@article{Kriakides2021Evolving,
title = {Evolving graph convolutional networks for neural architecture search},
author = {Kyriakides, George and Margaritis, Konstantinos},
url = {https://doi.org/10.1007/s00521-021-05979-8},
doi = {10.1007/s00521-021-05979-8},
year = {2021},
date = {2021-04-15},
journal = {Neural Computing and Applications},
abstract = {As neural architecture search (NAS) becomes an increasingly adopted method to design network architectures, various methods have been proposed to speedup the process. Besides proxy evaluation tasks, weight sharing, and scaling down the evaluated architectures, performance-predicting models exhibit multiple advantages. Eliminating the need to train candidate architectures and enabling transfer learning between datasets, researchers can also utilize them as a surrogate function for Bayesian optimization. On the other hand, graph convolutional networks (GCNs) have also been increasingly adopted for various tasks, enabling deep learning techniques on graphs without feature engineering. In this paper, we employ an evolutionary-based NAS method to evolve GCNs for the problem of predicting the relative performance of various architectures included in the NAS-Bench-101 dataset. By fine-tuning the architecture generated by our methodology, we manage to achieve a Kendall’s tau correlation coefficient of 0.907 between 1050 completely unseen architectures, utilizing only 450 samples, while also outperforming a strong baseline on the same task. Furthermore, we validate our method on custom global search space architectures, generated for the Fashion-MNIST dataset.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{PMID:33826511,
title = {Sample-Efficient Neural Architecture Search by Learning Actions for Monte Carlo Tree Search},
author = {Linnan Wang and Saining Xie and Teng Li and Rodrigo Fonseca and Yuandong Tian},
url = {https://doi.org/10.1109/TPAMI.2021.3071343},
doi = {10.1109/tpami.2021.3071343},
issn = {0162-8828},
year = {2021},
date = {2021-04-01},
journal = {IEEE transactions on pattern analysis and machine intelligence},
volume = {PP},
abstract = {Neural Architecture Search (NAS) has emerged as a promising technique for automatic neural network design. However, existing MCTS based NAS approaches often utilize manually designed action space, which is not directly related to the performance metric to be optimized (e.g., accuracy), leading to sample-inefficient explorations of architectures. To improve the sample efficiency, this paper proposes Latent Action Neural Architecture Search (LaNAS), which learns actions to recursively partition the search space into good or bad regions that contain networks with similar performance metrics. During the search phase, as different action sequences lead to regions with different performance, the search efficiency can be significantly improved by biasing towards the good regions. On three NAS tasks, empirical results demonstrate that LaNAS is at least an order more sample efficient than baseline methods including evolutionary algorithms, Bayesian optimizations, and random search. When applied in practice, both one-shot and regular LaNAS consistently outperform existing results. Particularly, LaNAS achieves 99.0% accuracy on CIFAR-10 and 80.8% top1 accuracy at 600 MFLOPS on ImageNet in only 800 samples, significantly outperforming AmoebaNet with 33x fewer samples. Our code is publicly available at https://github.com/facebookresearch/LaMCTS.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{ZhangJSPS2021,
title = {Multi-Level Cell Progressive Differentiable Architecture Search to Improve Image Classification Accuracy},
author = {Zhang, Zhentong and Yugang Shan and Jie Yuan},
url = {https://doi.org/10.1007/s11265-021-01647-1},
year = {2021},
date = {2021-03-08},
journal = {Journal of Signal Processing Systems},
abstract = {In recent years, the neural architecture search has continuously made significant progress in the field of image recognition. Among them, the differentiable method has obvious advantages compared with other search methods in terms of computational cost and accuracy to deal with image classification. However, the differentiable method is usually composed of single cell, which cannot efficiently extract the features of the network. In response to this problem, we propose a multi-level cell progressive differentiable method which allows cells to have different types according to the levels of the network. In differentiable method, the gap between the search network and the evaluation one is large, and the correlation is low. We design an algorithm to improve the distribution of architecture parameters. We also optimize the loss function and use the regularization method of additional action to improve deep network performance. The method achieves good search and classification results on CIFAR10 and ImageNet (mobile setting).},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{PMID:33750687,
title = {Auto-Pytorch: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL},
author = {Lucas Zimmer and Marius Lindauer and Frank Hutter},
url = {https://doi.org/10.1109/TPAMI.2021.3067763},
doi = {10.1109/tpami.2021.3067763},
issn = {0162-8828},
year = {2021},
date = {2021-03-01},
journal = {IEEE transactions on pattern analysis and machine intelligence},
volume = {PP},
