Maintained by Difan Deng and Marius Lindauer.
The following list considers papers related to neural architecture search. It is by no means complete. If you miss a paper on the list, please let us know.
Please note that although NAS methods steadily improve, the quality of empirical evaluations in this field are still lagging behind compared to other areas in machine learning, AI and optimization. We would therefore like to share some best practices for empirical evaluations of NAS methods, which we believe will facilitate sustained and measurable progress in the field. If you are interested in a teaser, please read our blog post or directly jump to our checklist.
Transformers have gained increasing popularity in different domains. For a comprehensive list of papers focusing on Neural Architecture Search for Transformer-Based spaces, the awesome-transformer-search repo is all you need.
2021
Qu, Xiaoyang; Wang, Jianzong; Liu, Jie; Xiao, Jing
Enhancing Neural Architecture Search by Upgrading Weak Components Proceedings Article
In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1-8, 2021.
@inproceedings{9533895,
title = {Enhancing Neural Architecture Search by Upgrading Weak Components},
author = {Xiaoyang Qu and Jianzong Wang and Jie Liu and Jing Xiao},
url = {https://ieeexplore.ieee.org/abstract/document/9533895},
doi = {10.1109/IJCNN52387.2021.9533895},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {2021 International Joint Conference on Neural Networks (IJCNN)},
pages = {1-8},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Sun, Lirong; Zhu, Wenbo; Lu, Qinghua; Li, Aiyuan; Luo, Lufeng; Chen, Jianwen; Wang, Jinhai
CellNet: An Improved Neural Architecture Search Method for Coal and Gangue Classification Proceedings Article
In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1-9, 2021.
@inproceedings{9534403,
title = {CellNet: An Improved Neural Architecture Search Method for Coal and Gangue Classification},
author = {Lirong Sun and Wenbo Zhu and Qinghua Lu and Aiyuan Li and Lufeng Luo and Jianwen Chen and Jinhai Wang},
doi = {10.1109/IJCNN52387.2021.9534403},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {2021 International Joint Conference on Neural Networks (IJCNN)},
pages = {1-9},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Xiao, Zhiwen; Xu, Xin; Xing, Huanlai; Qu, Rong; Song, Fuhong; Zhao, Bowen
RNTS: Robust Neural Temporal Search for Time Series Classification Proceedings Article
In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1-8, 2021.
@inproceedings{9534392,
title = {RNTS: Robust Neural Temporal Search for Time Series Classification},
author = {Zhiwen Xiao and Xin Xu and Huanlai Xing and Rong Qu and Fuhong Song and Bowen Zhao},
url = {https://ieeexplore.ieee.org/abstract/document/9534392},
doi = {10.1109/IJCNN52387.2021.9534392},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {2021 International Joint Conference on Neural Networks (IJCNN)},
pages = {1-8},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Li, Baopu; Fan, Yanwen; Pan, Zhihong; Cheng, Zhiyu; Zhang, Gang
Cursor-based Adaptive Quantization for Deep Convolutional Neural Network Proceedings Article
In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1-8, 2021.
@inproceedings{9533578,
title = {Cursor-based Adaptive Quantization for Deep Convolutional Neural Network},
author = {Baopu Li and Yanwen Fan and Zhihong Pan and Zhiyu Cheng and Gang Zhang},
url = {https://ieeexplore.ieee.org/abstract/document/9533578},
doi = {10.1109/IJCNN52387.2021.9533578},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {2021 International Joint Conference on Neural Networks (IJCNN)},
pages = {1-8},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Liu, Yue; Zhu, Kai; Liu, Zitu
SSRNAS: Search Space Reduced One-shot NAS by a Recursive Attention-based Predictor with Cell Tensor-flow Diagram Proceedings Article
In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1-8, 2021.
@inproceedings{9533297,
title = {SSRNAS: Search Space Reduced One-shot NAS by a Recursive Attention-based Predictor with Cell Tensor-flow Diagram},
author = {Yue Liu and Kai Zhu and Zitu Liu},
url = {https://ieeexplore.ieee.org/abstract/document/9533297},
doi = {10.1109/IJCNN52387.2021.9533297},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {2021 International Joint Conference on Neural Networks (IJCNN)},
pages = {1-8},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Sun, Junwei; Wang, Bai; Wu, Bin
Automated Graph Representation Learning for Node Classification Proceedings Article
In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1-7, 2021.
@inproceedings{9533811,
title = {Automated Graph Representation Learning for Node Classification},
author = {Junwei Sun and Bai Wang and Bin Wu},
url = {https://ieeexplore.ieee.org/document/9533811},
doi = {10.1109/IJCNN52387.2021.9533811},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {2021 International Joint Conference on Neural Networks (IJCNN)},
pages = {1-7},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Du, Xiaocong; Li, Zheng; Sun, Jingbo; Liu, Frank; Cao, Yu
Evolutionary NAS in Light of Model Stability for Accurate Continual Learning Proceedings Article
In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1-8, 2021.
@inproceedings{9534079,
title = {Evolutionary NAS in Light of Model Stability for Accurate Continual Learning},
author = {Xiaocong Du and Zheng Li and Jingbo Sun and Frank Liu and Yu Cao},
url = {https://ieeexplore.ieee.org/abstract/document/9534079},
doi = {10.1109/IJCNN52387.2021.9534079},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {2021 International Joint Conference on Neural Networks (IJCNN)},
pages = {1-8},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Pan, Zijie; Hu, Li; Tang, Weixuan; Li, Jin; He, Yi; Liu, Zheli
Privacy-Preserving Multi-Granular Federated Neural Architecture Search A General Framework Journal Article
In: IEEE Transactions on Knowledge and Data Engineering, pp. 1-1, 2021.
@article{9552481,
title = {Privacy-Preserving Multi-Granular Federated Neural Architecture Search A General Framework},
author = {Zijie Pan and Li Hu and Weixuan Tang and Jin Li and Yi He and Zheli Liu},
url = {https://ieeexplore.ieee.org/abstract/document/9552481},
doi = {10.1109/TKDE.2021.3116248},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {IEEE Transactions on Knowledge and Data Engineering},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Mills, Keith G.; Han, Fred X.; Zhang, Jialin; Rezaei, Seyed Saeed Changiz; Chudak, Fabian; Lu, Wei; Lian, Shuo; Jui, Shangling; Niu, Di
Profiling Neural Blocks and Design Spaces for Mobile Neural Architecture Search Proceedings Article
In: Demartini, Gianluca; Zuccon, Guido; Culpepper, J. Shane; Huang, Zi; Tong, Hanghang (Ed.): CIKM '21: The 30th ACM International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, November 1 - 5, 2021, pp. 4026–4035, ACM, 2021.
