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.
2023
2868.
Gillard, Ryan; Jonany, Stephen; Miao, Yingjie; Munn, Michael; Souza, Connal; Dungay, Jonathan; Liang, Chen; So, David R.; Le, Quoc V.; Real, Esteban
Unified Functional Hashing in Automatic Machine Learning Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2302-05433,
title = {Unified Functional Hashing in Automatic Machine Learning},
author = {Ryan Gillard and Stephen Jonany and Yingjie Miao and Michael Munn and Connal Souza and Jonathan Dungay and Chen Liang and David R. So and Quoc V. Le and Esteban Real},
url = {https://doi.org/10.48550/arXiv.2302.05433},
doi = {10.48550/arXiv.2302.05433},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2302.05433},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2867.
Romero, David W.; Zeghidour, Neil
DNArch: Learning Convolutional Neural Architectures by Backpropagation Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2302-05400,
title = {DNArch: Learning Convolutional Neural Architectures by Backpropagation},
author = {David W. Romero and Neil Zeghidour},
url = {https://doi.org/10.48550/arXiv.2302.05400},
doi = {10.48550/arXiv.2302.05400},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2302.05400},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2866.
Zhang, Jinxia; Chen, Xinyi; Wei, Haikun; Zhang, Kanjian
A lightweight network for photovoltaic cell defect detection in electroluminescence images based on neural architecture search and knowledge distillation Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2302-07455,
title = {A lightweight network for photovoltaic cell defect detection in electroluminescence images based on neural architecture search and knowledge distillation},
author = {Jinxia Zhang and Xinyi Chen and Haikun Wei and Kanjian Zhang},
url = {https://doi.org/10.48550/arXiv.2302.07455},
doi = {10.48550/arXiv.2302.07455},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2302.07455},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2865.
Yuan, Gonglin; Wang, Bin; Xue, Bing; Zhang, Mengjie
Particle Swarm Optimization for Efficiently Evolving Deep Convolutional Neural Networks Using an Autoencoder-based Encoding Strategy Journal Article
In: IEEE Transactions on Evolutionary Computation, pp. 1-1, 2023.
@article{10045029,
title = {Particle Swarm Optimization for Efficiently Evolving Deep Convolutional Neural Networks Using an Autoencoder-based Encoding Strategy},
author = {Gonglin Yuan and Bin Wang and Bing Xue and Mengjie Zhang},
doi = {10.1109/TEVC.2023.3245322},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {IEEE Transactions on Evolutionary Computation},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2864.
Bhattacharjee, Abhiroop; Moitra, Abhishek; Panda, Priyadarshini
XploreNAS: Explore Adversarially Robust & Hardware-efficient Neural Architectures for Non-ideal Xbars Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2302-07769,
title = {XploreNAS: Explore Adversarially Robust & Hardware-efficient Neural Architectures for Non-ideal Xbars},
author = {Abhiroop Bhattacharjee and Abhishek Moitra and Priyadarshini Panda},
url = {https://doi.org/10.48550/arXiv.2302.07769},
doi = {10.48550/arXiv.2302.07769},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2302.07769},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2863.
Cheng, Guangliang; Sun, Peng; Xu, Ting-Bing; Lyu, Shuchang; Lin, Peiwen
Local-to-Global Information Communication for Real-Time Semantic Segmentation Network Search Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2302-08481,
title = {Local-to-Global Information Communication for Real-Time Semantic Segmentation Network Search},
author = {Guangliang Cheng and Peng Sun and Ting-Bing Xu and Shuchang Lyu and Peiwen Lin},
url = {https://doi.org/10.48550/arXiv.2302.08481},
doi = {10.48550/arXiv.2302.08481},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2302.08481},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2862.
Mohammadrezaei, Parsa; Aminan, Mohammad; Soltanian, Mohammad; Borna, Keivan
Improving CNN-based solutions for emotion recognition using evolutionary algorithms Journal Article
In: Results in Applied Mathematics, vol. 18, pp. 100360, 2023, ISSN: 2590-0374.
@article{MOHAMMADREZAEI2023100360,
title = {Improving CNN-based solutions for emotion recognition using evolutionary algorithms},
author = {Parsa Mohammadrezaei and Mohammad Aminan and Mohammad Soltanian and Keivan Borna},
url = {https://www.sciencedirect.com/science/article/pii/S2590037423000067},
doi = {https://doi.org/10.1016/j.rinam.2023.100360},
issn = {2590-0374},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {Results in Applied Mathematics},
volume = {18},
pages = {100360},
abstract = {AI-based approaches, especially deep learning have made remarkable achievements in Speech Emotion Recognition (SER). Needless to say, Convolutional Neural Networks (CNNs) have been the backbone of many of these solutions. Although the use of CNNs have resulted in high performing models, building them needs domain knowledge and direct human intervention. The same issue arises while improving a model. To solve this problem, we use techniques that were firstly introduced in Neural Architecture Search (NAS) and use a genetic process to search for models with improved accuracy. More specifically, we insert blocks with dynamic structures in between the layers of an already existing model and then use genetic operations (i.e. selection, mutation, and crossover) to find the best performing structures. To validate our method, we use this algorithm to improve architectures by searching on the Berlin Database of Emotional Speech (EMODB). The experimental results show at least 1.7% performance improvement in terms of Accuracy on EMODB test set.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
AI-based approaches, especially deep learning have made remarkable achievements in Speech Emotion Recognition (SER). Needless to say, Convolutional Neural Networks (CNNs) have been the backbone of many of these solutions. Although the use of CNNs have resulted in high performing models, building them needs domain knowledge and direct human intervention. The same issue arises while improving a model. To solve this problem, we use techniques that were firstly introduced in Neural Architecture Search (NAS) and use a genetic process to search for models with improved accuracy. More specifically, we insert blocks with dynamic structures in between the layers of an already existing model and then use genetic operations (i.e. selection, mutation, and crossover) to find the best performing structures. To validate our method, we use this algorithm to improve architectures by searching on the Berlin Database of Emotional Speech (EMODB). The experimental results show at least 1.7% performance improvement in terms of Accuracy on EMODB test set.
2861.
Gao, Si; Zheng, Chengjian; Zhang, Xiaofeng; Liu, Shaoli; Wu, Biao; Lu, Kaidi; Zhang, Diankai; Wang, Ning
RCBSR: Re-parameterization Convolution Block for Super-Resolution Proceedings Article
In: Karlinsky, Leonid; Michaeli, Tomer; Nishino, Ko (Ed.): Computer Vision -- ECCV 2022 Workshops, pp. 540–548, Springer Nature Switzerland, Cham, 2023, ISBN: 978-3-031-25063-7.
