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.
2021 |
|
| 1189. | Luo, Xiangzhong; Liu, Di; Huai, Shuo; Liu, Weichen HSCoNAS: Hardware-Software Co-Design of Efficient DNNs via Neural Architecture Search Technical Report , 2021. @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} } |
| 1188. | 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. @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} } |
| 1187. | Gracheva, Ekaterina Trainless Model Performance Estimation for Neural Architecture Search Technical Report , 2021. @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} } |
| 1186. | Choi, Kwanghee; Choe, Minyoung; Lee, Hyelee Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised Learning Technical Report , 2021. @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} } |
| 1185. | Ban, Hao; Xie, Pengtao Interleaving Learning, with Application to Neural Architecture Search Technical Report , 2021. @techreport{DBLP:journals/corr/abs-2103-07018, title = {Interleaving Learning, with Application to Neural Architecture Search}, author = {Hao Ban and Pengtao Xie}, url = {https://arxiv.org/abs/2103.07018}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.07018}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1184. | Liu, Xiaobo; Zhang, Chaochao; Cai, Zhihua; Yang, Jianfeng; Zhou, Zhilang; Gong, Xin Continuous Particle Swarm Optimization-Based Deep Learning Architecture Search for Hyperspectral Image Classification Journal Article Remote Sensing, 13 (6), 2021, ISSN: 2072-4292. @article{rs13061082, title = {Continuous Particle Swarm Optimization-Based Deep Learning Architecture Search for Hyperspectral Image Classification}, author = {Xiaobo Liu and Chaochao Zhang and Zhihua Cai and Jianfeng Yang and Zhilang Zhou and Xin Gong}, url = {https://www.mdpi.com/2072-4292/13/6/1082}, doi = {10.3390/rs13061082}, issn = {2072-4292}, year = {2021}, date = {2021-01-01}, journal = {Remote Sensing}, volume = {13}, number = {6}, abstract = {Deep convolutional neural networks (CNNs) are widely used in hyperspectral image (HSI) classification. However, the most successful CNN architectures are handcrafted, which need professional knowledge and consume a very significant amount of time. To automatically design cell-based CNN architectures for HSI classification, we propose an efficient continuous evolutionary method, named CPSO-Net, which can dramatically accelerate optimal architecture generation by the optimization of weight-sharing parameters. First, a SuperNet with all candidate operations is maintained to share the parameters for all individuals and optimized by collecting the gradients of all individuals in the population. Second, a novel direct encoding strategy is devised to encode architectures into particles, which inherit the parameters from the SuperNet. Then, particle swarm optimization is used to search for the optimal deep architecture from the particle swarm. Furthermore, experiments with limited training samples based on four widely used biased and unbiased hyperspectral datasets showed that our proposed method achieves good performance comparable to the state-of-the-art HSI classification methods.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Deep convolutional neural networks (CNNs) are widely used in hyperspectral image (HSI) classification. However, the most successful CNN architectures are handcrafted, which need professional knowledge and consume a very significant amount of time. To automatically design cell-based CNN architectures for HSI classification, we propose an efficient continuous evolutionary method, named CPSO-Net, which can dramatically accelerate optimal architecture generation by the optimization of weight-sharing parameters. First, a SuperNet with all candidate operations is maintained to share the parameters for all individuals and optimized by collecting the gradients of all individuals in the population. Second, a novel direct encoding strategy is devised to encode architectures into particles, which inherit the parameters from the SuperNet. Then, particle swarm optimization is used to search for the optimal deep architecture from the particle swarm. Furthermore, experiments with limited training samples based on four widely used biased and unbiased hyperspectral datasets showed that our proposed method achieves good performance comparable to the state-of-the-art HSI classification methods. |
| 1183. | Zhang, Shi-Xin; Hsieh, Chang-Yu; Zhang, Shengyu; Yao, Hong Neural Predictor based Quantum Architecture Search Technical Report 2021. @techreport{zhang2021neural, title = {Neural Predictor based Quantum Architecture Search}, author = {Shi-Xin Zhang and Chang-Yu Hsieh and Shengyu Zhang and Hong Yao}, url = {https://arxiv.org/abs/2103.06524}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1182. | Cao, Shengcao; Wang, Xiaofang; Kitani, Kris Efficient Model Performance Estimation via Feature Histories Technical Report , 2021. @techreport{DBLP:journals/corr/abs-2103-04450, title = {Efficient Model Performance Estimation via Feature Histories}, author = {Shengcao Cao and Xiaofang Wang and Kris Kitani}, url = {https://arxiv.org/abs/2103.04450}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2103.04450}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1181. | Liang, Tingting; Wang, Yongtao; Tang, Zhi; Hu, Guosheng; Ling, Haibin OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection Technical Report 2021. @techreport{liang2021opanas, title = {OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection}, author = {Tingting Liang and Yongtao Wang and Zhi Tang and Guosheng Hu and Haibin Ling}, url = {https://arxiv.org/abs/2103.04507}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1180. | Zhang, Kaiyu; Chen, Jinglong; He, Shuilong; Xu, Enyong; Li, Fudong; Zhou, Zitong Mechanical Systems and Signal Processing, 158 , pp. 107773, 2021, ISSN: 0888-3270. @article{ZHANG2021107773, title = {Differentiable neural architecture search augmented with pruning and multi-objective optimization for time-efficient intelligent fault diagnosis of machinery}, author = {Kaiyu Zhang and Jinglong Chen and Shuilong He and Enyong Xu and Fudong Li and Zitong Zhou}, url = {https://www.sciencedirect.com/science/article/pii/S0888327021001680}, doi = {https://doi.org/10.1016/j.ymssp.2021.107773}, issn = {0888-3270}, year = {2021}, date = {2021-01-01}, journal = {Mechanical Systems and Signal Processing}, volume = {158}, pages = {107773}, abstract = {Intelligent fault diagnosis, which is mainly based on neural network, has been widely used in machinery monitoring. Although such deep learning methods are effective, the new architectures are mainly handcrafted by series of experiments that require ample time and substantial efforts. To automate process of building neural networks and save designing time, a novel differentiable neural architecture search method is proposed. By gradually reducing candidate operations while retaining trained parameters during pruning, computation consumed by each stage of neural architecture search is decreased, which accelerates search process. To improve inferential efficiency of subnetworks, specially designed penalty terms are introduced into the objective function for searching optimal numbers of layers and nodes, which can reduce complexity of subnetworks and save calculation time of signal analysis. In addition, exclusive competition between candidate operations is broken by changing discretization and selection methods of operations, which provides a basis for channel fusion. Effectiveness of the proposed method is verified by two datasets. Experiments show that this method can generate subnetworks of lower complexity and less computational cost than other state-of-art neural architecture search techniques, while achieving competitive result.