AutoML | Literature on Neural Architecture Search

1717.

Vo, An; Pham, Tan Ngoc; Nguyen, Van Bich; Luong, Ngoc Hoang

Training-Free Multi-Objective and Many-Objective Evolutionary Neural Architecture Search with Synaptic Flow Proceedings Article

In: The 11th International Symposium on Information and Communication Technology, pp. 1–8, Association for Computing Machinery, Hanoi, Vietnam, 2022, ISBN: 9781450397254.

Abstract | Links | BibTeX

@inproceedings{10.1145/3568562.3568569,

title = {Training-Free Multi-Objective and Many-Objective Evolutionary Neural Architecture Search with Synaptic Flow},

author = {An Vo and Tan Ngoc Pham and Van Bich Nguyen and Ngoc Hoang Luong},

url = {https://doi.org/10.1145/3568562.3568569},

doi = {10.1145/3568562.3568569},

isbn = {9781450397254},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {The 11th International Symposium on Information and Communication Technology},

pages = {1–8},

publisher = {Association for Computing Machinery},

address = {Hanoi, Vietnam},

series = {SoICT 2022},

abstract = {Neural architecture search (NAS) algorithms often suffer from the expensive computation cost because a sufficient number of candidate architectures need to be evaluated during the search. Each architecture evaluation involves hundreds of training epochs to obtain proper weights for computing the accuracy of that architecture. Recently, a training-free performance metric Synaptic Flow has been proposed to facilitate these architecture evaluations. Synaptic Flow can be computed using randomly initialized network weights and its values are found to have certain correlation degree with network test accuracy. Furthermore, in real-world neural architecture designing, network performance (e.g., test accuracy) is not the sole objective, and network complexity metrics (e.g., the number of parameters, latency) are also considered. In this paper, we investigate several multi-objective NAS problem formulations, where each involves one performance metric and one complexity metric, and a many-objective NAS problem formulation, that involves one performance metric and four complexity metrics. We consider two variants of the performance metric for each formulation: a training-based variant that employs network accuracy and a training-free variant that employs Synaptic Flow. We use the non-dominated sorting genetic algorithm II to solve these NAS problem formulations, and then compare the quality of the obtained architectures and the efficiency of solving each formulation. Experimental results on standard benchmark NATS-Bench exhibit the advantages of the training-free many-objective evolutionary NAS (TF-MaOENAS) approach in obtaining competitive architectures with reasonable computing cost. The code is available at: https://github.com/ELO-Lab/TF-MaOENAS.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

Close

1716.

Wu, Xinle; Zhang, Dalin; Zhang, Miao; Guo, Chenjuan; Yang, Bin; Jensen, Christian S.

Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting Technical Report

2022.

Links | BibTeX

1715.

Mills, Keith G.; Han, Fred X.; Zhang, Jialin; Chudak, Fabian; Mamaghani, Ali Safari; Salameh, Mohammad; Lu, Wei; Jui, Shangling; Niu, Di

GENNAPE: Towards Generalized Neural Architecture Performance Estimators Technical Report

2022.

Links | BibTeX

1714.

Zhang, Tunhou; Ma, Mingyuan; Yan, Feng; Li, Hai; Chen, Yiran

PIDS: Joint Point Interaction-Dimension Search for 3D Point Cloud Technical Report

2022.

Links | BibTeX

1713.

Li, Yufei; Bao, Liang; Huang, Kaipeng; Wu, Chase; Li, Xinwei

RSFIN: A Rule Search-based Fuzzy Inference Network for Performance Prediction of Configurable Software Systems Technical Report

2022.

Abstract | Links | BibTeX

1712.

Liu, Zhipu; Zhang, Lei; Zhang, David

Neural Image Parts Group Search for Person Re-identification Journal Article

In: IEEE Transactions on Circuits and Systems for Video Technology, pp. 1-1, 2022.

Links | BibTeX

1711.

Huang, Junhao; Xue, Bing; Sun, Yanan; Zhang, Mengjie

EDE-NAS: An Eclectic Differential Evolution Approach to Single-Path Neural Architecture Search Proceedings Article

In: Äziz, Haris; Corr^ea, Débora; French, Tim" (Ed.): ÄI 2022: Advances in Artificial Intelligence", pp. 116–130, Springer International Publishing, Cham, 2022, ISBN: 978-3-031-22695-3.

Abstract | Links | BibTeX

1710.

Zhang, Xin; Saniie, Jafar

Reinforcement Learning Based Neural Architecture Search for Flaw Detection in Intelligent Ultrasonic Imaging NDE System Proceedings Article

In: 2022 IEEE International Ultrasonics Symposium (IUS), pp. 1-4, 2022.