abstract = {While early AutoML frameworks focused on optimizing traditional ML pipelines and their hyperparameters, a recent trend in AutoML is to focus on neural architecture search. In this paper, we introduce Auto-PyTorch, which brings the best of these two worlds together by jointly and robustly optimizing the architecture of networks and the training hyperparameters to enable fully automated deep learning (AutoDL). Auto-PyTorch achieves state-of-the-art performance on several tabular benchmarks by combining multi-fidelity optimization with portfolio construction for warmstarting and ensembling of deep neural networks (DNNs) and common baselines for tabular data. To thoroughly study our assumptions on how to design such an AutoDL system, we additionally introduce a new benchmark on learning curves for DNNs, dubbed LCBench, and run extensive ablation studies of the full Auto-PyTorch on typical AutoML benchmarks, eventually showing that Auto-PyTorch performs better than several state-of-the-art competitors on average.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{9377468,
title = {MIGO-NAS: Towards Fast and Generalizable Neural Architecture Search},
author = {X Zheng and R Ji and Y Chen and Q Wang and B Zhang and Q Ye and J Chen and F Huang and Y Tian},
url = {https://www.computer.org/csdl/journal/tp/5555/01/09377468/1rUNdbz4LQY},
doi = {10.1109/TPAMI.2021.3065138},
issn = {1939-3539},
year = {2021},
date = {2021-03-01},
journal = {IEEE Transactions on Pattern Analysis & Machine Intelligence},
number = {01},
pages = {1-1},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{9354953,
title = {Partially-Connected Neural Architecture Search for Reduced Computational Redundancy},
author = {Y Xu and L Xie and W Dai and X Zhang and X Chen and G Qi and H Xiong and Q Tian},
url = {https://www.computer.org/csdl/journal/tp/5555/01/09354953/1rgCccYlOaQ},
doi = {10.1109/TPAMI.2021.3059510},
issn = {1939-3539},
year = {2021},
date = {2021-02-01},
journal = {IEEE Transactions on Pattern Analysis & Machine Intelligence},
number = {01},
pages = {1-1},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {Differentiable architecture search (DARTS) enables effective neural architecture search (NAS) using gradient descent, but suffers from high memory and computational costs. In this paper, we propose a novel approach, namely Partially-Connected DARTS (PC-DARTS), to achieve efficient and stable neural architecture search by reducing the channel and spatial redundancies of the super-network. In the channel level, partial channel connection is presented to randomly sample a small subset of channels for operation selection to accelerate the search process and suppress the over-fitting of the super-network. Side operation is introduced for bypassing (non-sampled) channels to guarantee the performance of searched architectures under extremely low sampling rates. In the spatial level, input features are down-sampled to eliminate spatial redundancy and enhance the efficiency of the mixed computation for operation selection. Furthermore, edge normalization is developed to maintain the consistency of edge selection based on channel sampling with the architectural parameters for edges. Experimental results demonstrate that the proposed approach achieves higher search speed and training stability than DARTS. PC-DARTS obtains a top-1 error rate of 2.55% on CIFAR-10 with 0.07 GPU-days for architecture search, and a state-of-the-art top-1 error rate of 24.1% on ImageNet (under the mobile setting) within 2.8 GPU-day.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{rs13071404,
title = {Graph Convolutional Networks by Architecture Search for PolSAR Image Classification},
author = {Hongying Liu and Derong Xu and Tianwen Zhu and Fanhua Shang and Yuanyuan Liu and Jianhua Lu and Ri Yang},
url = {https://www.mdpi.com/2072-4292/13/7/1404},
doi = {10.3390/rs13071404},
issn = {2072-4292},
year = {2021},
date = {2021-01-01},
journal = {Remote Sensing},
volume = {13},
number = {7},
abstract = {Classification of polarimetric synthetic aperture radar (PolSAR) images has achieved good results due to the excellent fitting ability of neural networks with a large number of training samples. However, the performance of most convolutional neural networks (CNNs) degrades dramatically when only a few labeled training samples are available. As one well-known class of semi-supervised learning methods, graph convolutional networks (GCNs) have gained much attention recently to address the classification problem with only a few labeled samples. As the number of layers grows in the network, the parameters dramatically increase. It is challenging to determine an optimal architecture manually. In this paper, we propose a neural architecture search method based GCN (ASGCN) for the classification of PolSAR images. We construct a novel graph whose nodes combines both the physical features and spatial relations between pixels or samples to represent the image. Then we build a new searching space whose components are empirically selected from some graph neural networks for architecture search and develop the differentiable architecture search method to construction our ASGCN. Moreover, to address the training of large-scale images, we present a new weighted mini-batch algorithm to reduce the computing memory consumption and ensure the balance of sample distribution, and also analyze and compare with other similar training strategies. Experiments on several real-world PolSAR datasets show that our method has improved the overall accuracy as much as 3.76% than state-of-the-art methods.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{DONG2021,
