AutoML | Literature on Neural Architecture Search

3160.

Kancharagunta, Kishan Babu; Marapatla, AjayDilipKumar; Manchala, Harikesh; Pillalamarri, Uday Kiran; Kanthala, Danush; Musku, Sai Ritish Reddy; Kamsani, Charan Sai

Cyclone Intensity Estimation: A Studyof Neural Architecture Search andTransfer Learning in CNNs Miscellaneous

2024.

Abstract | Links | BibTeX

@misc{PPR:PPR823571,

title = {Cyclone Intensity Estimation: A Studyof Neural Architecture Search andTransfer Learning in CNNs},

author = {Kishan Babu Kancharagunta and AjayDilipKumar Marapatla and Harikesh Manchala and Uday Kiran Pillalamarri and Danush Kanthala and Sai Ritish Reddy Musku and Charan Sai Kamsani},

url = {https://doi.org/10.21203/rs.3.rs-4093387/v1},

doi = {10.21203/rs.3.rs-4093387/v1},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

publisher = {Research Square},

abstract = {Tropical cyclones (TCs) are severe weather phenomena that can significantly affect human lives. These events can lead to calamities characterized by strong sustainable winds and enormous waves. We proposed an architecture based on convolutional neural networks (CNNs) to tackle this problem. This method makes use of cyclone infrared images. Using customized FCL architectures, we used transfer learning and fine-tuning on CNN architectures such as VGG16, VGG19, and ResNet50, both with and without data augmentation. Fine-tuning involved 4 layers of VGG16, 8 layers of VGG19, and 12 layers of ResNet50 to capture cyclone features effectively. The CNN models were used to these architectures to extract features, and the resulting feature maps were fed to various combinations of Fully Connected Networks (FCL). The most optimistic results were achieved with the VGG16 + FCL (128 x 64 x 1) architecture through transfer learning, producing a Mean Absolute Error (MAE) of 7.51 kts, Root Mean Square Error (RMSE) of 9.63 kts, and an R2 Score of 0.92. Consequently, we identified this model as the foundational basis for Neural Architecture Search (NAS) to enhance the FCL architecture. The NAS process generated various architectures, among which the VGG16 + FCL (128 x 128 x 1) architecture stood out with notable performance, featuring a Mean Squared Error (MSE) of 6.77 kts, RMSE of 8.88 kts, and an impressive R2-Score of 0.945.},

keywords = {},

pubstate = {published},

tppubtype = {misc}

}

Close

3159.

Zhou, Qinqin; Sheng, Kekai; Zheng, Xiawu; Li, Ke; Tian, Yonghong; Chen, Jie; Ji, Rongrong

Training-Free Transformer Architecture Search With Zero-Cost Proxy Guided Evolution Journal Article

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1-17, 2024.

Links | BibTeX

3158.

Yu, Hongyuan; Wan, Cheng; Liu, Mengchen; Chen, Dongdong; Xiao, Bin; Dai, Xiyang

Real-Time Image Segmentation via Hybrid Convolutional-Transformer Architecture Search Technical Report

2024.

Links | BibTeX

3157.

Benmeziane, Hadjer; Maghraoui, Kaoutar El; Ouarnoughi, Hamza; Niar, Smail

Grassroots operator search for model edge adaptation using mathematical search space Journal Article

In: Future Generation Computer Systems, vol. 157, pp. 29-40, 2024, ISSN: 0167-739X.

Abstract | Links | BibTeX

@article{BENMEZIANE202429,

title = {Grassroots operator search for model edge adaptation using mathematical search space},

author = {Hadjer Benmeziane and Kaoutar El Maghraoui and Hamza Ouarnoughi and Smail Niar},

url = {https://www.sciencedirect.com/science/article/pii/S0167739X24001018},

doi = {https://doi.org/10.1016/j.future.2024.03.029},

issn = {0167-739X},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {Future Generation Computer Systems},