@inproceedings{10.1007/978-3-031-25063-7_33,
title = {RCBSR: Re-parameterization Convolution Block for Super-Resolution},
author = {Si Gao and Chengjian Zheng and Xiaofeng Zhang and Shaoli Liu and Biao Wu and Kaidi Lu and Diankai Zhang and Ning Wang},
editor = {Leonid Karlinsky and Tomer Michaeli and Ko Nishino},
isbn = {978-3-031-25063-7},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {Computer Vision -- ECCV 2022 Workshops},
pages = {540--548},
publisher = {Springer Nature Switzerland},
address = {Cham},
abstract = {Super resolution(SR) with high efficiency and low power consumption is highly demanded in the actual application scenes. In this paper, We designed a super light-weight SR network with strong feature expression. The network we proposed is named RCBSR. Based on the novel technique of re-parameterization, we adopt a block with multiple paths structure in the training stage and merge multiple paths structure into one single 3$$backslashtimes $$texttimes3 convolution in the inference stage. And then the neural architecture search(NAS) method is adopted to determine amounts of block M and amounts of channel C. Finally, the proposed SR network achieves a fairly good result of PSNR(27.52 dB) with power consumption(0.1 W@30 fps) on the MediaTek Dimensity 9000 platform in the challenge testing stage.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Super resolution(SR) with high efficiency and low power consumption is highly demanded in the actual application scenes. In this paper, We designed a super light-weight SR network with strong feature expression. The network we proposed is named RCBSR. Based on the novel technique of re-parameterization, we adopt a block with multiple paths structure in the training stage and merge multiple paths structure into one single 3$$backslashtimes $$texttimes3 convolution in the inference stage. And then the neural architecture search(NAS) method is adopted to determine amounts of block M and amounts of channel C. Finally, the proposed SR network achieves a fairly good result of PSNR(27.52 dB) with power consumption(0.1 W@30 fps) on the MediaTek Dimensity 9000 platform in the challenge testing stage.
2860.
Maulik, Romit; Egele, Romain; Raghavan, Krishnan; Balaprakash, Prasanna
Quantifying uncertainty for deep learning based forecasting and flow-reconstruction using neural architecture search ensembles Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2302-09748,
title = {Quantifying uncertainty for deep learning based forecasting and flow-reconstruction using neural architecture search ensembles},
author = {Romit Maulik and Romain Egele and Krishnan Raghavan and Prasanna Balaprakash},
url = {https://doi.org/10.48550/arXiv.2302.09748},
doi = {10.48550/arXiv.2302.09748},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2302.09748},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2859.
Wei, Lanning; He, Zhiqiang; Zhao, Huan; Yao, Quanming
Search to Capture Long-range Dependency with Stacking GNNs for Graph Classification Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2302-08671,
title = {Search to Capture Long-range Dependency with Stacking GNNs for Graph Classification},
author = {Lanning Wei and Zhiqiang He and Huan Zhao and Quanming Yao},
url = {https://doi.org/10.48550/arXiv.2302.08671},
doi = {10.48550/arXiv.2302.08671},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2302.08671},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2858.
Han, Fred X.; Mills, Keith G.; Chudak, Fabian; Riahi, Parsa; Salameh, Mohammad; Zhang, Jialin; Lu, Wei; Jui, Shangling; Niu, Di
A General-Purpose Transferable Predictor for Neural Architecture Search Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2302-10835,
title = {A General-Purpose Transferable Predictor for Neural Architecture Search},
author = {Fred X. Han and Keith G. Mills and Fabian Chudak and Parsa Riahi and Mohammad Salameh and Jialin Zhang and Wei Lu and Shangling Jui and Di Niu},
url = {https://doi.org/10.48550/arXiv.2302.10835},
doi = {10.48550/arXiv.2302.10835},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2302.10835},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2857.
Lyu, Zimeng; Ororbia, Alexander; Desell, Travis
Online Evolutionary Neural Architecture Search for Multivariate Non-Stationary Time Series Forecasting Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2302-10347,
title = {Online Evolutionary Neural Architecture Search for Multivariate Non-Stationary Time Series Forecasting},
author = {Zimeng Lyu and Alexander Ororbia and Travis Desell},
url = {https://doi.org/10.48550/arXiv.2302.10347},
doi = {10.48550/arXiv.2302.10347},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2302.10347},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2856.
Kuş, Zeki; Aydin, Musa; Kiraz, Berna; Can, Burhanettin
Neural Architecture Search Using Metaheuristics for Automated Cell Segmentation Proceedings Article
In: Gaspero, Luca Di; Festa, Paola; Nakib, Amir; Pavone, Mario (Ed.): Metaheuristics, pp. 158–171, Springer International Publishing, Cham, 2023, ISBN: 978-3-031-26504-4.
@inproceedings{10.1007/978-3-031-26504-4_12,
title = {Neural Architecture Search Using Metaheuristics for Automated Cell Segmentation},
author = {Zeki Kuş and Musa Aydin and Berna Kiraz and Burhanettin Can},
editor = {Luca Di Gaspero and Paola Festa and Amir Nakib and Mario Pavone},
url = {https://link.springer.com/chapter/10.1007/978-3-031-26504-4_12},
isbn = {978-3-031-26504-4},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {Metaheuristics},
pages = {158--171},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {Deep neural networks give successful results for segmentation of medical images. The need for optimizing many hyper-parameters presents itself as a significant limitation hampering the effectiveness of deep neural network based segmentation task. Manual selection of these hyper-parameters is not feasible as the search space increases. At the same time, these generated networks are problem-specific. Recently, studies that perform segmentation of medical images using Neural Architecture Search (NAS) have been proposed. However, these studies significantly limit the possible network structures and search space. In this study, we proposed a structure called UNAS-Net that brings together the advantages of successful NAS studies and is more flexible in terms of the networks that can be created. The UNAS-Net structure has been optimized using metaheuristics including Differential Evolution (DE) and Local Search (LS), and the generated networks have been tested on Optofil and Cell Nuclei data sets. When the results are examined, it is seen that the networks produced by the heuristic methods improve the performance of the U-Net structure in terms of both segmentation performance and computational complexity. As a result, the proposed structure can be used when the automatic generation of neural networks that provide fast inference as well as successful segmentation performance is desired.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Deep neural networks give successful results for segmentation of medical images. The need for optimizing many hyper-parameters presents itself as a significant limitation hampering the effectiveness of deep neural network based segmentation task. Manual selection of these hyper-parameters is not feasible as the search space increases. At the same time, these generated networks are problem-specific. Recently, studies that perform segmentation of medical images using Neural Architecture Search (NAS) have been proposed. However, these studies significantly limit the possible network structures and search space. In this study, we proposed a structure called UNAS-Net that brings together the advantages of successful NAS studies and is more flexible in terms of the networks that can be created. The UNAS-Net structure has been optimized using metaheuristics including Differential Evolution (DE) and Local Search (LS), and the generated networks have been tested on Optofil and Cell Nuclei data sets. When the results are examined, it is seen that the networks produced by the heuristic methods improve the performance of the U-Net structure in terms of both segmentation performance and computational complexity. As a result, the proposed structure can be used when the automatic generation of neural networks that provide fast inference as well as successful segmentation performance is desired.