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Intelligent fault diagnosis, which is mainly based on neural network, has been widely used in machinery monitoring. Although such deep learning methods are effective, the new architectures are mainly handcrafted by series of experiments that require ample time and substantial efforts. To automate process of building neural networks and save designing time, a novel differentiable neural architecture search method is proposed. By gradually reducing candidate operations while retaining trained parameters during pruning, computation consumed by each stage of neural architecture search is decreased, which accelerates search process. To improve inferential efficiency of subnetworks, specially designed penalty terms are introduced into the objective function for searching optimal numbers of layers and nodes, which can reduce complexity of subnetworks and save calculation time of signal analysis. In addition, exclusive competition between candidate operations is broken by changing discretization and selection methods of operations, which provides a basis for channel fusion. Effectiveness of the proposed method is verified by two datasets. Experiments show that this method can generate subnetworks of lower complexity and less computational cost than other state-of-art neural architecture search techniques, while achieving competitive result. |
| 1179. | Chen, Yaofo; Guo, Yong; Chen, Qi; Li, Minli; Wang, Yaowei; Zeng, Wei; Tan, Mingkui Contrastive Neural Architecture Search with Neural Architecture Comparators Inproceedings CVPR2021, 2021. @inproceedings{DBLP:journals/corr/abs-2103-05471, title = {Contrastive Neural Architecture Search with Neural Architecture Comparators}, author = {Yaofo Chen and Yong Guo and Qi Chen and Minli Li and Yaowei Wang and Wei Zeng and Mingkui Tan}, url = {https://arxiv.org/abs/2103.05471}, year = {2021}, date = {2021-01-01}, booktitle = {CVPR2021}, journal = {CoRR}, volume = {abs/2103.05471}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 1178. | Javeri, Indrajeet Y; Toutiaee, Mohammadhossein; Arpinar, Ismailcem B; Miller, Tom W; Miller, John A Improving Neural Networks for Time Series Forecasting using Data Augmentation and AutoML Technical Report 2021. @techreport{javeri2021improving, title = {Improving Neural Networks for Time Series Forecasting using Data Augmentation and AutoML}, author = {Indrajeet Y Javeri and Mohammadhossein Toutiaee and Ismailcem B Arpinar and Tom W Miller and John A Miller}, url = {https://arxiv.org/abs/2103.01992}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1177. | Guo, Qingbei; Wu, Xiao-Jun; Kittler, Josef; Feng, Zhiquan Differentiable Neural Architecture Learning for Efficient Neural Network Design Technical Report 2021. @techreport{guo2021differentiable, title = {Differentiable Neural Architecture Learning for Efficient Neural Network Design}, author = {Qingbei Guo and Xiao-Jun Wu and Josef Kittler and Zhiquan Feng}, url = {https://arxiv.org/abs/2103.02126}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1176. | Liu, Luyan; Wen, Zhiwei; Liu, Songwei; Zhou, Hong-Yu; Zhu, Hongwei; Xie, Weicheng; Shen, Linlin; Ma, Kai; Zheng, Yefeng MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures Technical Report 2021. @techreport{liu2021mixsearch, title = {MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures}, author = {Luyan Liu and Zhiwei Wen and Songwei Liu and Hong-Yu Zhou and Hongwei Zhu and Weicheng Xie and Linlin Shen and Kai Ma and Yefeng Zheng}, url = {https://arxiv.org/abs/2102.13280}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1175. | Zhang, Ziwei; Wang, Xin; Zhu, Wenwu Automated Machine Learning on Graphs: A Survey Technical Report 2021. @techreport{zhang2021automated, title = {Automated Machine Learning on Graphs: A Survey}, author = {Ziwei Zhang and Xin Wang and Wenwu Zhu}, url = {https://arxiv.org/abs/2103.00742}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1174. | Jeong, Wonyong; Lee, Hayeon; Park, Gun; Hyung, Eunyoung; Baek, Jinheon; Hwang, Sung Ju Task-Adaptive Neural Network Retrieval with Meta-Contrastive Learning Technical Report 2021. @techreport{jeong2021taskadaptive, title = {Task-Adaptive Neural Network Retrieval with Meta-Contrastive Learning}, author = {Wonyong Jeong and Hayeon Lee and Gun Park and Eunyoung Hyung and Jinheon Baek and Sung Ju Hwang}, url = {https://arxiv.org/abs/2103.01495}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1173. | Guo, Yong; Chen, Yaofo; Zheng, Yin; Chen, Qi; Zhao, Peilin; Chen, Jian; Huang, Junzhou; Tan, Mingkui Pareto-Frontier-aware Neural Architecture Generation for Diverse Budgets Technical Report 2021. @techreport{guo2021paretofrontieraware, title = {Pareto-Frontier-aware Neural Architecture Generation for Diverse Budgets}, author = {Yong Guo and Yaofo Chen and Yin Zheng and Qi Chen and Peilin Zhao and Jian Chen and Junzhou Huang and Mingkui Tan}, url = {https://arxiv.org/abs/2103.00219}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1172. | Le, Cat P; Soltani, Mohammadreza; Ravier, Robert; Tarokh, Vahid Neural Architecture Search From Task Similarity Measure Technical Report 2021. @techreport{le2021neural, title = {Neural Architecture Search From Task Similarity Measure}, author = {Cat P Le and Mohammadreza Soltani and Robert Ravier and Vahid Tarokh}, url = {https://arxiv.org/abs/2103.00241}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1171. | Xie, Guoyang; Wang, Jinbao; Yu, Guo; Zheng, Feng; Jin, Yaochu Tiny Adversarial Mulit-Objective Oneshot Neural Architecture Search Technical Report 2021. @techreport{xie2021tiny, title = {Tiny Adversarial Mulit-Objective Oneshot Neural Architecture Search}, author = {Guoyang Xie and Jinbao Wang and Guo Yu and Feng Zheng and Yaochu Jin}, url = {https://arxiv.org/abs/2103.00363}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1170. | Zhang, T; Lei, C; Zhang, Z; Meng, X -B; Chen, C L P AS-NAS: Adaptive Scalable Neural Architecture Search with Reinforced Evolutionary Algorithm for Deep Learning Journal Article IEEE Transactions on Evolutionary Computation, pp. 1-1, 2021. @article{9360872, title = {AS-NAS: Adaptive Scalable Neural Architecture Search with Reinforced Evolutionary Algorithm for Deep Learning}, author = {T Zhang and C Lei and Z Zhang and X -B Meng and C L P Chen}, url = {https://ieeexplore.ieee.org/abstract/document/9360872}, doi = {10.1109/TEVC.2021.3061466}, year = {2021}, date = {2021-01-01}, journal = {IEEE Transactions on Evolutionary Computation}, pages = {1-1}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