volume = {157},

pages = {29-40},

abstract = {Hardware-aware Neural Architecture Search (HW-NAS) is increasingly being used to design efficient deep learning architectures. An efficient and flexible search space is crucial to the success of HW-NAS. Current approaches focus on designing a macro-architecture and searching for the architecture’s hyperparameters based on a set of possible values. This approach is biased by the expertise of deep learning (DL) engineers and standard modeling approaches. In this paper, we present a Grassroots Operator Search (GOS) methodology. Our HW-NAS adapts a given model for edge devices by searching for efficient operator replacement. We express each operator as a set of mathematical instructions that capture its behavior. The mathematical instructions are then used as the basis for searching and selecting efficient replacement operators that maintain the accuracy of the original model while reducing computational complexity. Our approach is grassroots since it relies on the mathematical foundations to construct new and efficient operators for DL architectures. We demonstrate on various DL models, that our method consistently outperforms the original models on two edge devices, namely Redmi Note 7S and Raspberry Pi3, with a minimum of 2.2x speedup while maintaining high accuracy. Additionally, we showcase a use case of our GOS approach in pulse rate estimation on wristband devices, where we achieve state-of-the-art performance, while maintaining reduced computational complexity, demonstrating the effectiveness of our approach in practical applications.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Close

3156.

Rajapakshe, Thejan; Rana, Rajib; Khalifa, Sara; Sisman, Berrak; Schuller, Björn W.; Busso, Carlos

emoDARTS: Joint Optimisation of CNN & Sequential Neural Network Architectures for Superior Speech Emotion Recognition Technical Report

2024.

Links | BibTeX

3155.

Mills, Keith G.; Han, Fred X.; Salameh, Mohammad; Lu, Shengyao; Zhou, Chunhua; He, Jiao; Sun, Fengyu; Niu, Di

Building Optimal Neural Architectures using Interpretable Knowledge Technical Report

2024.

Links | BibTeX

3154.

Wu, Yongtao; Liu, Fanghui; Simon-Gabriel, Carl-Johann; Chrysos, Grigorios G.; Cevher, Volkan

Robust NAS under adversarial training: benchmark, theory, and beyond Technical Report

2024.

Links | BibTeX

3153.

Lin, Wei; Peng, Xu; Yu, Zhengtao; Jin, Taisong

Hypergraph Neural Architecture Search Proceedings Article

In: Wooldridge, Michael J.; Dy, Jennifer G.; Natarajan, Sriraam (Ed.): Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, February 20-27, 2024, Vancouver, Canada, pp. 13837–13845, AAAI Press, 2024.

Links | BibTeX

3152.

Liang, Xinyan; Fu, Pinhan; Guo, Qian; Zheng, Keyin; Qian, Yuhua

DC-NAS: Divide-and-Conquer Neural Architecture Search for Multi-Modal Classification Proceedings Article

In: Wooldridge, Michael J.; Dy, Jennifer G.; Natarajan, Sriraam (Ed.): Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, February 20-27, 2024, Vancouver, Canada, pp. 13754–13762, AAAI Press, 2024.

Links | BibTeX

3151.

Cai, Zicheng; Chen, Lei; Liu, Peng; Ling, Tongtao; Lai, Yutao

EG-NAS: Neural Architecture Search with Fast Evolutionary Exploration Proceedings Article

In: Wooldridge, Michael J.; Dy, Jennifer G.; Natarajan, Sriraam (Ed.): Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, February 20-27, 2024, Vancouver, Canada, pp. 11159–11167, AAAI Press, 2024.

Links | BibTeX

3150.

Cai, Jie; Wang, Xin; Li, Haoyang; Zhang, Ziwei; Zhu, Wenwu

Multimodal Graph Neural Architecture Search under Distribution Shifts Proceedings Article

In: Wooldridge, Michael J.; Dy, Jennifer G.; Natarajan, Sriraam (Ed.): Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, February 20-27, 2024, Vancouver, Canada, pp. 8227–8235, AAAI Press, 2024.

Links | BibTeX

3149.

Peng, Chensheng; Zeng, Zhaoyu; Gao, Jinling; Zhou, Jundong; Tomizuka, Masayoshi; Wang, Xinbing; Zhou, Chenghu; Ye, Nanyang

PNAS-MOT: Multi-Modal Object Tracking with Pareto Neural Architecture Search Miscellaneous

2024.