2855.
Gülcü, Ayla; Kuş, Zeki
Neural Architecture Search Using Differential Evolution in MAML Framework for Few-Shot Classification Problems Proceedings Article
In: Gaspero, Luca Di; Festa, Paola; Nakib, Amir; Pavone, Mario (Ed.): Metaheuristics, pp. 143–157, Springer International Publishing, Cham, 2023, ISBN: 978-3-031-26504-4.
@inproceedings{10.1007/978-3-031-26504-4_11,
title = {Neural Architecture Search Using Differential Evolution in MAML Framework for Few-Shot Classification Problems},
author = {Ayla Gülcü and Zeki Kuş},
editor = {Luca Di Gaspero and Paola Festa and Amir Nakib and Mario Pavone},
isbn = {978-3-031-26504-4},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {Metaheuristics},
pages = {143--157},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {Model-Agnostic Meta-Learning (MAML) algorithm is an optimization based meta-learning algorithm which aims to find a good initial state of the neural network that can then be adapted to any novel task using a few optimization steps. In this study, we take MAML with a simple four-block convolution architecture as our baseline, and try to improve its few-shot classification performance by using an architecture generated automatically through the neural architecture search process. We use differential evolution algorithm as the search strategy for searching over cells within a predefined search space. We have performed our experiments using two well-known few-shot classification datasets, miniImageNet and FC100 dataset. For each of those datasets, the performance of the original MAML is compared to the performance of our MAML-NAS model under both 1-shot 5-way and 5-shot 5-way settings. The results reveal that MAML-NAS results in better or at least comparable accuracy values for both of the datasets in all settings. More importantly, this performance is achieved by much simpler architectures, that is architectures requiring less floating-point operations.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Model-Agnostic Meta-Learning (MAML) algorithm is an optimization based meta-learning algorithm which aims to find a good initial state of the neural network that can then be adapted to any novel task using a few optimization steps. In this study, we take MAML with a simple four-block convolution architecture as our baseline, and try to improve its few-shot classification performance by using an architecture generated automatically through the neural architecture search process. We use differential evolution algorithm as the search strategy for searching over cells within a predefined search space. We have performed our experiments using two well-known few-shot classification datasets, miniImageNet and FC100 dataset. For each of those datasets, the performance of the original MAML is compared to the performance of our MAML-NAS model under both 1-shot 5-way and 5-shot 5-way settings. The results reveal that MAML-NAS results in better or at least comparable accuracy values for both of the datasets in all settings. More importantly, this performance is achieved by much simpler architectures, that is architectures requiring less floating-point operations.
2854.
Muneer, V; Biju, G M; Bhattacharya, Avik
Optimal Machine Learning based Controller for Shunt Active Power Filter by Auto Machine Learning Journal Article
In: IEEE Journal of Emerging and Selected Topics in Power Electronics, pp. 1-1, 2023.
@article{10049454,
title = {Optimal Machine Learning based Controller for Shunt Active Power Filter by Auto Machine Learning},
author = {V Muneer and G M Biju and Avik Bhattacharya},
url = {https://ieeexplore.ieee.org/abstract/document/10049454},
doi = {10.1109/JESTPE.2023.3244605},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {IEEE Journal of Emerging and Selected Topics in Power Electronics},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2853.
Zhan, Lin; Fan, Jiayuan; Ye, Peng; Cao, Jianjian
A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search For Hyperspectral Image Classification Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2302-11868,
title = {A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search For Hyperspectral Image Classification},
author = {Lin Zhan and Jiayuan Fan and Peng Ye and Jianjian Cao},
url = {https://doi.org/10.48550/arXiv.2302.11868},
doi = {10.48550/arXiv.2302.11868},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2302.11868},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2852.
Zhan, Lin; Fan, Jiayuan; Ye, Peng; Cao, Jianjian
A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search For Hyperspectral Image Classification Journal Article
In: CoRR, vol. abs/2302.11868, 2023.
@article{DBLP:journals/corr/abs-2302-11868b,
title = {A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search For Hyperspectral Image Classification},
author = {Lin Zhan and Jiayuan Fan and Peng Ye and Jianjian Cao},
url = {https://ieeexplore.ieee.org/abstract/document/10052655},
doi = {10.48550/arXiv.2302.11868},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2302.11868},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2851.
Lu, Xiaotong; Dong, Weisheng; Li, Xin; Wu, Jinjian; Li, Leida; Shi, Guangming
Adaptive Search-and-Training for Robust and Efficient Network Pruning Journal Article
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1-14, 2023.
@article{10052756,
title = {Adaptive Search-and-Training for Robust and Efficient Network Pruning},
author = {Xiaotong Lu and Weisheng Dong and Xin Li and Jinjian Wu and Leida Li and Guangming Shi},
url = {https://ieeexplore.ieee.org/abstract/document/10052756},
doi = {10.1109/TPAMI.2023.3248612},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
pages = {1-14},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2850.
Bataineh, Ali Al; Kaur, Devinder; Al-khassaweneh, Mahmood; Al-sharoa, Esraa
Automated CNN Architectural Design: A Simple and Efficient Methodology for Computer Vision Tasks Journal Article
In: Mathematics, vol. 11, no. 5, pp. 1-17, 2023.
@article{RePEc:gam:jmathe:v:11:y:2023:i:5:p:1141-:d:1079919,
title = {Automated CNN Architectural Design: A Simple and Efficient Methodology for Computer Vision Tasks},
author = {Ali Al Bataineh and Devinder Kaur and Mahmood Al-khassaweneh and Esraa Al-sharoa},
url = {https://www.mdpi.com/2227-7390/11/5/1141},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {Mathematics},
volume = {11},
number = {5},
pages = {1-17},
abstract = {Convolutional neural networks (CNN) have transformed the field of computer vision by enabling the automatic extraction of features, obviating the need for manual feature engineering. Despite their success, identifying an optimal architecture for a particular task can be a time-consuming and challenging process due to the vast space of possible network designs. To address this, we propose a novel neural architecture search (NAS) framework that utilizes the clonal selection algorithm (CSA) to automatically design high-quality CNN architectures for image classification problems. Our approach uses an integer vector representation to encode CNN architectures and hyperparameters, combined with a truncated Gaussian mutation scheme that enables efficient exploration of the search space. We evaluated the proposed method on six challenging EMNIST benchmark datasets for handwritten digit recognition, and our results demonstrate that it outperforms nearly all existing approaches. In addition, our approach produces state-of-the-art performance while having fewer trainable parameters than other methods, making it low-cost, simple, and reusable for application to multiple datasets.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Convolutional neural networks (CNN) have transformed the field of computer vision by enabling the automatic extraction of features, obviating the need for manual feature engineering. Despite their success, identifying an optimal architecture for a particular task can be a time-consuming and challenging process due to the vast space of possible network designs. To address this, we propose a novel neural architecture search (NAS) framework that utilizes the clonal selection algorithm (CSA) to automatically design high-quality CNN architectures for image classification problems. Our approach uses an integer vector representation to encode CNN architectures and hyperparameters, combined with a truncated Gaussian mutation scheme that enables efficient exploration of the search space. We evaluated the proposed method on six challenging EMNIST benchmark datasets for handwritten digit recognition, and our results demonstrate that it outperforms nearly all existing approaches. In addition, our approach produces state-of-the-art performance while having fewer trainable parameters than other methods, making it low-cost, simple, and reusable for application to multiple datasets.