| 1169. | Chen, J; Jiang, Y; Huang, Z; Guo, X; Wu, B; Sun, L; Wu, T Fine-Grained Detection of Driver Distraction Based on Neural Architecture Search Journal Article IEEE Transactions on Intelligent Transportation Systems, pp. 1-19, 2021. @article{9352235, title = {Fine-Grained Detection of Driver Distraction Based on Neural Architecture Search}, author = {J Chen and Y Jiang and Z Huang and X Guo and B Wu and L Sun and T Wu}, url = {https://ieeexplore.ieee.org/abstract/document/9352235}, doi = {10.1109/TITS.2021.3055545}, year = {2021}, date = {2021-01-01}, journal = {IEEE Transactions on Intelligent Transportation Systems}, pages = {1-19}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
| 1168. | Zhang, Zijun; Cofer, Evan M; Troyanskaya, Olga G AMBIENT: Accelerated Convolutional Neural Network Architecture Search for Regulatory Genomics Inproceedings Machine Learning in Computational Biology (MLCB 2020), 2021. @inproceedings{ZhangMLCB2020, title = {AMBIENT: Accelerated Convolutional Neural Network Architecture Search for Regulatory Genomics}, author = {Zijun Zhang and Evan M. Cofer and Olga G. Troyanskaya}, url = {https://www.biorxiv.org/content/biorxiv/early/2021/02/27/2021.02.25.432960.full.pdf}, year = {2021}, date = {2021-01-01}, booktitle = {Machine Learning in Computational Biology (MLCB 2020)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 1167. | Wu, Junru; Dai, Xiyang; Chen, Dongdong; Chen, Yinpeng; Liu, Mengchen; Yu, Ye; Wang, Zhangyang; Liu, Zicheng; Chen, Mei; Yuan, Lu Weak NAS Predictors Are All You Need Technical Report 2021. @techreport{wu2021weak, title = {Weak NAS Predictors Are All You Need}, author = {Junru Wu and Xiyang Dai and Dongdong Chen and Yinpeng Chen and Mengchen Liu and Ye Yu and Zhangyang Wang and Zicheng Liu and Mei Chen and Lu Yuan}, url = {https://arxiv.org/abs/2102.10490}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1166. | Guo, Yong; Zheng, Yin; Tan, Mingkui; Chen, Qi; Li, Zhipeng; Chen, Jian; Zhao, Peilin; Huang, Junzhou Towards Accurate and Compact Architectures via Neural Architecture Transformer Technical Report 2021. @techreport{guo2021accurate, title = {Towards Accurate and Compact Architectures via Neural Architecture Transformer}, author = {Yong Guo and Yin Zheng and Mingkui Tan and Qi Chen and Zhipeng Li and Jian Chen and Peilin Zhao and Junzhou Huang}, url = {https://arxiv.org/abs/2102.10301}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1165. | Nguyen, Nam; Chang, Morris J Contrastive Self-supervised Neural Architecture Search Miscellaneous 2021. @misc{nguyen2021contrastive, title = {Contrastive Self-supervised Neural Architecture Search}, author = {Nam Nguyen and Morris J Chang}, url = {https://arxiv.org/abs/2102.10557}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {misc} } |
| 1164. | Nayman, Niv; Aflalo, Yonathan; Noy, Asaf; Zelnik-Manor, Lihi HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search Technical Report 2021. @techreport{nayman2021hardcore, title = {HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search}, author = {Niv Nayman and Yonathan Aflalo and Asaf Noy and Lihi Zelnik-Manor}, url = {https://arxiv.org/abs/2102.11646}, year = {2021}, date = {2021-01-01}, journal = {arXiv preprint arXiv:2102.11646}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1163. | Lu, Longfei; Lyu, Bo Reducing energy consumption of Neural Architecture Search: An inference latency prediction framework Journal Article Sustainable Cities and Society, 67 , pp. 102747, 2021, ISSN: 2210-6707. @article{LU2021102747, title = {Reducing energy consumption of Neural Architecture Search: An inference latency prediction framework}, author = {Longfei Lu and Bo Lyu}, url = {https://www.sciencedirect.com/science/article/pii/S221067072100041X}, doi = {https://doi.org/10.1016/j.scs.2021.102747}, issn = {2210-6707}, year = {2021}, date = {2021-01-01}, journal = {Sustainable Cities and Society}, volume = {67}, pages = {102747}, abstract = {Benefit from the success of NAS (Neural Architecture Search) in deep learning, humans are hopefully been released from the tremendous labor of manual tuning of structure and hyper-parameters. However, the success of NAS comes at the cost of much more computational resource consumption, thousands of times more computational power than ordinary training of manual-designed models, especially for the resource-aware multi-objective NAS, which must be serialized as a sequential loop of sampling, training, deployment, and inference. Recent research has shown that deep learning leads to huge energy consumption and CO2 emission (training of the namely Transformer can emit CO2 as much as five cars in their lifetimes Strubell et al. (2019)). Aiming to alleviate this issue, we propose the end-to-end inference latency prediction framework to empower the NAS process with a direct resource-aware efficiency indicator. Namely, we first propose the end-to-end latency prediction framework, which can predict latency quickly and accurately based on the dataset collected by ourselves. Eventually, we experimentally show that with the encoding scheme we designed, our proposed best model, LSTM-GBDT Latency Predictor(LGLP) achieves an excellent result of 0.9349 MSE, 0.5249 MAE, 0.9842 R2, and 0.9925 corrcoef. In other words, our limited dataset and encoding scheme already provide the precise knowledge representation of this large search space. By equipping NAS with the proposed framework, taking NEMO for example, it will save 1588 kWh⋅PUE energy, 1515 pounds CO2 emissions, and $3176 cloud compute cost of AWS. For NAS is now widely exploited in research or industry applications, this will bring incalculable benefits to society and the environment.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Benefit from the success of NAS (Neural Architecture Search) in deep learning, humans are hopefully been released from the tremendous labor of manual tuning of structure and hyper-parameters. However, the success of NAS comes at the cost of much more computational resource consumption, thousands of times more computational power than ordinary training of manual-designed models, especially for the resource-aware multi-objective NAS, which must be serialized as a sequential loop of sampling, training, deployment, and inference. Recent research has shown that deep learning leads to huge energy consumption and CO2 emission (training of the namely Transformer can emit CO2 as much as five cars in their lifetimes Strubell et al. (2019)). Aiming to alleviate this issue, we propose the end-to-end inference latency prediction framework to empower the NAS process with a direct resource-aware efficiency indicator. Namely, we first propose the end-to-end latency prediction framework, which can predict latency quickly and accurately based on the dataset collected by ourselves. Eventually, we experimentally show that with the encoding scheme we designed, our proposed best model, LSTM-GBDT Latency Predictor(LGLP) achieves an excellent result of 0.9349 MSE, 0.5249 MAE, 0.9842 R2, and 0.9925 corrcoef. In other words, our limited dataset and encoding scheme already provide the precise knowledge representation of this large search space. By equipping NAS with the proposed framework, taking NEMO for example, it will save 1588 kWh⋅PUE energy, 1515 pounds CO2 emissions, and $3176 cloud compute cost of AWS. For NAS is now widely exploited in research or industry applications, this will bring incalculable benefits to society and the environment. |