Links | BibTeX

3148.

Levchenko, Denis; Rappos, Efstratios; Ataee, Shabnam; Nigro, Biagio; Robert, Stephan

Chain-structured neural architecture search for financial time series forecasting Technical Report

2024.

Links | BibTeX

3147.

Ali, Muhammad Junaid; Moalic, Laurent; Essaid, Mokhtar; Idoumghar, Lhassane

Robust Neural Architecture Search Using Differential Evolution for Medical Images Proceedings Article

In: Smith, Stephen; Correia, João; Cintrano, Christian (Ed.): Applications of Evolutionary Computation, pp. 163–179, Springer Nature Switzerland, Cham, 2024, ISBN: 978-3-031-56855-8.

Abstract | Links | BibTeX

3146.

He, Zhimin; Deng, Maijie; Zheng, Shenggen; Li, Lvzhou; Situ, Haozhen

Training-Free Quantum Architecture Search Proceedings Article

In: Wooldridge, Michael J.; Dy, Jennifer G.; Natarajan, Sriraam (Ed.): Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, February 20-27, 2024, Vancouver, Canada, pp. 12430–12438, AAAI Press, 2024.

Links | BibTeX

3145.

Benmeziane, Hadjer

A Pre-Search Evaluation Framework for Assessing Search Space Complexity Proceedings Article

In: The Second Tiny Papers Track at ICLR 2024, 2024.

Links | BibTeX

3144.

Garcia-Garcia, Cosijopii; Morales-Reyes, Alicia; Escalante, Hugo Jair

Progressive Self-supervised Multi-objective NAS for Image Classification Proceedings Article

In: Smith, Stephen; Correia, João; Cintrano, Christian (Ed.): Applications of Evolutionary Computation, pp. 180–195, Springer Nature Switzerland, Cham, 2024, ISBN: 978-3-031-56855-8.

Abstract | Links | BibTeX

3143.

Feng, Tai-Che; Wang, Sheng-De

VP-DARTS: Validated Pruning Differentiable Architecture Search Proceedings Article

In: Rocha, Ana Paula; Steels, Luc; Herik, H. Jaap (Ed.): Proceedings of the 16th International Conference on Agents and Artificial Intelligence, ICAART 2024, Volume 2, Rome, Italy, February 24-26, 2024, pp. 47–57, SCITEPRESS, 2024.

Links | BibTeX

3142.

Zhu, Chendi; Li, Lujun; Wu, Yuli; Sun, Zhengxing

SasWOT: Real-Time Semantic Segmentation Architecture Search WithOut Training Proceedings Article

In: Wooldridge, Michael J.; Dy, Jennifer G.; Natarajan, Sriraam (Ed.): Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, February 20-27, 2024, Vancouver, Canada, pp. 7722–7730, AAAI Press, 2024.

Links | BibTeX

3141.

Lu, Liming; Chen, Zhenghan; Lu, Xiaoyu; Rao, Yihang; Li, Lujun; Pang, Shuchao

UniADS: Universal Architecture-Distiller Search for Distillation Gap Proceedings Article

In: Wooldridge, Michael J.; Dy, Jennifer G.; Natarajan, Sriraam (Ed.): Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, February 20-27, 2024, Vancouver, Canada, pp. 14167–14174, AAAI Press, 2024.

Links | BibTeX

3140.

Diaz, Edicson Santiago Bonilla; Naredo, Enrique; D'ıaz, Nicolas Francisco Mateo; Dias, Douglas Mota; Diaz, Maria Alejandra Bonilla; Harnett, Susan; Ryan, Conor

Neural Architecture Search for Bearing Fault Classification Proceedings Article

In: Rocha, Ana Paula; Steels, Luc; Herik, H. Jaap (Ed.): Proceedings of the 16th International Conference on Agents and Artificial Intelligence, ICAART 2024, Volume 2, Rome, Italy, February 24-26, 2024, pp. 288–300, SCITEPRESS, 2024.