2849.
Zheng, Shenghe; Wang, Hongzhi; Mu, Tianyu
DCLP: Neural Architecture Predictor with Curriculum Contrastive Learning Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2302-13020,
title = {DCLP: Neural Architecture Predictor with Curriculum Contrastive Learning},
author = {Shenghe Zheng and Hongzhi Wang and Tianyu Mu},
url = {https://doi.org/10.48550/arXiv.2302.13020},
doi = {10.48550/arXiv.2302.13020},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2302.13020},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2848.
Zheng, Xin; Zhang, Miao; Chen, Chunyang; Zhang, Qin; Zhou, Chuan; Pan, Shirui
Auto-HeG: Automated Graph Neural Network on Heterophilic Graphs Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2302-12357,
title = {Auto-HeG: Automated Graph Neural Network on Heterophilic Graphs},
author = {Xin Zheng and Miao Zhang and Chunyang Chen and Qin Zhang and Chuan Zhou and Shirui Pan},
url = {https://doi.org/10.48550/arXiv.2302.12357},
doi = {10.48550/arXiv.2302.12357},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2302.12357},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2847.
Chen, Angelica; Dohan, David M.; So, David R.
EvoPrompting: Language Models for Code-Level Neural Architecture Search Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2302-14838,
title = {EvoPrompting: Language Models for Code-Level Neural Architecture Search},
author = {Angelica Chen and David M. Dohan and David R. So},
url = {https://doi.org/10.48550/arXiv.2302.14838},
doi = {10.48550/arXiv.2302.14838},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2302.14838},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2846.
He, Yang; Xiao, Lingao
Structured Pruning for Deep Convolutional Neural Networks: A survey Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2303-00566,
title = {Structured Pruning for Deep Convolutional Neural Networks: A survey},
author = {Yang He and Lingao Xiao},
url = {https://doi.org/10.48550/arXiv.2303.00566},
doi = {10.48550/arXiv.2303.00566},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2303.00566},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2845.
Rajesh, Chilukamari; Kumar, Sushil
Äutomatic Retinal Vessel Segmentation Using BTLBO Proceedings Article
In: Thakur, Manoj; Agnihotri, Samar; Rajpurohit, Bharat Singh; Pant, Millie; Deep, Kusum; Nagar, Atulya K. (Ed.): Soft Computing for Problem Solving, pp. 189–200, Springer Nature Singapore, Singapore, 2023, ISBN: 978-981-19-6525-8.
@inproceedings{10.1007/978-981-19-6525-8_15,
title = {Äutomatic Retinal Vessel Segmentation Using BTLBO},
author = {Chilukamari Rajesh and Sushil Kumar},
editor = {Manoj Thakur and Samar Agnihotri and Bharat Singh Rajpurohit and Millie Pant and Kusum Deep and Atulya K. Nagar},
url = {https://link.springer.com/chapter/10.1007/978-981-19-6525-8_15},
isbn = {978-981-19-6525-8},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {Soft Computing for Problem Solving},
pages = {189--200},
publisher = {Springer Nature Singapore},
address = {Singapore},
abstract = {The accuracy of retinal vessel segmentation (RVS) is crucial in assisting physicians in the ophthalmology diagnosis or other systemic diseases. However, manual segmentation needs a high level of knowledge, time-consuming, complex, and prone to errors. As a result, automatic vessel segmentation is required, which might be a significant technological breakthrough in the medical field. We proposed a novel strategy in this paper, that uses neural architecture search (NAS) to optimize a U-net architecture using a binary teaching learning-based optimization (BTLBO) evolutionary algorithm for RVS to increase vessel segmentation performance and reduce the workload of manually developing deep networks with limited computing resources. We used a publicly available DRIVE dataset to examine the proposed approach and showed that the discovered model generated by the proposed approach outperforms existing methods.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The accuracy of retinal vessel segmentation (RVS) is crucial in assisting physicians in the ophthalmology diagnosis or other systemic diseases. However, manual segmentation needs a high level of knowledge, time-consuming, complex, and prone to errors. As a result, automatic vessel segmentation is required, which might be a significant technological breakthrough in the medical field. We proposed a novel strategy in this paper, that uses neural architecture search (NAS) to optimize a U-net architecture using a binary teaching learning-based optimization (BTLBO) evolutionary algorithm for RVS to increase vessel segmentation performance and reduce the workload of manually developing deep networks with limited computing resources. We used a publicly available DRIVE dataset to examine the proposed approach and showed that the discovered model generated by the proposed approach outperforms existing methods.
2844.
Wang, Chunnan; Chen, Bozhou; Li, Geng; Wang, Hongzhi
Automated Graph Neural Network Search Under Federated Learning Framework Journal Article
In: IEEE Transactions on Knowledge and Data Engineering, pp. 1-13, 2023.
@article{10056291,
title = {Automated Graph Neural Network Search Under Federated Learning Framework},
author = {Chunnan Wang and Bozhou Chen and Geng Li and Hongzhi Wang},
url = {https://ieeexplore.ieee.org/abstract/document/10056291},
doi = {10.1109/TKDE.2023.3250264},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {IEEE Transactions on Knowledge and Data Engineering},
pages = {1-13},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2843.
Eisenbach, Markus; Lübberstedt, Jannik; Aganian, Dustin; Gross, Horst-Michael
A Little Bit Attention Is All You Need for Person Re-Identification Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2302-14574,
title = {A Little Bit Attention Is All You Need for Person Re-Identification},
author = {Markus Eisenbach and Jannik Lübberstedt and Dustin Aganian and Horst-Michael Gross},
url = {https://doi.org/10.48550/arXiv.2302.14574},
doi = {10.48550/arXiv.2302.14574},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2302.14574},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2842.
Hasana, Md. Mehedi; Ibrahim, Muhammad; Ali, Md. Sawkat
Speeding Up EfficientNet: Selecting Update Blocks of Convolutional Neural Networks using Genetic Algorithm in Transfer Learning Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2303-00261,
title = {Speeding Up EfficientNet: Selecting Update Blocks of Convolutional Neural Networks using Genetic Algorithm in Transfer Learning},
author = {Md. Mehedi Hasana and Muhammad Ibrahim and Md. Sawkat Ali},
url = {https://doi.org/10.48550/arXiv.2303.00261},
doi = {10.48550/arXiv.2303.00261},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2303.00261},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2841.