| 1162. | Song, Xingyou; Choromanski, Krzysztof; Parker-Holder, Jack; Tang, Yunhao; Peng, Daiyi; Jain, Deepali; Gao, Wenbo; Pacchiano, Aldo; Sarlós, Tamás; Yang, Yuxiang ES-ENAS - Combining Evolution Strategies with Neural Architecture Search at No Extra Cost for Reinforcement Learning Technical Report , 2021. @techreport{Song2021_xto, title = {ES-ENAS - Combining Evolution Strategies with Neural Architecture Search at No Extra Cost for Reinforcement Learning}, author = {Xingyou Song and Krzysztof Choromanski and Jack Parker-Holder and Yunhao Tang and Daiyi Peng and Deepali Jain and Wenbo Gao and Aldo Pacchiano and Tamás Sarlós and Yuxiang Yang}, url = {https://arxiv.org/abs/1611.01578}, year = {2021}, date = {2021-01-01}, volume = {abs/2101.07415}, key = {journals/corr/abs-2101-07415}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1161. | Rorabaugh, Ariel Keller; -, Silvina Caíno; II, Michael Wyatt R; Johnston, Travis; Taufer, Michela PEng4NN: An Accurate Performance Estimation Engine for Efficient Automated Neural Network Architecture Search Technical Report , 2021. @techreport{ArielKellerRorabaugh2021_ncl, title = {PEng4NN: An Accurate Performance Estimation Engine for Efficient Automated Neural Network Architecture Search}, author = {Ariel Keller Rorabaugh and Silvina Caíno - and Michael Wyatt R II and Travis Johnston and Michela Taufer}, url = {https://arxiv.org/abs/2101.04185}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2101.04185}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1160. | Zhang, Haokui; Gong, Chengrong; Bai, Yunpeng; Bai, Zongwen; Li, Ying 3D-ANAS: 3D Asymmetric Neural Architecture Search for Fast Hyperspectral Image Classification Miscellaneous 2021. @misc{HaokuiZhang2021_uqt, title = {3D-ANAS: 3D Asymmetric Neural Architecture Search for Fast Hyperspectral Image Classification}, author = {Haokui Zhang and Chengrong Gong and Yunpeng Bai and Zongwen Bai and Ying Li}, url = {https://arxiv.org/abs/2101.04287}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2101.04287}, keywords = {}, pubstate = {published}, tppubtype = {misc} } |
| 1159. | Wei, Tao; Wang, Changhu; Chen, Chang Wen Modularized Morphing of Deep Convolutional Neural Networks - A Graph Approach Journal Article 70 (2), pp. 305-315, 2021. @article{Wei2021_ghp, title = {Modularized Morphing of Deep Convolutional Neural Networks - A Graph Approach}, author = {Tao Wei and Changhu Wang and Chang Wen Chen}, url = {https://arxiv.org/abs/1701.03281}, doi = {10.1109/TC.2020.2988006}, year = {2021}, date = {2021-01-01}, volume = {70}, number = {2}, pages = {305-315}, key = {journals/tc/WeiWC21}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
| 1158. | Gu, Hongyang; Fu, Guangyuan; Li, Jianmin; Zhu, Jun Auto-ReID+: Searching for a multi-branch ConvNet for person re-identification Journal Article Neurocomputing, 435 , pp. 53-66, 2021, ISSN: 0925-2312. @article{HongyangGu2021_bui, title = {Auto-ReID+: Searching for a multi-branch ConvNet for person re-identification}, author = {Hongyang Gu and Guangyuan Fu and Jianmin Li and Jun Zhu}, url = {https://www.sciencedirect.com/science/article/pii/S0925231220320178}, doi = {https://doi.org/10.1016/j.neucom.2020.12.105}, issn = {0925-2312}, year = {2021}, date = {2021-01-01}, journal = {Neurocomputing}, volume = {435}, pages = {53-66}, abstract = {In the field of person re-identification (ReID), multi-branch models are more effective in learning robust features than single-branch models. The current popular multi-branch models are based on ResNet or GoogleNet. These networks are designed initially to solve classification problems. There is an essential difference between ReID and classification problems, so it is particularly important to find a corresponding multi-branch backbone for ReID tasks. We propose to automatically search for a multi-branch convolutional neural network (CNN) for ReID tasks utilizing neural architecture search (NAS). First, we designed a multi-resolution, multi-branch macro search architecture that can extract more abundant scale information. Then in the searching process, the early stopping mechanism is proposed to improve the effectiveness and efficiency of the entire searching process. Finally, we experimentally prove on four mainstream datasets that the searched model can achieve state-of-the-art performance with only 5.7 million parameters.}, keywords = {}, pubstate = {published}, tppubtype = {article} } In the field of person re-identification (ReID), multi-branch models are more effective in learning robust features than single-branch models. The current popular multi-branch models are based on ResNet or GoogleNet. These networks are designed initially to solve classification problems. There is an essential difference between ReID and classification problems, so it is particularly important to find a corresponding multi-branch backbone for ReID tasks. We propose to automatically search for a multi-branch convolutional neural network (CNN) for ReID tasks utilizing neural architecture search (NAS). First, we designed a multi-resolution, multi-branch macro search architecture that can extract more abundant scale information. Then in the searching process, the early stopping mechanism is proposed to improve the effectiveness and efficiency of the entire searching process. Finally, we experimentally prove on four mainstream datasets that the searched model can achieve state-of-the-art performance with only 5.7 million parameters. |