title = {Subject Sensitive EEG Discrimination with Fast Reconstructable CNN Driven by Reinforcement Learning: A Case Study of ASD Evaluation},
author = {Heyou Dong and Dan Chen and Lei Zhang and Hengjin Ke and Xiaoli Li},
url = {https://www.sciencedirect.com/science/article/pii/S0925231221005270},
doi = {https://doi.org/10.1016/j.neucom.2021.04.009},
issn = {0925-2312},
year = {2021},
date = {2021-01-01},
journal = {Neurocomputing},
abstract = {Recent Electroencephalogram (EEG) analysis in connection with brain disorders has been tremendously benefiting from the (Deep) Neural Network technology in neuroscience research and neuro-engineering practices. However, the performance of existing hand-crafted models, such as the stability, has largely been refrained. This is the case especially in the paradigms that sensitive to the individuality of subjects and the non-stationarity of cognitive dynamics, such as Autism Spectrum Disorder (ASD) evaluation. Aiming at this problem, this study develops a Q-Learning method to enable fast reconstruction of Convolutional Neural Network (CNN) thus to support EEG discrimination adapting to the individuality of subjects under examination. The proposed method first generates a CNN model with the structure and hyper-parameters determined (i.e., Neural Architecture Search) by the customized Q-Learning algorithm, where the CNN model is treated as a discrete system to be optimized. With the sharp shift of subjects, the Q-Learning algorithm reconstructs the CNN model to reach optimization reusing the tacit knowledge learned from the previous trials. A case study has been performed to check the proposed method versus state-of-the-art counterparts based on resting-state EEG collected from 175 ASD-suspicious children with a diverse geological distribution. The observations in the case study indicate that: 1) the method outperforms the counterparts with an individual/sample accuracy of 92.63%/83.23% achieved; 2) the method can quickly reconstruct the CNN model with the group of subjects shifting from one region to another to maintain an encouraging performance while the counterparts without reconstruction may drop by about 12%.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{9380321,
title = {An Efficient Hardware Design for Accelerating Sparse CNNs with NAS-based Models},
author = {Y Liang and L Lu and Y Jin and J Xie and R Huang and J Zhang and W Lin},
url = {https://ieeexplore.ieee.org/abstract/document/9380321},
doi = {10.1109/TCAD.2021.3066563},
year = {2021},
date = {2021-01-01},
journal = {IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{9377449,
title = {BioNetExplorer: Architecture-Space Exploration of Bio-Signal Processing Deep Neural Networks for Wearables},
author = {B S Prabakaran and A Akhtar and S Rehman and O Hasan and M Shafique},
url = {https://ieeexplore.ieee.org/abstract/document/9377449},
doi = {10.1109/JIOT.2021.3065815},
year = {2021},
date = {2021-01-01},
journal = {IEEE Internet of Things Journal},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{DBLP:journals/corr/abs-2103-16889,
title = {Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition},
author = {Guangrun Wang and Liang Lin and Rongcong Chen and Guangcong Wang and Jiqi Zhang},
url = {https://arxiv.org/abs/2103.16889},
year = {2021},
date = {2021-01-01},
journal = {IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{9383257,
title = {Evolutionary Algorithm-Based and Network Architecture Search-Enabled Multiobjective Traffic Classification},
author = {X Wang and X Wang and L Jin and R Lv and B Dai and M He and T Lv},
url = {https://ieeexplore.ieee.org/abstract/document/9383257},
doi = {10.1109/ACCESS.2021.3068267},
year = {2021},
date = {2021-01-01},
journal = {IEEE Access},
volume = {9},
pages = {52310-52325},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{9392299,
title = {BNAS: Efficient Neural Architecture Search Using Broad Scalable Architecture},
author = {Z Ding and Y Chen and N Li and D Zhao and Z Sun and C L P Chen},
url = {https://ieeexplore.ieee.org/abstract/document/9392299},
doi = {10.1109/TNNLS.2021.3067028},
year = {2021},
date = {2021-01-01},
journal = {IEEE Transactions on Neural Networks and Learning Systems},
pages = {1-15},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{9387697,
title = {A Linear NAS Service of ConvNets for Fast Deployment in the Edge of 5G Networks},
author = {J Wang and J Zhao and J An and D Wang and M Qiu},
url = {https://ieeexplore.ieee.org/abstract/document/9387697},
doi = {10.1109/MNET.011.1900336},
year = {2021},
date = {2021-01-01},
journal = {IEEE Network},
volume = {35},
number = {2},
pages = {46-52},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{lankford2021IJMO,
title = {Open-Source Neural Architecture Search with Ensemble and Pre-trained Networks},
author = {Séamus Lankford},
url = {http://www.ijmo.org/vol11/774-Q304.pdf},
year = {2021},
date = {2021-01-01},
journal = {International Journal of Modeling and Optimization},
volume = {11},
number = {2},
pages = {33-41},
keywords = {},
pubstate = {published},
tppubtype = {article}
}