@inproceedings{DBLP:conf/cikm/MillsHZRCLLJN21,
title = {Profiling Neural Blocks and Design Spaces for Mobile Neural Architecture Search},
author = {Keith G. Mills and Fred X. Han and Jialin Zhang and Seyed Saeed Changiz Rezaei and Fabian Chudak and Wei Lu and Shuo Lian and Shangling Jui and Di Niu},
editor = {Gianluca Demartini and Guido Zuccon and J. Shane Culpepper and Zi Huang and Hanghang Tong},
url = {https://doi.org/10.1145/3459637.3481944},
doi = {10.1145/3459637.3481944},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {CIKM '21: The 30th ACM International Conference on Information
and Knowledge Management, Virtual Event, Queensland, Australia, November
1 - 5, 2021},
pages = {4026--4035},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Rahbar, Mahdi; Yazdani, Samaneh
Forecasting of COVID-19 Cases, Using an Evolutionary Neural Architecture Search Approach Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2109-13062,
title = {Forecasting of COVID-19 Cases, Using an Evolutionary Neural Architecture Search Approach},
author = {Mahdi Rahbar and Samaneh Yazdani},
url = {https://arxiv.org/abs/2109.13062},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2109.13062},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Tran, Linh-Tam; Ali, Muhammad Salman; Bae, Sung-Ho
A Feature Fusion Based Indicator for Training-Free Neural Architecture Search Journal Article
In: IEEE Access, vol. 9, pp. 133914-133923, 2021.
@article{9548935,
title = {A Feature Fusion Based Indicator for Training-Free Neural Architecture Search},
author = {Linh-Tam Tran and Muhammad Salman Ali and Sung-Ho Bae},
url = {https://ieeexplore.ieee.org/abstract/document/9548935},
doi = {10.1109/ACCESS.2021.3115911},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {IEEE Access},
volume = {9},
pages = {133914-133923},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Zhang, Jiuling; Ding, Zhiming
Delve into the Performance Degradation of Differentiable Architecture Search Proceedings Article
In: Demartini, Gianluca; Zuccon, Guido; Culpepper, J. Shane; Huang, Zi; Tong, Hanghang (Ed.): CIKM '21: The 30th ACM International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, November 1 - 5, 2021, pp. 2547–2556, ACM, 2021.
@inproceedings{DBLP:conf/cikm/ZhangD21,
title = {Delve into the Performance Degradation of Differentiable Architecture Search},
author = {Jiuling Zhang and Zhiming Ding},
editor = {Gianluca Demartini and Guido Zuccon and J. Shane Culpepper and Zi Huang and Hanghang Tong},
url = {https://doi.org/10.1145/3459637.3482248},
doi = {10.1145/3459637.3482248},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {CIKM '21: The 30th ACM International Conference on Information
and Knowledge Management, Virtual Event, Queensland, Australia, November
1 - 5, 2021},
pages = {2547--2556},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Mills, Keith G.; Han, Fred X.; Salameh, Mohammad; Rezaei, Seyed Saeed Changiz; Kong, Linglong; Lu, Wei; Lian, Shuo; Jui, Shangling; Niu, Di
L2NAS: Learning to Optimize Neural Architectures via Continuous-Action Reinforcement Learning Proceedings Article
In: Demartini, Gianluca; Zuccon, Guido; Culpepper, J. Shane; Huang, Zi; Tong, Hanghang (Ed.): CIKM '21: The 30th ACM International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, November 1 - 5, 2021, pp. 1284–1293, ACM, 2021.
@inproceedings{DBLP:conf/cikm/MillsHSRKLLJN21,
title = {L2NAS: Learning to Optimize Neural Architectures via Continuous-Action Reinforcement Learning},
author = {Keith G. Mills and Fred X. Han and Mohammad Salameh and Seyed Saeed Changiz Rezaei and Linglong Kong and Wei Lu and Shuo Lian and Shangling Jui and Di Niu},
editor = {Gianluca Demartini and Guido Zuccon and J. Shane Culpepper and Zi Huang and Hanghang Tong},
url = {https://doi.org/10.1145/3459637.3482360},
doi = {10.1145/3459637.3482360},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {CIKM '21: The 30th ACM International Conference on Information
and Knowledge Management, Virtual Event, Queensland, Australia, November
1 - 5, 2021},
pages = {1284--1293},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Helms, Domenik; Amende, Karl; Bukhari, Saqib; Graaff, Thies; Frickenstein, Alexander; Hafner, Frank; Hirscher, Tobias; Mantowsky, Sven; Schneider, Georg; Vemparala, Manoj-Rohit
Optimizing Neural Networks for Embedded Hardware Proceedings Article
In: SMACD / PRIME 2021; International Conference on SMACD and 16th Conference on PRIME, pp. 1-6, 2021.
@inproceedings{9547911,
title = {Optimizing Neural Networks for Embedded Hardware},
author = {Domenik Helms and Karl Amende and Saqib Bukhari and Thies Graaff and Alexander Frickenstein and Frank Hafner and Tobias Hirscher and Sven Mantowsky and Georg Schneider and Manoj-Rohit Vemparala},
url = {https://ieeexplore.ieee.org/abstract/document/9547911},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {SMACD / PRIME 2021; International Conference on SMACD and 16th Conference on PRIME},
pages = {1-6},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Zheng, Zhong; Kang, Guixia
Model Compression with NAS and Knowledge Distillation for Medical Image Segmentation Book Chapter
In: 2021 4th International Conference on Data Science and Information Technology, pp. 173–176, Association for Computing Machinery, New York, NY, USA, 2021, ISBN: 9781450390248.