| 1157. | He, Xin; Wang, Shihao; Chu, Xiaowen; Shi, Shaohuai; Tang, Jiangping; Liu, Xin; Yan, Chenggang; Zhang, Jiyong; Ding, Guiguang Automated Model Design and Benchmarking of 3D Deep Learning Models for COVID-19 Detection with Chest CT Scans Technical Report , 2021. @techreport{DBLP:journals/corr/abs-2101-05442, title = {Automated Model Design and Benchmarking of 3D Deep Learning Models for COVID-19 Detection with Chest CT Scans}, author = {Xin He and Shihao Wang and Xiaowen Chu and Shaohuai Shi and Jiangping Tang and Xin Liu and Chenggang Yan and Jiyong Zhang and Guiguang Ding}, url = {https://arxiv.org/abs/2101.05442}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2101.05442}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1156. | Zhou, Benjia; Li, Yunan; Wan, Jun Regional Attention with Architecture-Rebuilt 3D Network for RGB-D Gesture Recognition Technical Report 2021. @techreport{zhou2021regional, title = {Regional Attention with Architecture-Rebuilt 3D Network for RGB-D Gesture Recognition}, author = {Benjia Zhou and Yunan Li and Jun Wan}, url = {https://arxiv.org/abs/2102.05348}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1155. | Yang, Zhao; Zhang, Shengbing; Li, Ruxu; Li, Chuxi; Wang, Miao; Wang, Danghui; Zhang, Meng Efficient Resource-Aware Convolutional Neural Architecture Search for Edge Computing with Pareto-Bayesian Optimization Journal Article Sensors, 21 (2), 2021, ISSN: 1424-8220. @article{s21020444, title = {Efficient Resource-Aware Convolutional Neural Architecture Search for Edge Computing with Pareto-Bayesian Optimization}, author = {Zhao Yang and Shengbing Zhang and Ruxu Li and Chuxi Li and Miao Wang and Danghui Wang and Meng Zhang}, url = {https://www.mdpi.com/1424-8220/21/2/444}, doi = {10.3390/s21020444}, issn = {1424-8220}, year = {2021}, date = {2021-01-01}, journal = {Sensors}, volume = {21}, number = {2}, abstract = {With the development of deep learning technologies and edge computing, the combination of them can make artificial intelligence ubiquitous. Due to the constrained computation resources of the edge device, the research in the field of on-device deep learning not only focuses on the model accuracy but also on the model efficiency, for example, inference latency. There are many attempts to optimize the existing deep learning models for the purpose of deploying them on the edge devices that meet specific application requirements while maintaining high accuracy. Such work not only requires professional knowledge but also needs a lot of experiments, which limits the customization of neural networks for varied devices and application scenarios. In order to reduce the human intervention in designing and optimizing the neural network structure, multi-objective neural architecture search methods that can automatically search for neural networks featured with high accuracy and can satisfy certain hardware performance requirements are proposed. However, the current methods commonly set accuracy and inference latency as the performance indicator during the search process, and sample numerous network structures to obtain the required neural network. Lacking regulation to the search direction with the search objectives will generate a large number of useless networks during the search process, which influences the search efficiency to a great extent. Therefore, in this paper, an efficient resource-aware search method is proposed. Firstly, the network inference consumption profiling model for any specific device is established, and it can help us directly obtain the resource consumption of each operation in the network structure and the inference latency of the entire sampled network. Next, on the basis of the Bayesian search, a resource-aware Pareto Bayesian search is proposed. Accuracy and inference latency are set as the constraints to regulate the search direction. With a clearer search direction, the overall search efficiency will be improved. Furthermore, cell-based structure and lightweight operation are applied to optimize the search space for further enhancing the search efficiency. The experimental results demonstrate that with our method, the inference latency of the searched network structure reduced 94.71% without scarifying the accuracy. At the same time, the search efficiency increased by 18.18%.}, keywords = {}, pubstate = {published}, tppubtype = {article} } With the development of deep learning technologies and edge computing, the combination of them can make artificial intelligence ubiquitous. Due to the constrained computation resources of the edge device, the research in the field of on-device deep learning not only focuses on the model accuracy but also on the model efficiency, for example, inference latency. There are many attempts to optimize the existing deep learning models for the purpose of deploying them on the edge devices that meet specific application requirements while maintaining high accuracy. Such work not only requires professional knowledge but also needs a lot of experiments, which limits the customization of neural networks for varied devices and application scenarios. In order to reduce the human intervention in designing and optimizing the neural network structure, multi-objective neural architecture search methods that can automatically search for neural networks featured with high accuracy and can satisfy certain hardware performance requirements are proposed. However, the current methods commonly set accuracy and inference latency as the performance indicator during the search process, and sample numerous network structures to obtain the required neural network. Lacking regulation to the search direction with the search objectives will generate a large number of useless networks during the search process, which influences the search efficiency to a great extent. Therefore, in this paper, an efficient resource-aware search method is proposed. Firstly, the network inference consumption profiling model for any specific device is established, and it can help us directly obtain the resource consumption of each operation in the network structure and the inference latency of the entire sampled network. Next, on the basis of the Bayesian search, a resource-aware Pareto Bayesian search is proposed. Accuracy and inference latency are set as the constraints to regulate the search direction. With a clearer search direction, the overall search efficiency will be improved. Furthermore, cell-based structure and lightweight operation are applied to optimize the search space for further enhancing the search efficiency. The experimental results demonstrate that with our method, the inference latency of the searched network structure reduced 94.71% without scarifying the accuracy. At the same time, the search efficiency increased by 18.18%. |