Links | BibTeX

3139.

Xia, Yizhang; Song, Shihao; Hou, Zhanglu; Xu, Junwen; Zou, Juan; Liu, Yuan; Yang, Shengxiang

An Evolutionary Network Architecture Search Framework with Adaptive Multimodal Fusion for Hand Gesture Recognition Technical Report

2024.

Links | BibTeX

3138.

Tzolopoulos, Georgios; Korgialas, Christos; Kotropoulos, Constantine

On Spectrogram Analysis in a Multiple Classifier Fusion Framework for Power Grid Classification Using Electric Network Frequency Proceedings Article

In: Santana, Modesto Castrillón; Marsico, Maria De; Fred, Ana L. N. (Ed.): Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2024, Rome, Italy, February 24-26, 2024, pp. 91–99, SCITEPRESS, 2024.

Links | BibTeX

3137.

Cai, Zicheng; Chen, Lei; Ling, Tongtao; Liu, Hai-Lin

STO-DARTS: Stochastic Bilevel Optimization for Differentiable Neural Architecture Search Journal Article

In: IEEE Transactions on Emerging Topics in Computational Intelligence, pp. 1-12, 2024.

Links | BibTeX

3136.

Han, Xian-Hua; Jiang, Huiyan; Chen, Yen-Wei

Hyperspectral Image Reconstruction Using Hierarchical Neural Architecture Search from A Snapshot Image Proceedings Article

In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2500-2504, 2024.

Links | BibTeX

3135.

Rana, Amrita; Kim, Kyung Ki

NAS-OD: Neural Architecture Search for Object Detection Proceedings Article

In: 2024 International Conference on Electronics, Information, and Communication (ICEIC), pp. 1-3, 2024.

Links | BibTeX

3134.

Ma, Lianbo; Li, Nan; Zhu, Peican; Tang, Keke; Khan, Asad; Wang, Feng; Yu, Guo

A Novel Fuzzy Neural Network Architecture Search Framework for Defect Recognition With Uncertainties Journal Article

In: IEEE Transactions on Fuzzy Systems, pp. 1-12, 2024.

Links | BibTeX

3133.

Jin, Cong; Huang, Jin-jie

Inner Loop-Based Modified Differentiable Architecture Search Journal Article

In: IEEE Access, vol. 12, pp. 41918–41933, 2024.

Links | BibTeX

3132.

Xu, Hongyan; Pei, Xiaohuan; Su, Xiu; You, Shan; Xu, Chang

TCNAS: Transformer Architecture Evolving in Code Clone Detection Proceedings Article

In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5745-5749, 2024.

Links | BibTeX

3131.

Fu, Hongming; Wu, Guanyao; Liu, Zhu; Yan, Tiantian; Liu, Jinyuan

Segmentation-Driven Infrared and Visible Image Fusion Via Transformer-Enhanced Architecture Searching Proceedings Article

In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4230-4234, 2024.

Links | BibTeX

3130.

Liao, Yugang; Li, Junqing; Wei, Shuwei; Xiao, Xiumei

Evolutionary Search via channel attention based parameter inheritance and stochastic uniform sampled training Journal Article

In: Computer Vision and Image Understanding, vol. 243, pp. 104000, 2024, ISSN: 1077-3142.

Abstract | Links | BibTeX

@article{LIAO2024104000,

title = {Evolutionary Search via channel attention based parameter inheritance and stochastic uniform sampled training},

author = {Yugang Liao and Junqing Li and Shuwei Wei and Xiumei Xiao},

url = {https://www.sciencedirect.com/science/article/pii/S107731422400081X},

doi = {https://doi.org/10.1016/j.cviu.2024.104000},

issn = {1077-3142},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {Computer Vision and Image Understanding},