@inbook{10.1145/3478905.3478940,
title = {Model Compression with NAS and Knowledge Distillation for Medical Image Segmentation},
author = {Zhong Zheng and Guixia Kang},
url = {https://doi.org/10.1145/3478905.3478940},
isbn = {9781450390248},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {2021 4th International Conference on Data Science and Information Technology},
pages = {173–176},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
abstract = {Medical image segmentation task has been a hot research topic in the field of computer
vision and natural field for many years. With the rapid development and application
of convolutional neural networks, more and more medical segmentation models based
on deep learning have been proposed, and more successful results and applications
have been achieved in many disease segmentation tasks.The effect of medical image
segmentation tasks is getting better. However, the computational cost of the medical
image segmentation model has not been improved well. In this work, we propose a medical
image segmentation model compression scheme that is theoretically applicable to all
convolutional neural networks. First, we choose to construct a search space based
on the number of convolution kernels at each location where convolution is used in
the model, and then use neural network search to find a sub-network in this search
space with less computation and high segmentation accuracy. Aiming at the encoding-decoding
structure of the segmentation network, we propose Symmetrical-NAS to ensure that the
encoding structure and decoding structure of any sub-network in our search space are
symmetrical. Since it is too expensive to traverse the entire search space for training
to find the most suitable architecture, we use weight sharing for training. During
training, a sub-network in the search space is randomly selected for activation each
time. Second, we use the method of knowledge distillation for training. We use the
basic model as the teacher model and the searched sub-network as the student model
to realize the knowledge transfer between the teacher model and the student model.
Third, we use separable convolution instead of convolutional layer. Our method can
be applied to various medicial image segmentation models regardless of model architectures
and learning algorithms. Our method can reduce the computation of medical image segmentation
models by 90texttimes regarding FLOPs with little loss of segmentation effect. The code and
demo will be publicly available.},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
vision and natural field for many years. With the rapid development and application
of convolutional neural networks, more and more medical segmentation models based
on deep learning have been proposed, and more successful results and applications
have been achieved in many disease segmentation tasks.The effect of medical image
segmentation tasks is getting better. However, the computational cost of the medical
image segmentation model has not been improved well. In this work, we propose a medical
image segmentation model compression scheme that is theoretically applicable to all
convolutional neural networks. First, we choose to construct a search space based
on the number of convolution kernels at each location where convolution is used in
the model, and then use neural network search to find a sub-network in this search
space with less computation and high segmentation accuracy. Aiming at the encoding-decoding
structure of the segmentation network, we propose Symmetrical-NAS to ensure that the
encoding structure and decoding structure of any sub-network in our search space are
symmetrical. Since it is too expensive to traverse the entire search space for training
to find the most suitable architecture, we use weight sharing for training. During
training, a sub-network in the search space is randomly selected for activation each
time. Second, we use the method of knowledge distillation for training. We use the
basic model as the teacher model and the searched sub-network as the student model
to realize the knowledge transfer between the teacher model and the student model.
Third, we use separable convolution instead of convolutional layer. Our method can
be applied to various medicial image segmentation models regardless of model architectures
and learning algorithms. Our method can reduce the computation of medical image segmentation
models by 90texttimes regarding FLOPs with little loss of segmentation effect. The code and
demo will be publicly available.
Sharma, Arun K.; Verma, Nishchal K.
Transfer Learning based Evolutionary Deep Neural Network for Intelligent Fault Diagnosis Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2109-13479,
title = {Transfer Learning based Evolutionary Deep Neural Network for Intelligent Fault Diagnosis},
author = {Arun K. Sharma and Nishchal K. Verma},
url = {https://arxiv.org/abs/2109.13479},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2109.13479},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Yamada, Fuyuka; Tsuji, Satoki; Kawaguchi, Hiroshi; Inoue, Atsuki; Sakai, Yasufumi
A High-Speed Neural Architecture Search Considering the Number of Weights Proceedings Article
In: Edelkamp, Stefan; Möller, Ralf; Rueckert, Elmar (Ed.): KI 2021: Advances in Artificial Intelligence, pp. 109–115, Springer International Publishing, Cham, 2021, ISBN: 978-3-030-87626-5.
@inproceedings{10.1007/978-3-030-87626-5_9,
title = {A High-Speed Neural Architecture Search Considering the Number of Weights},
author = {Fuyuka Yamada and Satoki Tsuji and Hiroshi Kawaguchi and Atsuki Inoue and Yasufumi Sakai},
editor = {Stefan Edelkamp and Ralf Möller and Elmar Rueckert},
url = {https://link.springer.com/chapter/10.1007/978-3-030-87626-5_9},
isbn = {978-3-030-87626-5},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {KI 2021: Advances in Artificial Intelligence},
pages = {109--115},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {Neural architecture search (NAS) is a promising method to ascertain network architecture automatically and to build a suitable network for a particular application without any human intervention. However, NAS requires huge computation resources to find the optimal parameters of a network in the training phase of each search. Because a trade-off generally exists between model size and accuracy in deep learning models, the model size tends to increase in pursuit of higher accuracy. In applications with limited resources, such as edge AI, reducing the network weight might be more important than improving its accuracy. Alternatively, achieving high accuracy with maximum resources might be more important. The objective of this research is to find a model with sufficient accuracy with a limited number of weights and to reduce the search time. We improve the Differentiable Network Search (DARTS) algorithm, one of the fastest NAS methods, by adding another constraint to the loss function, which limits the number of network weights. We evaluate the proposed algorithm using three constraints. Compared to the conventional DARTS algorithm, the proposed algorithm reduces the search time by up to 40% when the model size range is set properly. It achieves comparable accuracy with that of DARTS.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Wang, Xiaoxing; Chu, Xiangxiang; Yan, Junchi; Yang, Xiaokang
DAAS: Differentiable Architecture and Augmentation Policy Search Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2109-15273,
title = {DAAS: Differentiable Architecture and Augmentation Policy Search},
author = {Xiaoxing Wang and Xiangxiang Chu and Junchi Yan and Xiaokang Yang},
url = {https://arxiv.org/abs/2109.15273},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2109.15273},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Zhang, Jiabin; Chu, Qi; Li, Weihai; Liu, Bin; Zhang, Weiming; Yu, Nenghai
Towards More Powerful Multi-column Convolutional Network for Crowd Counting Proceedings Article
In: Peng, Yuxin; Hu, Shi-Min; Gabbouj, Moncef; Zhou, Kun; Elad, Michael; Xu, Kun (Ed.): Image and Graphics, pp. 381–392, Springer International Publishing, Cham, 2021, ISBN: 978-3-030-87355-4.