| 1154. | Weng, Yu; Chen, Zehua; Zhou, Tianbao Improved differentiable neural architecture search for single image super-resolution Journal Article Peer-to-Peer Networking and Applications, 2021. @article{journals/PPNA/Weng21, title = {Improved differentiable neural architecture search for single image super-resolution}, author = {Yu Weng and Zehua Chen and Tianbao Zhou}, url = {https://doi.org/10.1007/s12083-020-01048-4}, doi = {10.1007/s12083-020-01048-4}, year = {2021}, date = {2021-01-01}, journal = {Peer-to-Peer Networking and Applications}, abstract = {Deep learning has shown prominent superiority over other machine learning algorithms in Single Image Super-Resolution (SISR). In order to reduce the efforts and resources cost on manually designing deep architecture, we use differentiable neural architecture search (DARTS) on SISR. Since neural architecture search was originally used for classification tasks, our experiments show that direct usage of DARTS on super-resolutions tasks will give rise to many skip connections in the search architecture, which results in the poor performance of final architecture. Thus, it is necessary for DARTS to have made some improvements for the application in the field of SISR. According to characteristics of SISR, we remove redundant operations and redesign some operations in the cell to achieve an improved DARTS. Then we use the improved DARTS to search convolution cells as a nonlinear mapping part of super-resolution network. The new super-resolution architecture shows its effectiveness on benchmark datasets and DIV2K dataset.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Deep learning has shown prominent superiority over other machine learning algorithms in Single Image Super-Resolution (SISR). In order to reduce the efforts and resources cost on manually designing deep architecture, we use differentiable neural architecture search (DARTS) on SISR. Since neural architecture search was originally used for classification tasks, our experiments show that direct usage of DARTS on super-resolutions tasks will give rise to many skip connections in the search architecture, which results in the poor performance of final architecture. Thus, it is necessary for DARTS to have made some improvements for the application in the field of SISR. According to characteristics of SISR, we remove redundant operations and redesign some operations in the cell to achieve an improved DARTS. Then we use the improved DARTS to search convolution cells as a nonlinear mapping part of super-resolution network. The new super-resolution architecture shows its effectiveness on benchmark datasets and DIV2K dataset. |
| 1153. | Liu, Jia; Jin, Yaochu Multi-objective Search of Robust Neural Architectures against Multiple Types of Adversarial Attacks Technical Report , 2021. @techreport{DBLP:journals/corr/abs-2101-06507, title = {Multi-objective Search of Robust Neural Architectures against Multiple Types of Adversarial Attacks}, author = {Jia Liu and Yaochu Jin}, url = {https://arxiv.org/abs/2101.06507}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2101.06507}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1152. | Wu, Yan; Huang, Zhiwu; Kumar, Suryansh; Sukthanker, Rhea Sanjay; Timofte, Radu; Gool, Luc Van Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution Technical Report , 2021. @techreport{DBLP:journals/corr/abs-2101-06658, title = {Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution}, author = {Yan Wu and Zhiwu Huang and Suryansh Kumar and Rhea Sanjay Sukthanker and Radu Timofte and Luc Van Gool}, url = {https://arxiv.org/abs/2101.06658}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2101.06658}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1151. | Alparslan, Yigit; Moyer, Ethan Jacob; Isozaki, Isamu Mclean; Schwartz, Daniel; Dunlop, Adam; Dave, Shesh; Kim, Edward Towards Searching Efficient and Accurate Neural Network Architectures in Binary Classification Problems Technical Report , 2021. @techreport{DBLP:journals/corr/abs-2101-06511, title = {Towards Searching Efficient and Accurate Neural Network Architectures in Binary Classification Problems}, author = {Yigit Alparslan and Ethan Jacob Moyer and Isamu Mclean Isozaki and Daniel Schwartz and Adam Dunlop and Shesh Dave and Edward Kim}, url = {https://arxiv.org/abs/2101.06511}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2101.06511}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1150. | Lee, Sanghyeop; Kim, Junyeob; Kang, Hyeon; Kang, Do-Young; Park, Jangsik Genetic Algorithm Based Deep Learning Neural Network Structure and Hyperparameter Optimization Journal Article Applied Sciences, 11 (2), 2021, ISSN: 2076-3417. @article{app11020744, title = {Genetic Algorithm Based Deep Learning Neural Network Structure and Hyperparameter Optimization}, author = {Sanghyeop Lee and Junyeob Kim and Hyeon Kang and Do-Young Kang and Jangsik Park}, url = {https://www.mdpi.com/2076-3417/11/2/744}, doi = {10.3390/app11020744}, issn = {2076-3417}, year = {2021}, date = {2021-01-01}, journal = {Applied Sciences}, volume = {11}, number = {2}, abstract = {Alzheimer’s disease is one of the major challenges of population ageing, and diagnosis and prediction of the disease through various biomarkers is the key. While the application of deep learning as imaging technologies has recently expanded across the medical industry, empirical design of these technologies is very difficult. The main reason for this problem is that the performance of the Convolutional Neural Networks (CNN) differ greatly depending on the statistical distribution of the input dataset. Different hyperparameters also greatly affect the convergence of the CNN models. With this amount of information, selecting appropriate parameters for the network structure has became a large research area. Genetic Algorithm (GA), is a very popular technique to automatically select a high-performance network architecture. In this paper, we show the possibility of optimising the network architecture using GA, where its search space includes both network structure configuration and hyperparameters. To verify the performance of our Algorithm, we used an amyloid brain image dataset that is used for Alzheimer’s disease diagnosis. As a result, our algorithm outperforms Genetic CNN by 11.73% on a given classification task.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Alzheimer’s disease is one of the major challenges of population ageing, and diagnosis and prediction of the disease through various biomarkers is the key. While the application of deep learning as imaging technologies has recently expanded across the medical industry, empirical design of these technologies is very difficult. The main reason for this problem is that the performance of the Convolutional Neural Networks (CNN) differ greatly depending on the statistical distribution of the input dataset. Different hyperparameters also greatly affect the convergence of the CNN models. With this amount of information, selecting appropriate parameters for the network structure has became a large research area. Genetic Algorithm (GA), is a very popular technique to automatically select a high-performance network architecture. In this paper, we show the possibility of optimising the network architecture using GA, where its search space includes both network structure configuration and hyperparameters. To verify the performance of our Algorithm, we used an amyloid brain image dataset that is used for Alzheimer’s disease diagnosis. As a result, our algorithm outperforms Genetic CNN by 11.73% on a given classification task. |