Links | BibTeX

1709.

Yu, Jialiang; Gao, Song; Tian, Jie; Bian, Hongli; Liu, Hui; Li, Junqing

Evolutionary Neural Architecture Search Based on Variational Inference Bayesian Convolutional Neural Network Proceedings Article

In: 2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS), pp. 1-6, 2022.

Links | BibTeX

1708.

Li, Jiaquan; Hong, Haokai; Shi, Minghui; Lin, Qiuzhen; Zhou, Fenfen; Tan, Kay Chen; Jiang, Min

Knowledge transfer for Object Detection with Evolution architecture search Proceedings Article

In: 2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS), pp. 1-6, 2022.

Links | BibTeX

1707.

Yuan, Jinliang; Xu, Mengwei; Zhao, Yuxin; Bian, Kaigui; Huang, Gang; Liu, Xuanzhe; Wang, Shangguang

Resource-Aware Federated Neural Architecture Search over Heterogeneous Mobile Devices Journal Article

In: IEEE Transactions on Big Data, pp. 1-11, 2022.

Links | BibTeX

1706.

Zhu, Yichen; Fu, Xiaowei

BNNAS++: Towards Unbiased Neural Architecture Search With Batch Normalization Journal Article

In: IEEE Access, vol. 10, pp. 128424-128432, 2022.

Links | BibTeX

1705.

Bouzidi, Halima; Odema, Mohanad; Ouarnoughi, Hamza; Faruque, Mohammad Abdullah Al; Niar, Smail

HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance Scaling Technical Report

2022.

Links | BibTeX

1704.

Guan, Ziyi; Zhou, Wenyong; Ren, Yuan; Xie, Rui; Yu, Hao; Wong, Ngai

A Hardware-Aware Neural Architecture Search Pareto Front Exploration for In-Memory Computing Proceedings Article

In: 2022 IEEE 16th International Conference on Solid-State & Integrated Circuit Technology (ICSICT), pp. 1-4, 2022.

Links | BibTeX

1703.

Peng, Yameng; Song, Andy; Ciesielski, Vic; Fayek, Haytham M.; Chang, Xiaojun

PRE-NAS: Evolutionary Neural Architecture Search with Predictor Journal Article

In: IEEE Transactions on Evolutionary Computation, pp. 1-1, 2022.

Links | BibTeX

1702.

Liu, Shiqing; Zhang, Haoyu; Jin, Yaochu

A survey on computationally efficient neural architecture search Journal Article

In: Journal of Automation and Intelligence, vol. 1, no. 1, pp. 100002, 2022, ISSN: 2949-8554.

Abstract | Links | BibTeX

1701.

Falanti, Andrea; Lomurno, Eugenio; Ardagna, Danilo; Matteucci, Matteo

POPNASv3: a Pareto-Optimal Neural Architecture Search Solution for Image and Time Series Classification Technical Report

2022.

Links | BibTeX

1700.

Lee, Bokyeung; Ko, Kyungdeuk; Hong, Jonghwan; Ko, Hanseok

Single Cell Training on Architecture Search for Image Denoising Technical Report

2022.

Links | BibTeX

1699.

Patel, Ria; Rorabaugh, Ariel Keller; Olaya, Paula; Caino-Lores, Silvina; Channing, Georgia; Schuman, Catherine; Miyashita, Osamu; Tama, Florence; Taufer, Michela

A Methodology to Generate Efficient Neural Networks for Classification of Scientific Datasets Proceedings Article

In: 2022 IEEE 18th International Conference on e-Science (e-Science), pp. 389-390, 2022.

Links | BibTeX

1698.

Dai, Haixing; Li, Qing; Zhao, Lin; Pan, Liming; Shi, Cheng; Liu, Zhengliang; Wu, Zihao; Zhang, Lu; Zhao, Shijie; Wu, Xia; Liu, Tianming; Zhu, Dajiang

Graph Representation Neural Architecture Search for Optimal Spatial/Temporal Functional Brain Network Decomposition Proceedings Article

In: Lian, Chunfeng; Cao, Xiaohuan; Rekik, Islem; Xu, Xuanang; Cui, Zhiming (Ed.): Machine Learning in Medical Imaging, pp. 279–287, Springer Nature Switzerland, Cham, 2022, ISBN: 978-3-031-21014-3.