Lin, Shih-Ping; Wang, Sheng-De
SGAS-es: Avoiding Performance Collapse by Sequential Greedy Architecture Search with the Early Stopping Indicator Proceedings Article
In: Ärai, Kohei" (Ed.): Ädvances in Information and Communication", pp. 135–154, Springer Nature Switzerland, Cham, 2023, ISBN: 978-3-031-28073-3.
@inproceedings{10.1007/978-3-031-28073-3_10,
title = {SGAS-es: Avoiding Performance Collapse by Sequential Greedy Architecture Search with the Early Stopping Indicator},
author = {Shih-Ping Lin and Sheng-De Wang},
editor = {Kohei" Ärai},
url = {https://link.springer.com/chapter/10.1007/978-3-031-28073-3_10},
isbn = {978-3-031-28073-3},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {Ädvances in Information and Communication"},
pages = {135--154},
publisher = {Springer Nature Switzerland},
address = {Cham},
abstract = {Sequential Greedy Architecture Search (SGAS) reduces the discretization loss of Differentiable Architecture Search (DARTS). However, we observed that SGAS may lead to unstable searched results as DARTS. We referred to this problem as the cascade performance collapse issue. Therefore, we proposed Sequential Greedy Architecture Search with the Early Stopping Indicator (SGAS-es). We adopted the early stopping mechanism in each phase of SGAS to stabilize searched results and further improve the searching ability. The early stopping mechanism is based on the relation among Flat Minima, the largest eigenvalue of the Hessian matrix of the loss function, and performance collapse. We devised a mathematical derivation to show the relation between Flat Minima and the largest eigenvalue. The moving averaged largest eigenvalue is used as an early stopping indicator. Finally, we used NAS-Bench-201 and Fashion-MNIST to confirm the performance and stability of SGAS-es. Moreover, we used EMNIST-Balanced to verify the transferability of searched results. These experiments show that SGAS-es is a robust method and can derive the architecture with good performance and transferability.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Sequential Greedy Architecture Search (SGAS) reduces the discretization loss of Differentiable Architecture Search (DARTS). However, we observed that SGAS may lead to unstable searched results as DARTS. We referred to this problem as the cascade performance collapse issue. Therefore, we proposed Sequential Greedy Architecture Search with the Early Stopping Indicator (SGAS-es). We adopted the early stopping mechanism in each phase of SGAS to stabilize searched results and further improve the searching ability. The early stopping mechanism is based on the relation among Flat Minima, the largest eigenvalue of the Hessian matrix of the loss function, and performance collapse. We devised a mathematical derivation to show the relation between Flat Minima and the largest eigenvalue. The moving averaged largest eigenvalue is used as an early stopping indicator. Finally, we used NAS-Bench-201 and Fashion-MNIST to confirm the performance and stability of SGAS-es. Moreover, we used EMNIST-Balanced to verify the transferability of searched results. These experiments show that SGAS-es is a robust method and can derive the architecture with good performance and transferability.
2840.
Lu, Shun; Hu, Yu; Yang, Longxing; Sun, Zihao; Mei, Jilin; Tan, Jianchao; Song, Chengru
PA&DA: Jointly Sampling PAth and DAta for Consistent NAS Conference
CVPR2023, vol. abs/2302.14772, 2023.
@conference{DBLP:journals/corr/abs-2302-14772,
title = {PA&DA: Jointly Sampling PAth and DAta for Consistent NAS},
author = {Shun Lu and Yu Hu and Longxing Yang and Zihao Sun and Jilin Mei and Jianchao Tan and Chengru Song},
url = {https://doi.org/10.48550/arXiv.2302.14772},
doi = {10.48550/arXiv.2302.14772},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {CVPR2023},
journal = {CoRR},
volume = {abs/2302.14772},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
2839.
Njor, Emil; Madsen, Jan; Fafoutis, Xenofon
Data Aware Neural Architecture Search Proceedings Article
In: Proceedings of tinyML Research Symposium, 2023, (tinyML Research Symposium’23 ; Conference date: 27-03-2023 Through 27-03-2023).
@inproceedings{40cb879dbb9a4fd9bd92ad27b617056f,
title = {Data Aware Neural Architecture Search},
author = {Emil Njor and Jan Madsen and Xenofon Fafoutis},
url = {https://orbit.dtu.dk/en/publications/data-aware-neural-architecture-search},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {Proceedings of tinyML Research Symposium},
abstract = {Neural Architecture Search (NAS) is a popular tool for automatically generating Neural Network (NN) architectures. In early NAS works, these tools typically optimized NN architectures for a single metric, such as accuracy. However, in the case of resource constrained Machine Learning, one single metric is not enough to evaluate a NN architecture. For example, a NN model achieving a high accuracy is not useful if it does not fit inside the flash memory of a given system. Therefore, recent works on NAS for resource constrained systems have investigated various approaches to optimize for multiple metrics. In this paper, we propose that, on top of these approaches, it could be beneficial for NAS optimization of resource constrained systems to also consider input data granularity. We name such a system “Data Aware NAS”, and we provide experimental evidence of its benefits by comparing it to traditional NAS.},
note = {tinyML Research Symposium’23 ; Conference date: 27-03-2023 Through 27-03-2023},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Neural Architecture Search (NAS) is a popular tool for automatically generating Neural Network (NN) architectures. In early NAS works, these tools typically optimized NN architectures for a single metric, such as accuracy. However, in the case of resource constrained Machine Learning, one single metric is not enough to evaluate a NN architecture. For example, a NN model achieving a high accuracy is not useful if it does not fit inside the flash memory of a given system. Therefore, recent works on NAS for resource constrained systems have investigated various approaches to optimize for multiple metrics. In this paper, we propose that, on top of these approaches, it could be beneficial for NAS optimization of resource constrained systems to also consider input data granularity. We name such a system “Data Aware NAS”, and we provide experimental evidence of its benefits by comparing it to traditional NAS.
2838.
Wang, Kun; Han, Ling; Li, Liangzhi
A decoupled search deep network framework for high-resolution remote sensing image classification Journal Article
In: Remote Sensing Letters, vol. 14, no. 3, pp. 243-253, 2023.
@article{doi:10.1080/2150704X.2023.2185110,
title = {A decoupled search deep network framework for high-resolution remote sensing image classification},
author = {Kun Wang and Ling Han and Liangzhi Li},
url = {https://doi.org/10.1080/2150704X.2023.2185110},
doi = {10.1080/2150704X.2023.2185110},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {Remote Sensing Letters},
volume = {14},
number = {3},
pages = {243-253},
publisher = {Taylor & Francis},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2837.