| 1149. | Jiang, Hanliang; Shen, Fuhao; Gao, Fei; Han, Weidong Learning efficient, explainable and discriminative representations for pulmonary nodules classification Journal Article Pattern Recognition, 113 , pp. 107825, 2021, ISSN: 0031-3203. @article{JIANG2021107825, title = {Learning efficient, explainable and discriminative representations for pulmonary nodules classification}, author = {Hanliang Jiang and Fuhao Shen and Fei Gao and Weidong Han}, url = {https://www.sciencedirect.com/science/article/pii/S0031320321000121}, doi = {https://doi.org/10.1016/j.patcog.2021.107825}, issn = {0031-3203}, year = {2021}, date = {2021-01-01}, journal = {Pattern Recognition}, volume = {113}, pages = {107825}, abstract = {Automatic pulmonary nodules classification is significant for early diagnosis of lung cancers. Recently, deep learning techniques have enabled remarkable progress in this field. However, these deep models are typically of high computational complexity and work in a black-box manner. To combat these challenges, in this work, we aim to build an efficient and (partially) explainable classification model. Specially, we use neural architecture search (NAS) to automatically search 3D network architectures with excellent accuracy/speed trade-off. Besides, we use the convolutional block attention module (CBAM) in the networks, which helps us understand the reasoning process. During training, we use A-Softmax loss to learn angularly discriminative representations. In the inference stage, we employ an ensemble of diverse neural networks to improve the prediction accuracy and robustness. We conduct extensive experiments on the LIDC-IDRI database. Compared with previous state-of-the-art, our model shows highly comparable performance by using less than 1/40 parameters. Besides, empirical study shows that the reasoning process of learned networks is in conformity with physicians’ diagnosis. Related code and results have been released at: https://github.com/fei-hdu/NAS-Lung.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Automatic pulmonary nodules classification is significant for early diagnosis of lung cancers. Recently, deep learning techniques have enabled remarkable progress in this field. However, these deep models are typically of high computational complexity and work in a black-box manner. To combat these challenges, in this work, we aim to build an efficient and (partially) explainable classification model. Specially, we use neural architecture search (NAS) to automatically search 3D network architectures with excellent accuracy/speed trade-off. Besides, we use the convolutional block attention module (CBAM) in the networks, which helps us understand the reasoning process. During training, we use A-Softmax loss to learn angularly discriminative representations. In the inference stage, we employ an ensemble of diverse neural networks to improve the prediction accuracy and robustness. We conduct extensive experiments on the LIDC-IDRI database. Compared with previous state-of-the-art, our model shows highly comparable performance by using less than 1/40 parameters. Besides, empirical study shows that the reasoning process of learned networks is in conformity with physicians’ diagnosis. Related code and results have been released at: https://github.com/fei-hdu/NAS-Lung. |
| 1148. | Alparslan, Yigit; Moyer, Ethan Jacob; Kim, Edward Evaluating Online and Offline Accuracy Traversal Algorithms for k-Complete Neural Network Architectures Journal Article CoRR, abs/2101.06518 , 2021. @article{DBLP:journals/corr/abs-2101-06518, title = {Evaluating Online and Offline Accuracy Traversal Algorithms for k-Complete Neural Network Architectures}, author = {Yigit Alparslan and Ethan Jacob Moyer and Edward Kim}, url = {https://arxiv.org/abs/2101.06518}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2101.06518}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
| 1147. | Vaccaro, Lorenzo; Sansonetti, Giuseppe; Micarelli, Alessandro An Empirical Review of Automated Machine Learning Journal Article Computers, 10 (1), 2021, ISSN: 2073-431X. @article{computers10010011, title = {An Empirical Review of Automated Machine Learning}, author = {Lorenzo Vaccaro and Giuseppe Sansonetti and Alessandro Micarelli}, url = {https://www.mdpi.com/2073-431X/10/1/11}, doi = {10.3390/computers10010011}, issn = {2073-431X}, year = {2021}, date = {2021-01-01}, journal = {Computers}, volume = {10}, number = {1}, abstract = {In recent years, Automated Machine Learning (AutoML) has become increasingly important in Computer Science due to the valuable potential it offers. This is testified by the high number of works published in the academic field and the significant efforts made in the industrial sector. However, some problems still need to be resolved. In this paper, we review some Machine Learning (ML) models and methods proposed in the literature to analyze their strengths and weaknesses. Then, we propose their use—alone or in combination with other approaches—to provide possible valid AutoML solutions. We analyze those solutions from a theoretical point of view and evaluate them empirically on three Atari games from the Arcade Learning Environment. Our goal is to identify what, we believe, could be some promising ways to create truly effective AutoML frameworks, therefore able to replace the human expert as much as possible, thereby making easier the process of applying ML approaches to typical problems of specific domains. We hope that the findings of our study will provide useful insights for future research work in AutoML.}, keywords = {}, pubstate = {published}, tppubtype = {article} } In recent years, Automated Machine Learning (AutoML) has become increasingly important in Computer Science due to the valuable potential it offers. This is testified by the high number of works published in the academic field and the significant efforts made in the industrial sector. However, some problems still need to be resolved. In this paper, we review some Machine Learning (ML) models and methods proposed in the literature to analyze their strengths and weaknesses. Then, we propose their use—alone or in combination with other approaches—to provide possible valid AutoML solutions. We analyze those solutions from a theoretical point of view and evaluate them empirically on three Atari games from the Arcade Learning Environment. Our goal is to identify what, we believe, could be some promising ways to create truly effective AutoML frameworks, therefore able to replace the human expert as much as possible, thereby making easier the process of applying ML approaches to typical problems of specific domains. We hope that the findings of our study will provide useful insights for future research work in AutoML. |