Abstract | Links | BibTeX

@inproceedings{10.1007/978-3-031-21014-3_29,

title = {Graph Representation Neural Architecture Search for Optimal Spatial/Temporal Functional Brain Network Decomposition},

author = {Haixing Dai and Qing Li and Lin Zhao and Liming Pan and Cheng Shi and Zhengliang Liu and Zihao Wu and Lu Zhang and Shijie Zhao and Xia Wu and Tianming Liu and Dajiang Zhu},

editor = {Chunfeng Lian and Xiaohuan Cao and Islem Rekik and Xuanang Xu and Zhiming Cui},

url = {https://link.springer.com/chapter/10.1007/978-3-031-21014-3_29},

isbn = {978-3-031-21014-3},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {Machine Learning in Medical Imaging},

pages = {279--287},

publisher = {Springer Nature Switzerland},

address = {Cham},

abstract = {Decomposing the spatial/temporal functional brain networks from 4D functional magnetic resonance imaging (fMRI) data has attracted extensive attention. Among all these efforts, deep neural network-based methods have shown significant advantages due to their powerful hierarchical representation ability. However, the network architectures of those deep learning models are manually crafted, which is time consuming and non-optimal. This paper presents a novel graph representation neural architecture search (GR-NAS) method based on graph representation to optimize the vanilla RNN cell structure for decomposing spatial/temporal brain networks. The core idea is to embed the discrete search space of the RNN cell into a continuous domain that preserves the topological information. After that, popular search algorithms, e.g., reinforcement learning (RL) and Bayesian optimization (BO), can be employed to find the optimal architecture in this continuous space. The proposed method was evaluated on the Human Connectome Project (HCP) task fMRI datasets. Extensive experiments demonstrated the superiority of the proposed model in brain network decomposition both spatially and temporally. To our best knowledge, the proposed model is among the early efforts using NAS strategy to optimally decompose spatial/temporal functional brain networks from fMRI data.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

Close

1697.

Garavagno, Andrea Mattia; Leonardis, Daniele; Frisoli, Antonio

Colab NAS: Obtaining lightweight task-specific convolutional neural networks following Occam's razor Technical Report

2022.

Links | BibTeX

1696.

Shavit, Hadar; Jatelnicki, Filip; Mor-Puigventós, Pol; Kowalczyk, Wojtek

From Xception to NEXcepTion: New Design Decisions and Neural Architecture Search Technical Report

2022.

Links | BibTeX

1695.

Huang, Han; Shen, Li; He, Chaoyang; Dong, Weisheng; Liu, Wei

Differentiable Neural Architecture Search for Extremely Lightweight Image Super-Resolution Journal Article

In: IEEE Transactions on Circuits and Systems for Video Technology, pp. 1-1, 2022.

Links | BibTeX

1694.

Park, Seongmin; Kwon, Beomseok; Lim, Jieun; Sim, Kyuyoung; Kim, Taeho; Choi, Jungwook

Automatic Network Adaptation for Ultra-Low Uniform-Precision Quantization Miscellaneous

2022.

Links | BibTeX

1693.

Nikulenkov, Mikhail; Khamitov, Kamil; Popova, Nina

Regularization Approach for Accelerating Neural Architecture Search Proceedings Article

In: Voevodin, Vladimir; Sobolev, Sergey; Yakobovskiy, Mikhail; Shagaliev, Rashit (Ed.): Supercomputing, pp. 475–485, Springer International Publishing, Cham, 2022, ISBN: 978-3-031-22941-1.

Abstract | Links | BibTeX

@inproceedings{10.1007/978-3-031-22941-1_35,

title = {Regularization Approach for Accelerating Neural Architecture Search},

author = {Mikhail Nikulenkov and Kamil Khamitov and Nina Popova},

editor = {Vladimir Voevodin and Sergey Sobolev and Mikhail Yakobovskiy and Rashit Shagaliev},

url = {https://link.springer.com/chapter/10.1007/978-3-031-22941-1_35},

isbn = {978-3-031-22941-1},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {Supercomputing},

pages = {475--485},

publisher = {Springer International Publishing},

address = {Cham},

abstract = {Modern Artificial Neural networks utilizes vast topologies to become applicable to the vast majority of the ML problems. Such topologies have an enormous number of parameters nowadays, which make it easier to use, but harder to train and modify. With such a number of parameters, the usage of semi-automatic techniques for constructing or adjusting new models for topical problems is vital for the whole industry. It makes it essential to optimize such methods like Neural Architecture Search (NAS) to efficiently utilize computational resources of the GPU and whole cluster. Since modern NAS tools are commonly used to optimize models in different areas or make a combination of models from the past, they have to use a plenty of computational power to perform certain hyperparameters optimization routines. Many NAS methods are of a highly parallel nature, but still they need a lot of computational power and have an enormous convergence time. The key to increasing performance of many NAS methods is boosting performance of the training of the highly-depth and synthesized model, to evaluate the probe of the model and obtain the score for this epoch. It means that demands for parallel implementations need to be available in different cluster configurations and should utilize as many nodes as possible, showing high scalability. However, straightforward approaches where NAS solving does not consider previous results lead to wasteful utilization of computation power. In this article, we introduce a new method that can improve convergence in NEAT-based NAS method using L1/L2 regularization during the evolution step.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

Close

1692.

