Maintained by Difan Deng and Marius Lindauer.
The following list considers papers related to neural architecture search. It is by no means complete. If you miss a paper on the list, please let us know.
Please note that although NAS methods steadily improve, the quality of empirical evaluations in this field are still lagging behind compared to other areas in machine learning, AI and optimization. We would therefore like to share some best practices for empirical evaluations of NAS methods, which we believe will facilitate sustained and measurable progress in the field. If you are interested in a teaser, please read our blog post or directly jump to our checklist.
Transformers have gained increasing popularity in different domains. For a comprehensive list of papers focusing on Neural Architecture Search for Transformer-Based spaces, the awesome-transformer-search repo is all you need.
2021
Huang, Shenyang; Francois-Lavet, Vincent; Rabusseau, Guillaume
Understanding Capacity Saturation in Incremental Learning Proceedings Article
In: The 34th Canadian Conference on Artificial Intelligence, 2021.
@inproceedings{Huang2021,
title = {Understanding Capacity Saturation in Incremental Learning},
author = {Shenyang Huang and Vincent Francois-Lavet and Guillaume Rabusseau},
url = {https://assets.pubpub.org/xabw479b/51621564316955.pdf},
year = {2021},
date = {2021-05-25},
booktitle = {The 34th Canadian Conference on Artificial Intelligence},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Chen, Wuyang; Gong, Xinyu; Wang, Zhangyang
Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective Proceedings Article
In: ICLR 2021, 2021.
@inproceedings{chen2021neural,
title = {Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective},
author = {Wuyang Chen and Xinyu Gong and Zhangyang Wang},
url = {https://arxiv.org/abs/2102.11535},
year = {2021},
date = {2021-05-04},
booktitle = {ICLR 2021},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Yang, Yuxuan; Gao, Zhongke; Li, Yanli; Wang, He
A CNN identified by reinforcement learning-based optimization framework for EEG-based state evaluation Journal Article
In: Journal of Neural Engineering, vol. 18, no. 4, pp. 046059, 2021.
@article{Yang_2021,
title = {A CNN identified by reinforcement learning-based optimization framework for EEG-based state evaluation},
author = {Yuxuan Yang and Zhongke Gao and Yanli Li and He Wang},
url = {https://doi.org/10.1088/1741-2552/abfa71},
doi = {10.1088/1741-2552/abfa71},
year = {2021},
date = {2021-05-01},
journal = {Journal of Neural Engineering},
volume = {18},
number = {4},
pages = {046059},
publisher = {IOP Publishing},
abstract = {Objective. Electroencephalogram (EEG) data, as a kind of complex time-series, is one of the most widely-used information measurements for evaluating human psychophysiological states. Recently, numerous works applied deep learning techniques, especially the convolutional neural network (CNN), into EEG-based research. The design of the hyper-parameters of the CNN model has a great influence on the performance of the model. Therefore, automatically designing these hyper-parameters can save the time and labor of experts. This leads to the appearance of the neural architecture search technique. In this paper, we propose a reinforcement learning (RL)-based step-by-step framework to efficiently search for CNN models. Approach. Specifically, the deep Q network in RL is first used to determine the depth of convolutional layers and the connection modes among layers. Then particle swarm optimization algorithm is used to fine-tune the number and size of convolution kernels. Through this step-by-step strategy, the search space can be narrowed in each step for saving the overall time cost. This framework is employed for both EEG-based sleep stage classification and driver drowsiness evaluation tasks. Main results. The results show that compared with state-of-the-art methods, the high-performance CNN models identified by the proposed optimization framework, can achieve high overall accuracy and better root mean squared error in the two tasks. Significance. Therefore, the proposed optimization framework has a great potential to provide high-performance results for other kinds of classification and prediction tasks. In this way, it can greatly save researchers’ time cost and promote broader applications of CNNs.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Schoenherr, Georg P.
The Nonlinearity Coefficient - A Practical Guide to Neural Architecture Design PhD Thesis
2021.
@phdthesis{Schoenherr2021,
title = {The Nonlinearity Coefficient - A Practical Guide to Neural Architecture Design},
author = {Georg P. Schoenherr},
url = {http://reports-archive.adm.cs.cmu.edu/anon/anon/home/ftp/usr/ftp/2021/abstracts/21-110.html},
year = {2021},
date = {2021-05-01},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
Zhang, Yi; Liu, Yang; Liu, X. Shirley
Neural network architecture search with AMBER Journal Article
In: Nature Machine Intelligence, pp. 372-373, 2021.