| 1146. | Li, Qing; Wu, Xia; Liu, Tianming Differentiable Neural Architecture Search for Optimal Spatial/Temporal Brain Function Network Decomposition Journal Article Medical Image Analysis, pp. 101974, 2021, ISSN: 1361-8415. @article{LI2021101974, title = {Differentiable Neural Architecture Search for Optimal Spatial/Temporal Brain Function Network Decomposition}, author = {Qing Li and Xia Wu and Tianming Liu}, url = {https://www.sciencedirect.com/science/article/pii/S1361841521000207}, doi = {https://doi.org/10.1016/j.media.2021.101974}, issn = {1361-8415}, year = {2021}, date = {2021-01-01}, journal = {Medical Image Analysis}, pages = {101974}, abstract = {ABSTRACT It has been a key topic to decompose the brain's spatial/temporal function networks from 4D functional magnetic resonance imaging (fMRI) data. With the advantages of robust and meaningful brain pattern extraction, deep neural networks have been shown to be more powerful and flexible in fMRI data modeling than other traditional methods. However, the challenge of designing neural network architecture for high-dimensional and complex fMRI data has also been realized recently. In this paper, we propose a new spatial/temporal differentiable neural architecture search algorithm (ST-DARTS) for optimal brain network decomposition. The core idea of ST-DARTS is to optimize the inner cell structure of the vanilla recurrent neural network (RNN) in order to effectively decompose spatial/temporal brain function networks from fMRI data. Based on the evaluations on all seven fMRI tasks in human connectome project (HCP) dataset, the ST-DARTS model is shown to perform promisingly, both spatially (i.e., it can recognize the most stimuli-correlated spatial brain network activation that is very similar to the benchmark) and temporally (i.e., its temporal activity is highly positively correlated with the task-design). To further improve the efficiency of ST-DARTS model, we introduce a flexible early-stopping mechanism, named as ST-DARTS±, which further improves experimental results significantly. To our best knowledge, the proposed ST-DARTS and ST-DARTS+ models are among the early efforts in optimally decomposing spatial/temporal brain function networks from fMRI data with neural architecture search strategy and they demonstrate great promise.}, keywords = {}, pubstate = {published}, tppubtype = {article} } ABSTRACT It has been a key topic to decompose the brain's spatial/temporal function networks from 4D functional magnetic resonance imaging (fMRI) data. With the advantages of robust and meaningful brain pattern extraction, deep neural networks have been shown to be more powerful and flexible in fMRI data modeling than other traditional methods. However, the challenge of designing neural network architecture for high-dimensional and complex fMRI data has also been realized recently. In this paper, we propose a new spatial/temporal differentiable neural architecture search algorithm (ST-DARTS) for optimal brain network decomposition. The core idea of ST-DARTS is to optimize the inner cell structure of the vanilla recurrent neural network (RNN) in order to effectively decompose spatial/temporal brain function networks from fMRI data. Based on the evaluations on all seven fMRI tasks in human connectome project (HCP) dataset, the ST-DARTS model is shown to perform promisingly, both spatially (i.e., it can recognize the most stimuli-correlated spatial brain network activation that is very similar to the benchmark) and temporally (i.e., its temporal activity is highly positively correlated with the task-design). To further improve the efficiency of ST-DARTS model, we introduce a flexible early-stopping mechanism, named as ST-DARTS±, which further improves experimental results significantly. To our best knowledge, the proposed ST-DARTS and ST-DARTS+ models are among the early efforts in optimally decomposing spatial/temporal brain function networks from fMRI data with neural architecture search strategy and they demonstrate great promise. |
| 1145. | Song, Xingyou; Choromanski, Krzysztof; -, Jack Parker; Tang, Yunhao; Peng, Daiyi; Jain, Deepali; Gao, Wenbo; Pacchiano, Aldo; ó, Tamás Sarl; Yang, Yuxiang ES-ENAS: Combining Evolution Strategies with Neural Architecture Search at No Extra Cost for Reinforcement Learning Technical Report , 2021. @techreport{DBLP:journals/corr/abs-2101-07415, title = {ES-ENAS: Combining Evolution Strategies with Neural Architecture Search at No Extra Cost for Reinforcement Learning}, author = {Xingyou Song and Krzysztof Choromanski and Jack Parker - and Yunhao Tang and Daiyi Peng and Deepali Jain and Wenbo Gao and Aldo Pacchiano and Tamás Sarl ó and Yuxiang Yang}, url = {https://arxiv.org/abs/2101.07415}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2101.07415}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1144. | Wu, Haiwei; Zhou, Jiantao GIID-Net: Generalizable Image Inpainting Detection via Neural Architecture Search and Attention Technical Report , 2021. @techreport{DBLP:journals/corr/abs-2101-07419, title = {GIID-Net: Generalizable Image Inpainting Detection via Neural Architecture Search and Attention}, author = {Haiwei Wu and Jiantao Zhou}, url = {https://arxiv.org/abs/2101.07419}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2101.07419}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1143. | Fu, Chaoyou; Hu, Yibo; Wu, Xiang; Shi, Hailin; Mei, Tao; He, Ran CM-NAS: Rethinking Cross-Modality Neural Architectures for Visible-Infrared Person Re-Identification Technical Report , 2021. @techreport{DBLP:journals/corr/abs-2101-08467, title = {CM-NAS: Rethinking Cross-Modality Neural Architectures for Visible-Infrared Person Re-Identification}, author = {Chaoyou Fu and Yibo Hu and Xiang Wu and Hailin Shi and Tao Mei and Ran He}, url = {https://arxiv.org/abs/2101.08467}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2101.08467}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1142. | Abdelfattah, Mohamed S; Mehrotra, Abhinav; Dudziak, Lukasz; Lane, Nicholas D Zero-Cost Proxies for Lightweight NAS Technical Report , 2021. @techreport{DBLP:journals/corr/abs-2101-08134, title = {Zero-Cost Proxies for Lightweight NAS}, author = {Mohamed S Abdelfattah and Abhinav Mehrotra and Lukasz Dudziak and Nicholas D Lane}, url = {https://arxiv.org/abs/2101.08134}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2101.08134}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1141. | Benmeziane, Hadjer; Maghraoui, Kaoutar El; Ouarnoughi, Hamza; ï, Sma; Wistuba, Martin; Wang, Naigang A Comprehensive Survey on Hardware-Aware Neural Architecture Search Technical Report , 2021. @techreport{DBLP:journals/corr/abs-2101-09336, title = {A Comprehensive Survey on Hardware-Aware Neural Architecture Search}, author = {Hadjer Benmeziane and Kaoutar El Maghraoui and Hamza Ouarnoughi and Sma ï and Martin Wistuba and Naigang Wang}, url = {https://arxiv.org/abs/2101.09336}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2101.09336}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |
| 1140. | He, Xin; Wang, Shihao; Ying, Guohao; Zhang, Jiyong; Chu, Xiaowen Efficient Multi-objective Evolutionary 3D Neural Architecture Search for COVID-19 Detection with Chest CT Scans Technical Report , 2021. @techreport{DBLP:journals/corr/abs-2101-10667, title = {Efficient Multi-objective Evolutionary 3D Neural Architecture Search for COVID-19 Detection with Chest CT Scans}, author = {Xin He and Shihao Wang and Guohao Ying and Jiyong Zhang and Xiaowen Chu}, url = {https://arxiv.org/abs/2101.10667}, year = {2021}, date = {2021-01-01}, journal = {CoRR}, volume = {abs/2101.10667}, keywords = {}, pubstate = {published}, tppubtype = {techreport} } |