@inproceedings{10.1007/978-3-030-87355-4_32,
title = {Towards More Powerful Multi-column Convolutional Network for Crowd Counting},
author = {Jiabin Zhang and Qi Chu and Weihai Li and Bin Liu and Weiming Zhang and Nenghai Yu},
editor = {Yuxin Peng and Shi-Min Hu and Moncef Gabbouj and Kun Zhou and Michael Elad and Kun Xu},
isbn = {978-3-030-87355-4},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Image and Graphics},
pages = {381--392},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {Scale variation has always been one of the most challenging problems for crowd counting. By using multi-column convolutions with different receptive fields to deal with different scales in the scene, the multi-column convolutional networks have achieved good performance. However, there is still great potential waiting to be explored for multi-column convolutional networks. To this end, we propose to design a multi-column neural network that can more effectively adapt to scene scale variations automatically, by applying Neural Architecture Search technology. First, we combine Progressive Neural Architecture Search scheme with crowd counting to construct our Progressive Multi-column Architecture Serach (PMAS) framework. Furthermore, to reduce the bias caused by the weight-share scheme, which is widely adopted in efficient Neural Architecture Search, we propose a novel pre-architecture-based weight-share scheme. Experiments on several challenging datasets demonstrate the effectiveness of our method.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Giovannelli, Tommaso; Kent, Griffin; Vicente, Luís Nunes
Bilevel stochastic methods for optimization and machine learning: Bilevel stochastic descent and DARTS Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2110-00604,
title = {Bilevel stochastic methods for optimization and machine learning: Bilevel stochastic descent and DARTS},
author = {Tommaso Giovannelli and Griffin Kent and Luís Nunes Vicente},
url = {https://arxiv.org/abs/2110.00604},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2110.00604},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Singamsetti, Mohan; Mahajan, Anmol; Guzdial, Matthew
Conceptual Expansion Neural Architecture Search (CENAS) Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2110-03144,
title = {Conceptual Expansion Neural Architecture Search (CENAS)},
author = {Mohan Singamsetti and Anmol Mahajan and Matthew Guzdial},
url = {https://arxiv.org/abs/2110.03144},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2110.03144},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Zhong, Zilong; Li, Ying; Ma, Lingfei; Li, Jonathan; Zheng, Wei-Shi
Spectral-Spatial Transformer Network for Hyperspectral Image Classification: A Factorized Architecture Search Framework Journal Article
In: IEEE Transactions on Geoscience and Remote Sensing, pp. 1-15, 2021.
@article{9565208,
title = {Spectral-Spatial Transformer Network for Hyperspectral Image Classification: A Factorized Architecture Search Framework},
author = {Zilong Zhong and Ying Li and Lingfei Ma and Jonathan Li and Wei-Shi Zheng},
url = {https://ieeexplore.ieee.org/abstract/document/9565208},
doi = {10.1109/TGRS.2021.3115699},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
pages = {1-15},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Shibayama, T.; Mizuno, N.; Kusano, H.; Kinoshita, A.; Minegishi, M.; Sakamoto, R.; Hasegawa, K.; Kachi, F.
Practical deep learning inversion using neural architecture search and a flexible training dataset generator Journal Article
In: vol. 2021, no. 1, pp. 1-5, 2021, ISSN: 2214-4609.
@article{eage:/content/papers/10.3997/2214-4609.202112777,
title = {Practical deep learning inversion using neural architecture search and a flexible training dataset generator},
author = {T. Shibayama and N. Mizuno and H. Kusano and A. Kinoshita and M. Minegishi and R. Sakamoto and K. Hasegawa and F. Kachi},
url = {https://www.earthdoc.org/content/papers/10.3997/2214-4609.202112777},
doi = {https://doi.org/10.3997/2214-4609.202112777},
issn = {2214-4609},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
volume = {2021},
number = {1},
pages = {1-5},
publisher = {European Association of Geoscientists & Engineers},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Liu, Jihao; Li, Hongsheng; Song, Guanglu; Huang, Xin; Liu, Yu
UniNet: Unified Architecture Search with Convolution, Transformer, and MLP Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2110-04035,
title = {UniNet: Unified Architecture Search with Convolution, Transformer, and MLP},
author = {Jihao Liu and Hongsheng Li and Guanglu Song and Xin Huang and Yu Liu},
url = {https://arxiv.org/abs/2110.04035},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2110.04035},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Pang, Ren; Xi, Zhaohan; Ji, Shouling; Luo, Xiapu; Wang, Ting
On the Security Risks of AutoML Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2110-06018,
title = {On the Security Risks of AutoML},
author = {Ren Pang and Zhaohan Xi and Shouling Ji and Xiapu Luo and Ting Wang},
url = {https://arxiv.org/abs/2110.06018},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2110.06018},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Loni, Mohammad; Zoljodi, Ali; Majd, Amin; Ahn, Byung Hoon; Daneshtalab, Masoud; Sjödin, Mikael; Esmaeilzadeh, Hadi
FastStereoNet: A Fast Neural Architecture Search for Improving the Inference of Disparity Estimation on Resource-Limited Platforms Journal Article
In: IEEE Transactions on Systems, Man, and Cybernetics: Systems, pp. 1-13, 2021.
@article{9609009,
title = {FastStereoNet: A Fast Neural Architecture Search for Improving the Inference of Disparity Estimation on Resource-Limited Platforms},
author = {Mohammad Loni and Ali Zoljodi and Amin Majd and Byung Hoon Ahn and Masoud Daneshtalab and Mikael Sjödin and Hadi Esmaeilzadeh},
url = {https://ieeexplore.ieee.org/document/9609009},
doi = {10.1109/TSMC.2021.3123136},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {IEEE Transactions on Systems, Man, and Cybernetics: Systems},
pages = {1-13},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Sarno, Francesco; Kumar, Suryansh; Kaya, Berk; Huang, Zhiwu; Ferrari, Vittorio; Gool, Luc Van
Neural Architecture Search for Efficient Uncalibrated Deep Photometric Stereo Proceedings Article
In: WACV 2022, 2021.
@inproceedings{DBLP:journals/corr/abs-2110-05621,
title = {Neural Architecture Search for Efficient Uncalibrated Deep Photometric Stereo},
author = {Francesco Sarno and Suryansh Kumar and Berk Kaya and Zhiwu Huang and Vittorio Ferrari and Luc Van Gool},
url = {https://arxiv.org/abs/2110.05621},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {WACV 2022},
journal = {CoRR},
volume = {abs/2110.05621},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Rong, Jingtao; Yu, Xinyi; Zhang, Mingyang; Ou, Linlin
Across-Task Neural Architecture Search via Meta Learning Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2110-05842,
title = {Across-Task Neural Architecture Search via Meta Learning},
author = {Jingtao Rong and Xinyi Yu and Mingyang Zhang and Linlin Ou},
url = {https://arxiv.org/abs/2110.05842},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2110.05842},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Wang, Xiaoxing; Guo, Wenxuan; Yan, Junchi; Su, Jianlin; Yang, Xiaokang
ZARTS: On Zero-order Optimization for Neural Architecture Search Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2110-04743,
title = {ZARTS: On Zero-order Optimization for Neural Architecture Search},
author = {Xiaoxing Wang and Wenxuan Guo and Junchi Yan and Jianlin Su and Xiaokang Yang},
url = {https://arxiv.org/abs/2110.04743},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2110.04743},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Xue, Fanghui; Xin, Jack
Network Compression via Cooperative Architecture Search and Distillation Proceedings Article
In: 4th International Conference on Artificial Intelligence for Industries, AI4I 2021, Laguna Hills, CA, USA, September 20-22, 2021, pp. 42–43, IEEE, 2021.