@article{Zhang2021,
title = {Neural network architecture search with AMBER},
author = {Zhang, Yi and Liu, Yang and Liu, X. Shirley},
url = {https://doi.org/10.1038/s42256-021-00350-x},
year = {2021},
date = {2021-05-01},
journal = {Nature Machine Intelligence},
pages = {372-373},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Yuan, Zhihang; Liu, Jingze; Li, Xingchen; Yan, Longhao; Chen, Haoxiang; Wu, Bingzhe; Yang, Yuchao; Sun, Guangyu
NAS4RRAM: neural network architecture search for inference on RRAM-based accelerators Journal Article
In: Science China Information Sciences, 2021.
@article{yuan2021,
title = {NAS4RRAM: neural network architecture search for inference on RRAM-based accelerators},
author = {Yuan, Zhihang and Liu, Jingze and Li, Xingchen and Yan, Longhao and Chen, Haoxiang and Wu, Bingzhe and Yang, Yuchao and Sun, Guangyu},
url = {https://doi.org/10.1007/s11432-020-3245-7},
doi = {10.1007/s11432-020-3245-7},
year = {2021},
date = {2021-05-01},
journal = {Science China Information Sciences},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Perenda, Erma; Rajendran, Sreeraj; Bovet, Gerome; Pollin, Sofie; Zheleva, Mariya
Evolutionary Optimization of Residual Neural Network Architectures for Modulation Classification Miscellaneous
2021.
@misc{perenda_rajendran_bovet_pollin_zheleva_2021,
title = {Evolutionary Optimization of Residual Neural Network Architectures for Modulation Classification},
author = {Erma Perenda and Sreeraj Rajendran and Gerome Bovet and Sofie Pollin and Mariya Zheleva},
url = {https://www.techrxiv.org/articles/preprint/Evolutionary_Optimization_of_Residual_Neural_Network_Architectures_for_Modulation_Classification/14528778/1},
doi = {10.36227/techrxiv.14528778.v1},
year = {2021},
date = {2021-05-01},
publisher = {TechRxiv},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Wang, Xiaobo
Teacher Guided Neural Architecture Search for Face Recognition Journal Article
In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 4, pp. 2817-2825, 2021.
@article{Wang_2021,
title = {Teacher Guided Neural Architecture Search for Face Recognition},
author = {Xiaobo Wang},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/16387},
year = {2021},
date = {2021-05-01},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
volume = {35},
number = {4},
pages = {2817-2825},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Anwar, Abrar
Evolving Spiking Circuit Motifs Using Weight Agnostic Neural Networks Journal Article
In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 18, pp. 15956-15957, 2021.
@article{Anwar_2021,
title = {Evolving Spiking Circuit Motifs Using Weight Agnostic Neural Networks},
author = {Abrar Anwar},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/17974},
year = {2021},
date = {2021-05-01},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
volume = {35},
number = {18},
pages = {15956-15957},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Pan, Zheyi; Ke, Songyu; Yang, Xiaodu; Liang, Yuxuan; Yu, Yong; Zhang, Junbo; Zheng, Yu
AutoSTG: Neural Architecture Search forPredictions of Spatio-Temporal Graphs Proceedings Article
In: WWW 2021, 2021.
@inproceedings{PanWWW2021,
title = {AutoSTG: Neural Architecture Search forPredictions of Spatio-Temporal Graphs},
author = {Zheyi Pan and Songyu Ke and Xiaodu Yang and Yuxuan Liang and Yong Yu and Junbo Zhang and Yu Zheng},
url = {http://panzheyi.cc/publication/pan2021autostg/paper.pdf},
year = {2021},
date = {2021-04-19},
booktitle = {WWW 2021},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Kyriakides, George; Margaritis, Konstantinos
Evolving graph convolutional networks for neural architecture search Journal Article
In: Neural Computing and Applications, 2021.
@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}
}
Harikrishnan, V. K.; Gambhir, MeenuAshima
Neural AutoML with Convolutional Networks for Diabetic Retinopathy Diagnosis Journal Article
In: Machine Intelligence and Smart Systems, pp. 145-157, 2021.
@article{Harikrishnan2021,
title = {Neural AutoML with Convolutional Networks for Diabetic Retinopathy Diagnosis},
author = { V. K. Harikrishnan and MeenuAshima Gambhir},
url = {https://link.springer.com/chapter/10.1007/978-981-33-4893-6_14},
year = {2021},
date = {2021-04-09},
journal = {Machine Intelligence and Smart Systems},
pages = {145-157},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Wang, Linnan; Xie, Saining; Li, Teng; Fonseca, Rodrigo; Tian, Yuandong
Sample-Efficient Neural Architecture Search by Learning Actions for Monte Carlo Tree Search Journal Article
In: IEEE transactions on pattern analysis and machine intelligence, vol. PP, 2021, ISSN: 0162-8828.