volume = {243},

pages = {104000},

abstract = {Convolutional neural networks’ performance is significantly affected by their architecture. Different algorithms have been developed to aid in automating the network structure selection. Recently, evolutionary neural architecture search (ENAS) methods have gained increasing number of attentions due to their excellent global search capability. Nevertheless, evolutionary neural architecture can be computationally expensive since improving evolution typically involves many performance evaluations. This study introduces a framework utilizing evolutionary search for a lightweight channel attention convolutional network. It leverages stochastic uniform sampled and parameter inheritance to address these challenges. The lightweight channel attention method is applied to the model to make it more capable of extracting features while using fewer parameters. In this framework, parent individuals undergo stochastic sampling and receive training repeatedly on each mini-batch of the training dataset. The strategy of parameter inheritance enables the assessment of offspring individuals’ fitness without fully training the offspring candidate network. Compared to existing methods on standard-bench (CIFAR-10, CIFAR-100, ImageNet) and real-world datasets(NEU-CLS, Chest Xray2017), our model demonstrated superior search efficiency by several orders of magnitude. Our experiments showed that Stochastic uniform sampled evolutionary Network (SUSE-Net) achieved the lowest error rate among state-of-the-art NAS models, with 2.55% for CIFAR-10, 14.8% for CIFAR-100, and 23.2% for ImageNet dataset. This results indicate that the proposed algorithm is not only more computationally efficient, but also competitive with existing methods in terms of learning performance.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Close

3129.

Niu, Ruicheng; Zhu, Ziyuan; Li, Chaofei; Meng, Dan

Search Robust and Adaptable Architecture Proceedings Article

In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5155-5159, 2024.

Links | BibTeX

3128.

Su, Xiu; You, Shan; Xu, Hongyan; Li, Xiuxing; Long, Jun; Chen, Yi; Xu, Chang

Beyond the Limit of Weight-Sharing: Pioneering Space-Evolving NAS with Large Language Models Proceedings Article

In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6225-6229, 2024.

Links | BibTeX

3127.

Chen, Yule; Liang, Hong; Jiao, Shaohua

NAS-MFF:NAS-Guided Multiscale Feature Fusion Network with Pareto Optimization for Sonar Images Classification Journal Article

In: IEEE Sensors Journal, pp. 1-1, 2024.

Links | BibTeX

3126.

Zhang, Zhaokai; Feng, Tianpeng; Liu, Yang; Sheng, Chunnan; Wang, Fanyi; Cai, He

DBS: Differentiable Budget-Aware Searching For Channel Pruning Proceedings Article

In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5810-5814, 2024.

Links | BibTeX

3125.

Xia, Renqiu; Zhang, Dongyuan; Dong, Yixin; Zhao, Juanping; Liao, Wenlong; He, Tao; Yan, Junchi

Efficient Architecture Search for Real-Time Instance Segmentation Proceedings Article

In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3310-3314, 2024.

Links | BibTeX

3124.

Lee, Junghyup; Ham, Bumsub

AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search Technical Report

2024.

Links | BibTeX

3123.

Zhou, Qiqi; Zhu, Yichen

When Training-Free Nas Meets Vision Transformers: A Neural Tangent Kernel Perspective Proceedings Article

In: 2024.

Links | BibTeX

3122.

Lv, Zeqiong; Qian, Chao; Yen, Gary G.; Sun, Yanan

Analyzing the Expected Hitting Time of Evolutionary Computation-Based Neural Architecture Search Algorithms Journal Article

In: IEEE Transactions on Emerging Topics in Computational Intelligence, pp. 1-13, 2024.

Links | BibTeX

3121.

Sakuma, Yuiko; Yoshimura, Masakazu; Otsuka, Junji; Irie, Atsushi; Ohashi, Takeshi

Mixed-precision Supernet Training from Vision Foundation Models using Low Rank Adapter Technical Report

2024.

Links | BibTeX

3120.

Lu, Shun; Hu, Yu; Yang, Longxing; Mei, Jilin; Sun, Zihao; Tan, Jianchao; Song, Chengru

PHD-NAS: Preserving helpful data to promote Neural Architecture Search Journal Article

In: Neurocomputing, vol. 587, pp. 127646, 2024, ISSN: 0925-2312.

Abstract | Links | BibTeX

3119.