@inproceedings{DBLP:conf/ai4i/XueX21,
title = {Network Compression via Cooperative Architecture Search and Distillation},
author = {Fanghui Xue and Jack Xin},
url = {https://doi.org/10.1109/AI4I51902.2021.00018},
doi = {10.1109/AI4I51902.2021.00018},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {4th International Conference on Artificial Intelligence for Industries,
AI4I 2021, Laguna Hills, CA, USA, September 20-22, 2021},
pages = {42--43},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Zhu, Wei
ÄutoNLU: Architecture Search for Sentence and Cross-sentence Attention Modeling with Re-designed Search Space Proceedings Article
In: Wang, Lu; Feng, Yansong; Hong, Yu; He, Ruifang (Ed.): Natural Language Processing and Chinese Computing, pp. 155–168, Springer International Publishing, Cham, 2021, ISBN: 978-3-030-88480-2.
@inproceedings{10.1007/978-3-030-88480-2_13,
title = {ÄutoNLU: Architecture Search for Sentence and Cross-sentence Attention Modeling with Re-designed Search Space},
author = {Wei Zhu},
editor = {Lu Wang and Yansong Feng and Yu Hong and Ruifang He},
url = {https://link.springer.com/chapter/10.1007/978-3-030-88480-2_13},
isbn = {978-3-030-88480-2},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Natural Language Processing and Chinese Computing},
pages = {155--168},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {The rise of BERT style pre-trained models has significantly improved natural language understanding (NLU) tasks. However, for industrial usage, we still have to rely on more traditional models for efficiency. Thus, in this paper, we present AutoNLU, which is designed for modeling sentence representation and cross-sentence attention in an automatic network architecture search (NAS) manner. We have two main contributions. First, we design a novel and comprehensive search space that consists of encoder operations and aggregator operations, and important design choices. Second, aiming for sentence-pair tasks, we use NAS to automatically model how the representations of two sentences interact with and attend to each other. A reinforcement learning (RL) based search algorithm is enhanced by cross operation and cross layer parameter sharing for efficient and reliable search. Model training is done by distilling knowledge from BERT models. By experimenting on SST-2, RTE, Sci-Tail and CoNLL 2003, we verify that our learned models are better at learning from BERT teachers than other baseline models. Ablation studies on Sci-Tail show that our search space design is valid, and our proposed strategies are helpful for improving the search results (The source code will be made public available.).},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Wang, Yi Ru; Khaki, Samir; Zheng, Weihang; Hosseini, Mahdi S.; Plataniotis, Konstantinos N.
CONetV2: Efficient Auto-Channel Size Optimization for CNNs Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2110-06830,
title = {CONetV2: Efficient Auto-Channel Size Optimization for CNNs},
author = {Yi Ru Wang and Samir Khaki and Weihang Zheng and Mahdi S. Hosseini and Konstantinos N. Plataniotis},
url = {https://arxiv.org/abs/2110.06830},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2110.06830},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Ganesan, Vinod; Ramesh, Gowtham; Kumar, Pratyush
SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2110-04711,
title = {SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions},
author = {Vinod Ganesan and Gowtham Ramesh and Pratyush Kumar},
url = {https://arxiv.org/abs/2110.04711},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2110.04711},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Sekanina, Lukas
Neural Architecture Search and Hardware Accelerator Co-Search: A Survey Journal Article
In: IEEE Access, vol. 9, pp. 151337-151362, 2021.
@article{9606893,
title = {Neural Architecture Search and Hardware Accelerator Co-Search: A Survey},
author = {Lukas Sekanina},
url = {https://ieeexplore.ieee.org/document/9606893},
doi = {10.1109/ACCESS.2021.3126685},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {IEEE Access},
volume = {9},
pages = {151337-151362},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Cheng, Anda; Wang, Jiaxing; Zhang, Xi Sheryl; Chen, Qiang; Wang, Peisong; Cheng, Jian
DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2110-08557,
title = {DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy},
author = {Anda Cheng and Jiaxing Wang and Xi Sheryl Zhang and Qiang Chen and Peisong Wang and Jian Cheng},
url = {https://arxiv.org/abs/2110.08557},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2110.08557},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Pang, Dong; Le, Xinyi; Guan, Xinping
RL-DARTS: Differentiable neural architecture search via reinforcement-learning-based meta-optimizer Journal Article
In: Knowledge-Based Systems, vol. 234, pp. 107585, 2021, ISSN: 0950-7051.
@article{PANG2021107585,
title = {RL-DARTS: Differentiable neural architecture search via reinforcement-learning-based meta-optimizer},
author = {Dong Pang and Xinyi Le and Xinping Guan},
url = {https://www.sciencedirect.com/science/article/pii/S0950705121008479},
doi = {https://doi.org/10.1016/j.knosys.2021.107585},
issn = {0950-7051},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {Knowledge-Based Systems},
volume = {234},
pages = {107585},
abstract = {Differentiable search approaches have attracted extensive attention recently due to their advantages in effectively finding novel neural architectures. However, these methods suffer from shortcomings on heavy computation consumption and low robustness in some cases. In this work, we propose a novel differentiable search method based on reinforcement learning, to further improve the computation efficiency, network precision, and robustness in the neural architecture search area. Our method constructs a reinforcement learning-based meta-optimizer to solve the architecture-parameter optimization problem, which is superior in properties of adaptability and robustness to fixed optimizers. This learnable meta-optimizer can alter its model parameters along with the search process to adapt the optimization procedure, making it possible to find out better structures and parameters with less time. Specifically, we formulate a double-loop algorithm to address the optimization problem in the searched super-network. Through switching between the external and internal loops, our method alternately optimizes the super-network and the meta-optimizer, which converges to the optimal location more rapidly and robustly.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Wu, Robert; Saxena, Nayan; Jain, Rohan
NeuralArTS: Structuring Neural Architecture Search with Type Theory Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2110-08710,
title = {NeuralArTS: Structuring Neural Architecture Search with Type Theory},
author = {Robert Wu and Nayan Saxena and Rohan Jain},
url = {https://arxiv.org/abs/2110.08710},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2110.08710},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Lin, Xuanxiang; Chen, Ke; Jia, Kui
Object Point Cloud Classification via Poly-Convolutional Architecture Search Book Chapter
In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 807–815, Association for Computing Machinery, New York, NY, USA, 2021, ISBN: 9781450386517.