Xue, Yu; Chen, Chen; Słowik, Adam
Neural Architecture Search Based on A Multi-objective Evolutionary Algorithm With Probability Stack Journal Article
In: IEEE Transactions on Evolutionary Computation, pp. 1-1, 2023.
@article{10059145,
title = {Neural Architecture Search Based on A Multi-objective Evolutionary Algorithm With Probability Stack},
author = {Yu Xue and Chen Chen and Adam Słowik},
doi = {10.1109/TEVC.2023.3252612},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {IEEE Transactions on Evolutionary Computation},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2836.
Cao, Chunhong; Xiang, Han; Song, Wei; Yi, Hongbo; Xiao, Fen; Gao, Xieping
Lightweight Multiscale Neural Architecture Search With Spectral–Spatial Attention for Hyperspectral Image Classification Journal Article
In: IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1-15, 2023.
@article{10061276,
title = {Lightweight Multiscale Neural Architecture Search With Spectral–Spatial Attention for Hyperspectral Image Classification},
author = {Chunhong Cao and Han Xiang and Wei Song and Hongbo Yi and Fen Xiao and Xieping Gao},
doi = {10.1109/TGRS.2023.3253247},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
volume = {61},
pages = {1-15},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2835.
Kus, Zeki; Akkan, Can; Gülcü, Ayla
Novel Surrogate Measures Based on a Similarity Network for Neural Architecture Search Journal Article
In: IEEE Access, vol. 11, pp. 22596–22613, 2023.
@article{DBLP:journals/access/KusAG23,
title = {Novel Surrogate Measures Based on a Similarity Network for Neural Architecture Search},
author = {Zeki Kus and Can Akkan and Ayla Gülcü},
url = {https://doi.org/10.1109/ACCESS.2023.3252887},
doi = {10.1109/ACCESS.2023.3252887},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {IEEE Access},
volume = {11},
pages = {22596--22613},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2834.
Cereda, Elia; Crupi, Luca; Risso, Matteo; Burrello, Alessio; Benini, Luca; Giusti, Alessandro; Pagliari, Daniele Jahier; Palossi, Daniele
Deep Neural Network Architecture Search for Accurate Visual Pose Estimation aboard Nano-UAVs Proceedings Article
In: IEEE ICRA 2023, 2023.
@inproceedings{DBLP:journals/corr/abs-2303-01931,
title = {Deep Neural Network Architecture Search for Accurate Visual Pose Estimation aboard Nano-UAVs},
author = {Elia Cereda and Luca Crupi and Matteo Risso and Alessio Burrello and Luca Benini and Alessandro Giusti and Daniele Jahier Pagliari and Daniele Palossi},
url = {https://doi.org/10.48550/arXiv.2303.01931},
doi = {10.48550/arXiv.2303.01931},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {IEEE ICRA 2023},
journal = {CoRR},
volume = {abs/2303.01931},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2833.
Ke, Songyu; Pan, Zheyi; He, Tianfu; Liang, Yuxuan; Zhang, Junbo; Zheng, Yu
AutoSTG+: An automatic framework to discover the optimal network for spatio-temporal graph prediction Journal Article
In: Artificial Intelligence, vol. 318, pp. 103899, 2023, ISSN: 0004-3702.
@article{KE2023103899,
title = {AutoSTG+: An automatic framework to discover the optimal network for spatio-temporal graph prediction},
author = {Songyu Ke and Zheyi Pan and Tianfu He and Yuxuan Liang and Junbo Zhang and Yu Zheng},
url = {https://www.sciencedirect.com/science/article/pii/S0004370223000450},
doi = {https://doi.org/10.1016/j.artint.2023.103899},
issn = {0004-3702},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {Artificial Intelligence},
volume = {318},
pages = {103899},
abstract = {Spatio-temporal graphs (STGs) are important structures to describe urban sensory data, e.g., traffic speed and air quality. Predicting over spatio-temporal graphs enables many essential applications in intelligent cities, such as traffic management and environment analysis. Recently, many deep learning models have been proposed for spatio-temporal graph prediction and achieved significant results. However, manually designing neural networks requires rich domain knowledge and heavy expert efforts, making it impractical for real-world deployments. Therefore, we study automated neural architecture search for spatio-temporal graphs, which meets three challenges: 1) how to define search space for capturing complex spatio-temporal correlations; 2) how to jointly model the explicit and implicit relationships between nodes of an STG; and 3) how to learn network weight parameters related to meta graphs of STGs. To tackle these challenges, we propose a novel neural architecture search framework, entitled AutoSTG+, for automated spatio-temporal graph prediction. In our AutoSTG+, spatial graph convolution and temporal convolution operations are adopted in the search space of AutoSTG+ to capture complex spatio-temporal correlations. Besides, we propose to employ the meta-learning technique to learn the adjacency matrices of spatial graph convolution layers and kernels of temporal convolution layers from the meta knowledge of meta graphs. And specifically, such meta-knowledge is learned by graph meta-knowledge learners, which iteratively aggregate knowledge on the attributed graphs and the similarity graphs. Finally, extensive experiments have been conducted on multiple real-world datasets to demonstrate that AutoSTG+ can find effective network architectures and achieve up to about 20% relative improvements compared to human-designed networks.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Spatio-temporal graphs (STGs) are important structures to describe urban sensory data, e.g., traffic speed and air quality. Predicting over spatio-temporal graphs enables many essential applications in intelligent cities, such as traffic management and environment analysis. Recently, many deep learning models have been proposed for spatio-temporal graph prediction and achieved significant results. However, manually designing neural networks requires rich domain knowledge and heavy expert efforts, making it impractical for real-world deployments. Therefore, we study automated neural architecture search for spatio-temporal graphs, which meets three challenges: 1) how to define search space for capturing complex spatio-temporal correlations; 2) how to jointly model the explicit and implicit relationships between nodes of an STG; and 3) how to learn network weight parameters related to meta graphs of STGs. To tackle these challenges, we propose a novel neural architecture search framework, entitled AutoSTG+, for automated spatio-temporal graph prediction. In our AutoSTG+, spatial graph convolution and temporal convolution operations are adopted in the search space of AutoSTG+ to capture complex spatio-temporal correlations. Besides, we propose to employ the meta-learning technique to learn the adjacency matrices of spatial graph convolution layers and kernels of temporal convolution layers from the meta knowledge of meta graphs. And specifically, such meta-knowledge is learned by graph meta-knowledge learners, which iteratively aggregate knowledge on the attributed graphs and the similarity graphs. Finally, extensive experiments have been conducted on multiple real-world datasets to demonstrate that AutoSTG+ can find effective network architectures and achieve up to about 20% relative improvements compared to human-designed networks.
2832.