Qiao, Ye; Xu, Haocheng; Huang, Sitao

TG-NAS: Leveraging Zero-Cost Proxies with Transformer and Graph Convolution Networks for Efficient Neural Architecture Search Technical Report

2024.

Links | BibTeX

3118.

Feng, Yuqi; Lv, Zeqiong; Chen, Hongyang; Gao, Shangce; An, Fengping; Sun, Yanan

LRNAS: Differentiable Searching for Adversarially Robust Lightweight Neural Architecture Journal Article

In: IEEE Transactions on Neural Networks and Learning Systems, pp. 1-15, 2024.

Links | BibTeX

3117.

Zhou, Yexu; King, Tobias; Huang, Yiran; Zhao, Haibin; Riedel, Till; Röddiger, Tobias; Beigl, Michael

Enhancing Efficiency in HAR Models: NAS Meets Pruning Proceedings Article

In: 22nd IEEE International Conference on Pervasive Computing and Communications (PerCom 2024), Institute of Electrical and Electronics Engineers (IEEE), 2024.

BibTeX

3116.

Geada, Rob; Towers, David; Forshaw, Matthew; Atapour-Abarghouei, Amir; McGough, A. Stephen

Insights from the Use of Previously Unseen Neural Architecture Search Datasets Technical Report

2024.

Links | BibTeX

3115.

Kukushkin, Maksim; Bogdan, Martin; Schmid, Thomas

On optimizing morphological neural networks for hyperspectral image classification Proceedings Article

In: Osten, Wolfgang (Ed.): Sixteenth International Conference on Machine Vision (ICMV 2023), pp. 1307202, International Society for Optics and Photonics SPIE, 2024.

Links | BibTeX

3114.

Xiao, Fen; Xiang, Han; Cao, Chunhong; Gao, Xieping

Neural Architecture Search-Based Few-Shot Learning for Hyperspectral Image Classification Journal Article

In: IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-15, 2024.

Links | BibTeX

3113.

Zhang, Yusen; Qin, Yunchuan; Zhang, Yufeng; Zhou, Xu; Jian, Songlei; Tan, Yusong; Li, Kenli

OnceNAS: Discovering efficient on-device inference neural networks for edge devices Journal Article

In: Information Sciences, vol. 669, pp. 120567, 2024, ISSN: 0020-0255.

Abstract | Links | BibTeX

@article{ZHANG2024120567,

title = {OnceNAS: Discovering efficient on-device inference neural networks for edge devices},

author = {Yusen Zhang and Yunchuan Qin and Yufeng Zhang and Xu Zhou and Songlei Jian and Yusong Tan and Kenli Li},

url = {https://www.sciencedirect.com/science/article/pii/S0020025524004808},

doi = {https://doi.org/10.1016/j.ins.2024.120567},

issn = {0020-0255},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {Information Sciences},

volume = {669},

pages = {120567},

abstract = {Edge Intelligence (EI) offers an attractive approach for local AI processing at the network edge for privacy protection and reduced transmission, but deploying resource-intensive neural networks on edge devices remains a challenge. The neural architecture search (NAS) technique, known for its automation and minimal manual intervention, serves as a pivotal tool for EI. However, existing methods typically concentrate on optimizing resource consumption for specific hardware, leading to hardware-specific neural architectures with limited generalizability. In response, we propose OnceNAS, a novel method that designs and optimizes on-device inference neural networks for resource-constrained edge devices. OnceNAS simultaneously optimizes for parameter count and inference latency in addition to inference accuracy, producing lightweight neural networks while maintaining their inference performance. Meanwhile, we introduce an efficient evaluation strategy that can simultaneously assess multiple metrics. Experimental results demonstrate the effectiveness of OnceNAS, achieving high-performing architectures with substantial size reduction (10.49x) and speedup (5.45x). As a result, OnceNAS offers practical value by generating efficient on-device inference neural architectures for resource-constrained edge devices, facilitating real-world applications like autonomous driving and smart healthcare. Furthermore, we contribute DARTS-Bench, an open-source dataset providing candidate architectures with hardware-related information and a user-friendly API, facilitating future research in lightweight NAS.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}