@inbook{10.1145/3474085.3475252,
title = {Object Point Cloud Classification via Poly-Convolutional Architecture Search},
author = {Xuanxiang Lin and Ke Chen and Kui Jia},
url = {https://doi.org/10.1145/3474085.3475252},
isbn = {9781450386517},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Proceedings of the 29th ACM International Conference on Multimedia},
pages = {807–815},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
abstract = {Existing point cloud classifiers concern on handling irregular data structures to discover a global and discriminative configuration of local geometries. These classification methods design a number of effective permutation-invariant feature encoding kernels, but still suffer from the intrinsic challenge of large geometric feature variations caused by inconsistent point distributions along object surface. In this paper, point cloud classification can be addressed via deep graph representation learning on aggregating multiple convolutional feature kernels (namely, a poly convolutional operation) anchored on each point with its local neighbours. Inspired by recent success of neural architecture search, we introduce a novel concept of poly-convolutional architecture search (PolyConv search in short) to model local geometric patterns in a more flexible manner.To this end, the Monte Carlo Tree Search (MCTS) method is adopted, which can be formulated into a Markov Decision Process problem to cast decisions for dependently selecting layer-wise aggregation kernels. Experiments on the popular ModelNet40 benchmark have verified that superior performance can be achieved by constructing networks via the MCTS method, with aggregation kernels in our PolyConv search space.},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Zhang, Miao; Liu, Tingwei; Piao, Yongri; Yao, Shunyu; Lu, Huchuan
Auto-MSFNet: Search Multi-Scale Fusion Network for Salient Object Detection Book Chapter
In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 667–676, Association for Computing Machinery, New York, NY, USA, 2021, ISBN: 9781450386517.
@inbook{10.1145/3474085.3475231,
title = {Auto-MSFNet: Search Multi-Scale Fusion Network for Salient Object Detection},
author = {Miao Zhang and Tingwei Liu and Yongri Piao and Shunyu Yao and Huchuan Lu},
url = {https://doi.org/10.1145/3474085.3475231},
isbn = {9781450386517},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Proceedings of the 29th ACM International Conference on Multimedia},
pages = {667–676},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
abstract = {Multi-scale features fusion plays a critical role in salient object detection. Most of existing methods have achieved remarkable performance by exploiting various multi-scale features fusion strategies. However, an elegant fusion framework requires expert knowledge and experience, heavily relying on laborious trial and error. In this paper, we propose a multi-scale features fusion framework based on Neural Architecture Search (NAS), named Auto-MSFNet. First, we design a novel search cell, named FusionCell to automatically decide multi-scale features aggregation. Rather than searching one repeatable cell stacked, we allow different FusionCells to flexibly integrate multi-level features. Simultaneously, considering features generated from CNNs are naturally spatial and channel-wise, we propose a new search space for efficiently focusing on the most relevant information. The search space mitigates incomplete object structures or over-predicted foreground regions caused by progressive fusion. Second, we propose a progressive polishing loss to further obtain exquisite boundaries by penalizing misalignment of salient object boundaries. Extensive experiments on five benchmark datasets demonstrate the effectiveness of the proposed method and achieve state-of-the-art performance on four evaluation metrics. The code and results of our method are available at https://github.com/OIPLab-DUT/Auto-MSFNet.},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Selg, Hardi; Jenihhin, Maksim; Ellervee, Peeter
JÄNES: A NAS Framework for ML-based EDA Applications Proceedings Article
In: 2021 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT), pp. 1-6, 2021.
@inproceedings{9568321,
title = {JÄNES: A NAS Framework for ML-based EDA Applications},
author = {Hardi Selg and Maksim Jenihhin and Peeter Ellervee},
url = {https://ieeexplore.ieee.org/abstract/document/9568321},
doi = {10.1109/DFT52944.2021.9568321},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {2021 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT)},
pages = {1-6},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Zhang, Zhihao; Jia, Zhihao
GradSign: Model Performance Inference with Theoretical Insights Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2110-08616,
title = {GradSign: Model Performance Inference with Theoretical Insights},
author = {Zhihao Zhang and Zhihao Jia},
url = {https://arxiv.org/abs/2110.08616},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2110.08616},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Li, Jian; Zhang, Bin; Wang, Yabiao; Tai, Ying; Zhang, Zhenyu; Wang, Chengjie; Li, Jilin; Huang, Xiaoming; Xia, Yili
ASFD: Automatic and Scalable Face Detector Book Chapter
In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 2139–2147, Association for Computing Machinery, New York, NY, USA, 2021, ISBN: 9781450386517.
@inbook{10.1145/3474085.3475372,
title = {ASFD: Automatic and Scalable Face Detector},
author = {Jian Li and Bin Zhang and Yabiao Wang and Ying Tai and Zhenyu Zhang and Chengjie Wang and Jilin Li and Xiaoming Huang and Yili Xia},
url = {https://doi.org/10.1145/3474085.3475372},
isbn = {9781450386517},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Proceedings of the 29th ACM International Conference on Multimedia},
pages = {2139–2147},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
abstract = {Along with current multi-scale based detectors, Feature Aggregation and Enhancement (FAE) modules have shown superior performance gains for cutting-edge object detection. However, these hand-crafted FAE modules show inconsistent improvements on face detection, which is mainly due to the significant distribution difference between its training and applying corpus, i.e. COCO vs. WIDER Face. To tackle this problem, we essentially analyse the effect of data distribution, and consequently propose to search an effective FAE architecture, termed AutoFAE by a differentiable architecture search, which outperforms all existing FAE modules in face detection with a considerable margin. Upon the found AutoFAE and existing backbones, a supernet is further built and trained, which automatically obtains a family of detectors under the different complexity constraints. Extensive experiments conducted on popular benchmarks, i.e. WIDER Face and FDDB, demonstrate the state-of-the-art performance-efficiency trade-off for the proposed automatic and scalable face detector (ASFD) family. In particular, our strong ASFD-D6 outperforms the best competitor with AP 96.7/96.2/92.1 on WIDER Face test, and the lightweight ASFD-D0 costs about 3.1 ms, i.e. more than 320 FPS, on the V100 GPU with VGA-resolution images.},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Papalexopoulos, Theodore; Tjandraatmadja, Christian; Anderson, Ross; Vielma, Juan Pablo; Belanger, David
Constrained Discrete Black-Box Optimization using Mixed-Integer Programming Technical Report
2021.