Brown, Austin; Gupta, Maanak; Abdelsalam, Mahmoud
Automated Machine Learning for Deep Learning based Malware Detection Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2303-01679,
title = {Automated Machine Learning for Deep Learning based Malware Detection},
author = {Austin Brown and Maanak Gupta and Mahmoud Abdelsalam},
url = {https://doi.org/10.48550/arXiv.2303.01679},
doi = {10.48550/arXiv.2303.01679},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2303.01679},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2831.
Santana, Roberto; Hidalgo-Cenalmor, Ivan; Garciarena, Unai; Mendiburu, Alexander; Lozano, José Antonio
Neuroevolutionary algorithms driven by neuron coverage metrics for semi-supervised classification Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2303-02801,
title = {Neuroevolutionary algorithms driven by neuron coverage metrics for semi-supervised classification},
author = {Roberto Santana and Ivan Hidalgo-Cenalmor and Unai Garciarena and Alexander Mendiburu and José Antonio Lozano},
url = {https://doi.org/10.48550/arXiv.2303.02801},
doi = {10.48550/arXiv.2303.02801},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2303.02801},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2830.
Lee, Jong-Ryul; Moon, Yong-Hyuk
Bespoke: A Block-Level Neural Network Optimization Framework for Low-Cost Deployment Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2303-01913,
title = {Bespoke: A Block-Level Neural Network Optimization Framework for Low-Cost Deployment},
author = {Jong-Ryul Lee and Yong-Hyuk Moon},
url = {https://doi.org/10.48550/arXiv.2303.01913},
doi = {10.48550/arXiv.2303.01913},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2303.01913},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2829.
Shen, Xuan; Wang, Yaohua; Lin, Ming; Huang, Yilun; Tang, Hao; Sun, Xiuyu; Wang, Yanzhi
DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2303-02165,
title = {DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network},
author = {Xuan Shen and Yaohua Wang and Ming Lin and Yilun Huang and Hao Tang and Xiuyu Sun and Yanzhi Wang},
url = {https://doi.org/10.48550/arXiv.2303.02165},
doi = {10.48550/arXiv.2303.02165},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2303.02165},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2828.
Ali, Mohamed Nabih; Paissan, Francesco; Falavigna, Daniele; Brutti, Alessio
Scaling strategies for on-device low-complexity source separation with Conv-Tasnet Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2303-03005,
title = {Scaling strategies for on-device low-complexity source separation with Conv-Tasnet},
author = {Mohamed Nabih Ali and Francesco Paissan and Daniele Falavigna and Alessio Brutti},
url = {https://doi.org/10.48550/arXiv.2303.03005},
doi = {10.48550/arXiv.2303.03005},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2303.03005},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2827.
Chitty-Venkata, Krishna Teja; Emani, Murali; Vishwanath, Venkatram; Somani, Arun K.
Neural Architecture Search Benchmarks: Insights and Survey Journal Article
In: IEEE Access, vol. 11, pp. 25217–25236, 2023.
@article{DBLP:journals/access/ChittyVenkataEVS23,
title = {Neural Architecture Search Benchmarks: Insights and Survey},
author = {Krishna Teja Chitty-Venkata and Murali Emani and Venkatram Vishwanath and Arun K. Somani},
url = {https://doi.org/10.1109/ACCESS.2023.3253818},
doi = {10.1109/ACCESS.2023.3253818},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {IEEE Access},
volume = {11},
pages = {25217--25236},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2826.
Qin, Dalin; Wang, Chenxi; Wen, Qingsong; Chen, Weiqi; Sun, Liang; Wang, Yi
Personalized Federated DARTS for Electricity Load Forecasting of Individual Buildings Journal Article
In: IEEE Transactions on Smart Grid, pp. 1-1, 2023.
@article{10063999,
title = {Personalized Federated DARTS for Electricity Load Forecasting of Individual Buildings},
author = {Dalin Qin and Chenxi Wang and Qingsong Wen and Weiqi Chen and Liang Sun and Yi Wang},
doi = {10.1109/TSG.2023.3253855},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {IEEE Transactions on Smart Grid},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2825.
Alaiad, Ahmad; Migdady, Aya; Al-Khatib, Ra’ed M.; Alzoubi, Omar; Zitar, Raed Abu; Abualigah, Laith
Autokeras Approach: A Robust Automated Deep Learning Network for Diagnosis Disease Cases in Medical Images Journal Article
In: Journal of Imaging, vol. 9, no. 3, 2023, ISSN: 2313-433X.
@article{jimaging9030064,
title = {Autokeras Approach: A Robust Automated Deep Learning Network for Diagnosis Disease Cases in Medical Images},
author = {Ahmad Alaiad and Aya Migdady and Ra’ed M. Al-Khatib and Omar Alzoubi and Raed Abu Zitar and Laith Abualigah},
url = {https://www.mdpi.com/2313-433X/9/3/64},
doi = {10.3390/jimaging9030064},
issn = {2313-433X},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {Journal of Imaging},
volume = {9},
number = {3},
abstract = {Automated deep learning is promising in artificial intelligence (AI). However, a few applications of automated deep learning networks have been made in the clinical medical fields. Therefore, we studied the application of an open-source automated deep learning framework, Autokeras, for detecting smear blood images infected with malaria parasites. Autokeras is able to identify the optimal neural network to perform the classification task. Hence, the robustness of the adopted model is due to it not needing any prior knowledge from deep learning. In contrast, the traditional deep neural network methods still require more construction to identify the best convolutional neural network (CNN). The dataset used in this study consisted of 27,558 blood smear images. A comparative process proved the superiority of our proposed approach over other traditional neural networks. The evaluation results of our proposed model achieved high efficiency with impressive accuracy, reaching 95.6% when compared with previous competitive models.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Automated deep learning is promising in artificial intelligence (AI). However, a few applications of automated deep learning networks have been made in the clinical medical fields. Therefore, we studied the application of an open-source automated deep learning framework, Autokeras, for detecting smear blood images infected with malaria parasites. Autokeras is able to identify the optimal neural network to perform the classification task. Hence, the robustness of the adopted model is due to it not needing any prior knowledge from deep learning. In contrast, the traditional deep neural network methods still require more construction to identify the best convolutional neural network (CNN). The dataset used in this study consisted of 27,558 blood smear images. A comparative process proved the superiority of our proposed approach over other traditional neural networks. The evaluation results of our proposed model achieved high efficiency with impressive accuracy, reaching 95.6% when compared with previous competitive models.
2824.
Wang, Zhipeng; Liu, Rengkui; Gao, Yi; Tang, Yuanjie
Metro Track Geometry Defect Identification Model Based on Car-Body Vibration Data and Differentiable Architecture Search Journal Article
In: Applied Sciences, vol. 13, no. 6, 2023, ISSN: 2076-3417.