Liu, Yuqiao; Li, Haipeng; Sun, Yanan; Liu, Shuaicheng

DAS: Neural Architecture Search via Distinguishing Activation Score Miscellaneous

2022.

Links | BibTeX

1691.

Damarla, Anupama; Doraikannan, Sumathi

Optimized one-shot neural architecture search for skin cancer classification Journal Article

In: Journal of Electronic Imaging, vol. 31, no. 6, pp. 063053, 2022.

Links | BibTeX

1690.

Wang, Zhaolei; Lu, Kunfeng; Yu, Chunmei; Yao, Na; Wang, Ludi; Zhao, Jikang

Rocket Self-learning Control based on Lightweight Neural Network Architecture Search Proceedings Article

In: 2022 IEEE International Conference on Unmanned Systems (ICUS), pp. 1621-1626, 2022.

Links | BibTeX

1689.

Ou, Yuwei; Xie, Xiangning; Gao, Shangce; Sun, Yanan; Tan, Kay Chen; Lv, Jiancheng

Differentiable Search of Accurate and Robust Architectures Miscellaneous

2022.

Links | BibTeX

1688.

Yao, Siya; Zhao, Yu; Deng, Qi; Ma, Jun; Kang, Qi

Multi-objective Neural Architecture Adaptation in Transfer Learning Proceedings Article

In: 2022 IEEE International Conference on Networking, Sensing and Control (ICNSC), pp. 1-5, 2022.

Links | BibTeX

1687.

Yao, Siya; Zhao, Yu; Deng, Qi; Ma, Jun; Kang, Qi

Multi-objective Neural Architecture Adaptation in Transfer Learning Proceedings Article

In: 2022 IEEE International Conference on Networking, Sensing and Control (ICNSC), pp. 1-5, 2022.

Links | BibTeX

1686.

Yao, Siya; Zhao, Yu; Deng, Qi; Ma, Jun; Kang, Qi

Multi-objective Neural Architecture Adaptation in Transfer Learning Proceedings Article

In: 2022 IEEE International Conference on Networking, Sensing and Control (ICNSC), pp. 1-5, 2022.

Links | BibTeX

1685.

Li, Yutong

Forest fire smoke recognition and detection based on EfficientNet Proceedings Article

In: 2022 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS), pp. 712-719, 2022.

Links | BibTeX

1684.

Lyu, Xinqi; Chen, Yibo; Chen, Jiamin; Liu, Xiangyue; Gao, Jianliang

Spatio-Temporal Based Architecture Topology Search for Multivariate Time Series Prediction Proceedings Article

In: 2022 IEEE International Conference on Big Data (Big Data), pp. 1304-1309, 2022.

Links | BibTeX

1683.

Wei, Zimian; Pan, Hengyue; Li, Lujun; Lu, Menglong; Niu, Xin; Dong, Peijie; Li, Dongsheng

Multi-trial Neural Architecture Search with Lottery Tickets Technical Report

2022.

Links | BibTeX

1682.

Xu, Binke; Bi, Ying; Xue, Bing; Schindler, Jan; Martin, Brent; Zhang, Mengjie

Automatically Designing U-Nets Using A Genetic Algorithm for Tree Image Segmentation Proceedings Article

In: 2022 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 626-633, 2022.

Links | BibTeX

1681.

Zheng, Xin; Zhang, Miao; Chen, Chunyang; Li, Chaojie; Zhou, Chuan; Pan, Shirui

Multi-Relational Graph Neural Architecture Search with Fine-grained Message Passing Proceedings Article

In: 2022 IEEE International Conference on Data Mining (ICDM), pp. 783-792, 2022.

Links | BibTeX

1680.

Noce, Julia; Chantong, Gianella; Jauregui, Gustavo; Mogami, Roberto; Monteiro, Alexandra; Figueiredo, Karla; Vellasco, Marley

Äpplied Enhanced Q-NAS for COVID-19 Detection in CT Images Proceedings Article

In: Mahmud, Mufti; Ieracitano, Cosimo; Kaiser, M. Shamim; Mammone, Nadia; Morabito, Francesco Carlo (Ed.): Äpplied Intelligence and Informatics", pp. 419–433, Springer Nature Switzerland, Cham, 2022, ISBN: 978-3-031-24801-6.

Abstract | BibTeX