@techreport{papalexopoulos2021constrained,
title = {Constrained Discrete Black-Box Optimization using Mixed-Integer Programming},
author = {Theodore Papalexopoulos and Christian Tjandraatmadja and Ross Anderson and Juan Pablo Vielma and David Belanger},
url = {https://arxiv.org/abs/2110.09569},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Kim, Dahyun; Singh, Kunal Pratap; Choi, Jonghyun
BNAS v2: Learning Architectures for Binary Networks with Empirical Improvements Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2110-08562,
title = {BNAS v2: Learning Architectures for Binary Networks with Empirical Improvements},
author = {Dahyun Kim and Kunal Pratap Singh and Jonghyun Choi},
url = {https://arxiv.org/abs/2110.08562},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2110.08562},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Shen, Yu; Li, Yang; Zheng, Jian; Zhang, Wentao; Yao, Peng; Li, Jixiang; Yang, Sen; Liu, Ji; Cui, Bin
ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2110-10423,
title = {ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies},
author = {Yu Shen and Yang Li and Jian Zheng and Wentao Zhang and Peng Yao and Jixiang Li and Sen Yang and Ji Liu and Bin Cui},
url = {https://arxiv.org/abs/2110.10423},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2110.10423},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Kong, Qi; Xu, Xin; Zhang, Liangliang
MEMA-NAS: Memory-Efficient Multi-Agent Neural Architecture Search Proceedings Article
In: Ma, Huimin; Wang, Liang; Zhang, Changshui; Wu, Fei; Tan, Tieniu; Wang, Yaonan; Lai, Jianhuang; Zhao, Yao (Ed.): Pattern Recognition and Computer Vision, pp. 176–187, Springer International Publishing, Cham, 2021, ISBN: 978-3-030-88013-2.
@inproceedings{10.1007/978-3-030-88013-2_15,
title = {MEMA-NAS: Memory-Efficient Multi-Agent Neural Architecture Search},
author = {Qi Kong and Xin Xu and Liangliang Zhang},
editor = {Huimin Ma and Liang Wang and Changshui Zhang and Fei Wu and Tieniu Tan and Yaonan Wang and Jianhuang Lai and Yao Zhao},
isbn = {978-3-030-88013-2},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Pattern Recognition and Computer Vision},
pages = {176--187},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {Öbject detection is a core computer vision task that aims to localize and classify categories for various objects in an image. With the development of convolutional neural networks, deep learning methods have been widely used in the object detection task, achieving promising performance compared to traditional methods. However, designing a well-performing detection network is inefficient. It consumes too much hardware resources and time to trial, and it also heavily relies on expert knowledge. To efficiently design the neural network architecture, there has been a growing interest in automatically designing neural network architecture by Neural Architecture Search (NAS). In this paper, we propose a Memory-Efficient Multi-Agent Neural Architecture Search (MEMA-NAS) framework in end-to-end object detection neural network. Specifically, we introduce the multi-agent learning to search holistic architecture of the detection network. In this way, a lot of GPU memory is saved, allowing us to search each module's architecture of the detection network simultaneously. To find a better tradeoff between the precision and computational costs, we add the resource constraint in our method. Search experiments on multiple datasets show that MEMA-NAS achieves state-of-the-art results in search efficiency and precision."},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Ho, T. Y.; Guo, D.; Jin, D.; Zhu, Z.; Hung, T. M.; Xiao, J.; Lu, L.; Lin, C. Y.
Comprehensive Head and Neck Organs at Risk Segmentation Using Stratified Learning and Neural Architecture Search Journal Article
In: International Journal of Radiation Oncology*Biology*Physics, vol. 111, no. 3, Supplement, pp. e369-e370, 2021, ISSN: 0360-3016, (2021 Proceedings of the ASTRO 63rd Annual Meeting).
@article{HO2021e369,
title = {Comprehensive Head and Neck Organs at Risk Segmentation Using Stratified Learning and Neural Architecture Search},
author = {T. Y. Ho and D. Guo and D. Jin and Z. Zhu and T. M. Hung and J. Xiao and L. Lu and C. Y. Lin},
url = {https://www.sciencedirect.com/science/article/pii/S0360301621019635},
doi = {https://doi.org/10.1016/j.ijrobp.2021.07.1093},
issn = {0360-3016},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {International Journal of Radiation Oncology*Biology*Physics},
volume = {111},
number = {3, Supplement},
pages = {e369-e370},
abstract = {Purpose/Objective(s)
Organs at risk (OAR) segmentation is an essential step in the radiotherapy of head and neck (H&N) cancer. Automated approaches benefit physicians in significantly reducing manual work and improving the annotation quality and consistency. Current standard deep learning methods face challenges when the number of OARs becomes large, e.g., > 40. Physicians often refer to easy OARs when delineating harder ones, e.g., using mandibles to help identify adjacent salivary glands. This study aims to emulate this process and develop a new approach that stratifies 42 head and neck OARs into anchor, mid-level, and small & hard (S&H) levels to ensure high segmentation quality.
Materials/Methods
We curated two datasets of CT scans, each annotated with 42 OAR masks: one from 142 oropharyngeal cancer (OPX) patients and the other from 31 nasopharyngeal cancer (NPC) patients. Our segmentation method is first developed and evaluated using the OPX dataset and then further tested using the NPC dataset. Emulating clinical practice, we first stratify the 42 OARs into 3 levels. Anchor OARs are high in intensity contrast and low in inter- and intra-reader variability. Mid-level OARs are low in contrast, but not inordinately small. S&H OARs are poor in contrast and very small. For each level, a tailored deep learning segmentation network is developed using the automated network architecture search (NAS). NAS allows the network to choose among 2D, 3D, or Pseudo-3D convolutions. by considering three levels of complexities. Anchor OARs are used to infer the mid-level and S&H OARs segmentation.
Results
With 4-fold cross-validation on the OPX dataset, our method has achieved an average 75.1% Dice score (DSC) and 1.1mm average surface distance (ASD). It outperforms the previous leading method, UaNet, on mid-level OAR segmentation by 3.4% DSC increase 0.4mm, ASD reduction; and on S&H OAR of 10.1% DSC increase, 1.0mm ASD reduction, respectively. Using the NPC patients as an unseen testing set, our method has achieved an average DSC of 76.3% and 1.3mm ASD, which is consistent as in the OPX dataset. This result demonstrates the robustness and generalizability of our method in patients, even with various cancer types.
