https://arxiv.org/abs/2104.14545}, year = {2021}, date = {2021-01-01}, booktitle = {CVPR2021}, journal = {CoRR}, volume = {abs/2104.14545}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Close https://arxiv.org/abs/2104.14545 Close
966.	Wang, Jiahao; Shu, Han; Xia, Weihao; Yang, Yujiu; Wang, Yunhe Coarse-to-Fine Searching for Efficient Generative Adversarial Networks Technical Report 2021. Links \| BibTeX @techreport{wang2021coarsetofine, title = {Coarse-to-Fine Searching for Efficient Generative Adversarial Networks}, author = {Jiahao Wang and Han Shu and Weihao Xia and Yujiu Yang and Yunhe Wang}, url = {https://arxiv.org/abs/2104.09223}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2104.09223 Close
965.	Ahn, Joon Young; Cho, Nam Ik Neural Architecture Search for Image Super-Resolution Using Densely Constructed Search Space: DeCoNAS Technical Report 2021. Links \| BibTeX @techreport{ahn2021neural, title = {Neural Architecture Search for Image Super-Resolution Using Densely Constructed Search Space: DeCoNAS}, author = {Joon Young Ahn and Nam Ik Cho}, url = {https://arxiv.org/abs/2104.09048}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2104.09048 Close
964.	Lu, Zexin; Xia, Wenjun; Huang, Yongqiang; Shan, Hongming; Chen, Hu; Zhou, Jiliu; Zhang, Yi MANAS: Multi-Scale and Multi-Level Neural Architecture Search for Low-Dose CT Denoising Journal Article CoRR, abs/2103.12995 , 2021. Links \| BibTeX @article{DBLP:journals/corr/abs-2103-12995, title = {MANAS: Multi-Scale and Multi-Level Neural Architecture Search for Low-Dose CT Denoising}, author = {Zexin Lu and Wenjun Xia and Yongqiang Huang and Hongming Shan and Hu Chen and Jiliu Zhou and Yi Zhang}, url = {https://arxiv.org/abs/2103.12995}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.12995}, keywords = {}, pubstate = {published}, tppubtype = {article} } Close https://arxiv.org/abs/2103.12995 Close
963.	Yin, Yihang; Huang, Siyu; Zhang, Xiang; Dou, Dejing BM-NAS: Bilevel Multimodal Neural Architecture Search Technical Report 2021. Links \| BibTeX @techreport{yin2021bmnas, title = {BM-NAS: Bilevel Multimodal Neural Architecture Search}, author = {Yihang Yin and Siyu Huang and Xiang Zhang and Dejing Dou}, url = {https://arxiv.org/abs/2104.09379}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2104.09379 Close
962.	Su, Xiu; Huang, Tao; Li, Yanxi; You, Shan; Wang, Fei; Qian, Chen; Zhang, Changshui; Xu, Chang Prioritized Architecture Sampling with Monto-Carlo Tree Search Technical Report , 2021. Links \| BibTeX @techreport{DBLP:journals/corr/abs-2103-11922, title = {Prioritized Architecture Sampling with Monto-Carlo Tree Search}, author = {Xiu Su and Tao Huang and Yanxi Li and Shan You and Fei Wang and Chen Qian and Changshui Zhang and Chang Xu}, url = {https://arxiv.org/abs/2103.11922}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.11922}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } Close https://arxiv.org/abs/2103.11922 Close

1111 entries « ‹ 3 of 23 › »

Literature on Neural Architecture Search

2021