@article{app13063457,
title = {Metro Track Geometry Defect Identification Model Based on Car-Body Vibration Data and Differentiable Architecture Search},
author = {Zhipeng Wang and Rengkui Liu and Yi Gao and Yuanjie Tang},
url = {https://www.mdpi.com/2076-3417/13/6/3457},
doi = {10.3390/app13063457},
issn = {2076-3417},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {Applied Sciences},
volume = {13},
number = {6},
abstract = {Efficient and low-cost modes for detecting metro track geometry defects (TGDs) are essential for condition-prediction-based preventive maintenance, which can help improve the safety of metro operations and reduce the maintenance cost of metro tracks. Compared with the traditional TGD detection method that utilizes the track geometry car, the method that uses a portable detector to acquire the car-body vibration data (CVD) can be used on an ordinary in-service train without occupying the metro schedule line, thereby improving efficiency and reducing the cost. A convolutional neural network-based identification model for TGD, built on a differentiable architecture search, is proposed in this study to employ only the CVD acquired by a portable detector for integrated identification of the type and severity level of TGDs. Second, the random oversampling method is introduced, and a strategy for applying this method is proposed to improve the poor training effect of the model caused by the natural class-imbalance problem arising from the TGD dataset. Subsequently, a comprehensive performance-evaluation metric (track geometry defect F-score) is designed by considering the actual management needs of the metro infrastructure. Finally, a case study is conducted using actual field data collected from Beijing Subway to validate the proposed model.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Efficient and low-cost modes for detecting metro track geometry defects (TGDs) are essential for condition-prediction-based preventive maintenance, which can help improve the safety of metro operations and reduce the maintenance cost of metro tracks. Compared with the traditional TGD detection method that utilizes the track geometry car, the method that uses a portable detector to acquire the car-body vibration data (CVD) can be used on an ordinary in-service train without occupying the metro schedule line, thereby improving efficiency and reducing the cost. A convolutional neural network-based identification model for TGD, built on a differentiable architecture search, is proposed in this study to employ only the CVD acquired by a portable detector for integrated identification of the type and severity level of TGDs. Second, the random oversampling method is introduced, and a strategy for applying this method is proposed to improve the poor training effect of the model caused by the natural class-imbalance problem arising from the TGD dataset. Subsequently, a comprehensive performance-evaluation metric (track geometry defect F-score) is designed by considering the actual management needs of the metro infrastructure. Finally, a case study is conducted using actual field data collected from Beijing Subway to validate the proposed model.
2823.
Mecharbat, Lotfi Abdelkrim; Benmeziane, Hadjer; Ouranoughi, Hamza; Niar, Smaïl
HyT-NAS: Hybrid Transformers Neural Architecture Search for Edge Devices Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2303-04440b,
title = {HyT-NAS: Hybrid Transformers Neural Architecture Search for Edge Devices},
author = {Lotfi Abdelkrim Mecharbat and Hadjer Benmeziane and Hamza Ouranoughi and Smaïl Niar},
url = {https://doi.org/10.48550/arXiv.2303.04440},
doi = {10.48550/arXiv.2303.04440},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2303.04440},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2822.
Wendlinger, Lorenz; Granitzer, Michael; Fellicious, Christofer
Pooling Graph Convolutional Networks for Structural Performance Prediction Proceedings Article
In: Nicosia, Giuseppe; Ojha, Varun; Malfa, Emanuele La; Malfa, Gabriele La; Pardalos, Panos; Fatta, Giuseppe Di; Giuffrida, Giovanni; Umeton, Renato (Ed.): Machine Learning, Optimization, and Data Science, pp. 1–16, Springer Nature Switzerland, Cham, 2023, ISBN: 978-3-031-25891-6.
@inproceedings{10.1007/978-3-031-25891-6_1,
title = {Pooling Graph Convolutional Networks for Structural Performance Prediction},
author = {Lorenz Wendlinger and Michael Granitzer and Christofer Fellicious},
editor = {Giuseppe Nicosia and Varun Ojha and Emanuele La Malfa and Gabriele La Malfa and Panos Pardalos and Giuseppe Di Fatta and Giovanni Giuffrida and Renato Umeton},
url = {https://link.springer.com/chapter/10.1007/978-3-031-25891-6_1},
isbn = {978-3-031-25891-6},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {Machine Learning, Optimization, and Data Science},
pages = {1--16},
publisher = {Springer Nature Switzerland},
address = {Cham},
abstract = {Neural Architecture Search can help in finding high-performance task specific neural network architectures. However, the training of architectures that is required for fitness computation can be prohibitively expensive. Employing surrogate models as performance predictors can reduce or remove the need for these costly evaluations. We present a deep graph learning approach that achieves state-of-the-art performance in multiple NAS performance prediction benchmarks. In contrast to other methods, this model is purely supervised, which can be a methodologic advantage, as it does not rely on unlabeled instances sampled from complex search spaces.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Neural Architecture Search can help in finding high-performance task specific neural network architectures. However, the training of architectures that is required for fitness computation can be prohibitively expensive. Employing surrogate models as performance predictors can reduce or remove the need for these costly evaluations. We present a deep graph learning approach that achieves state-of-the-art performance in multiple NAS performance prediction benchmarks. In contrast to other methods, this model is purely supervised, which can be a methodologic advantage, as it does not rely on unlabeled instances sampled from complex search spaces.
2821.
Wen, Hao; Li, Yuanchun; Zhang, Zunshuai; Jiang, Shiqi; Ye, Xiaozhou; Ouyang, Ye; Zhang, Ya-Qin; Liu, Yunxin
AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2303-07129,
title = {AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments},
author = {Hao Wen and Yuanchun Li and Zunshuai Zhang and Shiqi Jiang and Xiaozhou Ye and Ye Ouyang and Ya-Qin Zhang and Yunxin Liu},
url = {https://doi.org/10.48550/arXiv.2303.07129},
doi = {10.48550/arXiv.2303.07129},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2303.07129},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2820.
Gu, Jianyang; Wang, Kai; Luo, Hao; Chen, Chen; Jiang, Wei; Fang, Yuqiang; Zhang, Shanghang; You, Yang; Zhao, Jian
MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2303-07065,
title = {MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID},
author = {Jianyang Gu and Kai Wang and Hao Luo and Chen Chen and Wei Jiang and Yuqiang Fang and Shanghang Zhang and Yang You and Jian Zhao},
url = {https://doi.org/10.48550/arXiv.2303.07065},
doi = {10.48550/arXiv.2303.07065},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2303.07065},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2819.
Choi, Wonhyeok; Im, Sunghoon
Dynamic Neural Network for Multi-Task Learning Searching across Diverse Network Topologies Technical Report
2023.
@techreport{DBLP:journals/corr/abs-2303-06856,
title = {Dynamic Neural Network for Multi-Task Learning Searching across Diverse Network Topologies},
author = {Wonhyeok Choi and Sunghoon Im},
url = {https://doi.org/10.48550/arXiv.2303.06856},
doi = {10.48550/arXiv.2303.06856},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2303.06856},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}