Conclusion
We introduced a new stratified method for segmenting a large comprehensive set of H&N OARs. Our method integrates multi-stage segmentation and NAS in a synergy for the first time. It was trained using OPX patients and achieved state-of-the-art performance and generalized well to patients of NPC. Our method is a critical step towards an automated, accurate, and dependable OAR segmentation system in various H&N cancers.},
note = {2021 Proceedings of the ASTRO 63rd Annual Meeting},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Organs at risk (OAR) segmentation is an essential step in the radiotherapy of head and neck (H&N) cancer. Automated approaches benefit physicians in significantly reducing manual work and improving the annotation quality and consistency. Current standard deep learning methods face challenges when the number of OARs becomes large, e.g., > 40. Physicians often refer to easy OARs when delineating harder ones, e.g., using mandibles to help identify adjacent salivary glands. This study aims to emulate this process and develop a new approach that stratifies 42 head and neck OARs into anchor, mid-level, and small & hard (S&H) levels to ensure high segmentation quality.
Materials/Methods
We curated two datasets of CT scans, each annotated with 42 OAR masks: one from 142 oropharyngeal cancer (OPX) patients and the other from 31 nasopharyngeal cancer (NPC) patients. Our segmentation method is first developed and evaluated using the OPX dataset and then further tested using the NPC dataset. Emulating clinical practice, we first stratify the 42 OARs into 3 levels. Anchor OARs are high in intensity contrast and low in inter- and intra-reader variability. Mid-level OARs are low in contrast, but not inordinately small. S&H OARs are poor in contrast and very small. For each level, a tailored deep learning segmentation network is developed using the automated network architecture search (NAS). NAS allows the network to choose among 2D, 3D, or Pseudo-3D convolutions. by considering three levels of complexities. Anchor OARs are used to infer the mid-level and S&H OARs segmentation.
Results
With 4-fold cross-validation on the OPX dataset, our method has achieved an average 75.1% Dice score (DSC) and 1.1mm average surface distance (ASD). It outperforms the previous leading method, UaNet, on mid-level OAR segmentation by 3.4% DSC increase 0.4mm, ASD reduction; and on S&H OAR of 10.1% DSC increase, 1.0mm ASD reduction, respectively. Using the NPC patients as an unseen testing set, our method has achieved an average DSC of 76.3% and 1.3mm ASD, which is consistent as in the OPX dataset. This result demonstrates the robustness and generalizability of our method in patients, even with various cancer types.
Conclusion
We introduced a new stratified method for segmenting a large comprehensive set of H&N OARs. Our method integrates multi-stage segmentation and NAS in a synergy for the first time. It was trained using OPX patients and achieved state-of-the-art performance and generalized well to patients of NPC. Our method is a critical step towards an automated, accurate, and dependable OAR segmentation system in various H&N cancers.
Akhauri, Yash; Munoz, Juan Pablo; Iyer, Ravishankar; Jain, Nilesh
A Genetic Programming Approach To Zero-Shot Neural Architecture Ranking Proceedings Article
In: Advances in Programming Languages and Neurosymbolic Systems Workshop, 2021.
@inproceedings{<LineBreak>akhauri2021a,
title = {A Genetic Programming Approach To Zero-Shot Neural Architecture Ranking},
author = {Yash Akhauri and Juan Pablo Munoz and Ravishankar Iyer and Nilesh Jain},
url = {https://openreview.net/forum?id=xuVVuLcqBP5},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Advances in Programming Languages and Neurosymbolic Systems Workshop},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Hirose, Yoichi; Yoshinari, Nozomu; Shirakawa, Shinichi
NAS-HPO-Bench-II: A Benchmark Dataset on Joint Optimization of Convolutional Neural Network Architecture and Training Hyperparameters Proceedings Article
In: ACML2021, 2021.
@inproceedings{DBLP:journals/corr/abs-2110-10165,
title = {NAS-HPO-Bench-II: A Benchmark Dataset on Joint Optimization of Convolutional Neural Network Architecture and Training Hyperparameters},
author = {Yoichi Hirose and Nozomu Yoshinari and Shinichi Shirakawa},
url = {https://arxiv.org/abs/2110.10165},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {ACML2021},
journal = {CoRR},
volume = {abs/2110.10165},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Liu, Zhu; Ma, Long; Liu, Risheng; Fan, Xin; Luo, Zhongxuan; Zhang, Yuduo
Latency-Constrained Spatial-Temporal Aggregated Architecture Search for Video Deraining Proceedings Article
In: Ma, Huimin; Wang, Liang; Zhang, Changshui; Wu, Fei; Tan, Tieniu; Wang, Yaonan; Lai, Jianhuang; Zhao, Yao (Ed.): Pattern Recognition and Computer Vision, pp. 16–28, Springer International Publishing, Cham, 2021, ISBN: 978-3-030-88010-1.
@inproceedings{10.1007/978-3-030-88010-1_2,
title = {Latency-Constrained Spatial-Temporal Aggregated Architecture Search for Video Deraining},
author = {Zhu Liu and Long Ma and Risheng Liu and Xin Fan and Zhongxuan Luo and Yuduo Zhang},
editor = {Huimin Ma and Liang Wang and Changshui Zhang and Fei Wu and Tieniu Tan and Yaonan Wang and Jianhuang Lai and Yao Zhao},
url = {https://link.springer.com/chapter/10.1007/978-3-030-88010-1_2},
isbn = {978-3-030-88010-1},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Pattern Recognition and Computer Vision},
pages = {16--28},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {Existing deep learning-based video deraining techniques have achieved remarkable processes. However, there exist some fundamental issues including plentiful engineering experiences for architecture design and slow hardware-insensitive inference speed. To settle these issues, we develop a highly efficient spatial-temporal aggregated video deraining architecture, derived from the architecture search procedure under a newly-defined flexible search space and latency-constrained search strategy. To be specific, we establish an inter-frame aggregation module to fully integrate temporal correlation according to a set division perspective. Subsequently, we construct an intra-frame enhancement module to eliminate the residual rain streaks by introducing rain kernels that characterize the rain locations. A flexible search space for defining architectures of these two modules is built to avert the demand for expensive engineering skills. Further, we design a latency-constrained differentiable search strategy to automatically discover a hardware-sensitive high-efficient video deraining architecture. Extensive experiments demonstrate that our method can obtain best performance against other state-of-the-art methods.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}