@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}
}
Zhang, Zhentong; Shan, Yugang; Yuan, Jie
Multi-Level Cell Progressive Differentiable Architecture Search to Improve Image Classification Accuracy Journal Article
In: Journal of Signal Processing Systems, 2021.
@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}
}
Zheng, X; Ji, R; Chen, Y; Wang, Q; Zhang, B; Ye, Q; Chen, J; Huang, F; Tian, Y
MIGO-NAS: Towards Fast and Generalizable Neural Architecture Search Journal Article
In: IEEE Transactions on Pattern Analysis & Machine Intelligence, no. 01, pp. 1-1, 2021, ISSN: 1939-3539.
@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}
}
Zimmer, Lucas; Lindauer, Marius; Hutter, Frank
Auto-Pytorch: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL Journal Article
In: IEEE transactions on pattern analysis and machine intelligence, vol. PP, 2021, ISSN: 0162-8828.
@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}
}
Liu, Lanlan; Zhang, Yuting; Deng, Jia; Soatto, Stefano
Dynamically Grown Generative Adversarial Networks Proceedings Article
In: AAAI 2021, 2021.
@inproceedings{LiuAAAI2021,
title = {Dynamically Grown Generative Adversarial Networks},
author = {Lanlan Liu and Yuting Zhang and Jia Deng and Stefano Soatto},
url = {https://www.aaai.org/AAAI21Papers/AAAI-1376.LiuL.pdf},
year = {2021},
date = {2021-02-02},
booktitle = {AAAI 2021},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Xu, Y; Xie, L; Dai, W; Zhang, X; Chen, X; Qi, G; Xiong, H; Tian, Q
Partially-Connected Neural Architecture Search for Reduced Computational Redundancy Journal Article
In: IEEE Transactions on Pattern Analysis & Machine Intelligence, no. 01, pp. 1-1, 2021, ISSN: 1939-3539.
@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}
}
Hao, Jie; Zhu, William
Architecture self-attention mechanism: nonlinear optimization for neural architecture search Journal Article
In: Journal of Nonlinear and Variational Analysis, vol. 5, pp. 119-140, 2021.
@article{Hao2021,
title = { Architecture self-attention mechanism: nonlinear optimization for neural architecture search},
author = {Jie Hao and William Zhu},
url = {http://jnva.biemdas.com/issues/JNVA2021-1-8.pdf},
doi = { 10.23952/jnva.5.2021.1.08},
year = {2021},
date = {2021-02-01},
journal = {Journal of Nonlinear and Variational Analysis},
volume = {5},
pages = {119-140},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Gao, Yanjie; Gu, Xianyu; Zhang, Hongyu; Lin, Haoxiang; Yang, Mao
Runtime Performance Prediction for Deep Learning Models with Graph Neural Network Technical Report
Microsoft no. MSR-TR-2021-3, 2021.
@techreport{gao2021runtime,
title = {Runtime Performance Prediction for Deep Learning Models with Graph Neural Network},
author = {Yanjie Gao and Xianyu Gu and Hongyu Zhang and Haoxiang Lin and Mao Yang},
url = {https://www.microsoft.com/en-us/research/publication/runtime-performance-prediction-for-deep-learning-models-with-graph-neural-network/},
year = {2021},
date = {2021-02-01},
urldate = {2021-02-01},
number = {MSR-TR-2021-3},
institution = {Microsoft},
abstract = {Recently, deep learning (DL) has been widely adopted in many application domains. Predicting the runtime performance of DL models such as GPU memory consumption and training time is important to boost development productivity and reduce resource waste because improper configurations of hyperparameters and neural architectures can result in many failed training jobs or inappropriate models. However, general runtime performance prediction for DL models is challenging due to the hybrid DL programming paradigm, complicated hidden factors within the framework runtime, fairly huge model configuration space, and wide differences among models. In this paper, we propose DNNPerf, a novel and general machine learning approach to predict the runtime performance of DL models using Graph Neural Network. DNNPerf represents a DL model as a directed acyclic computation graph and designs a rich set of effective performance-related features based on the computational semantics of both nodes and edges. We also propose a new Attention-based Node-Edge Encoder to better encode the node and edge features. DNNPerf is extensively evaluated on thousands of configurations of real-world and synthetic DL models to predict their GPU memory consumption and training time. The experimental results demonstrate that DNNPerf achieves an overall error of 13.684% for the GPU memory consumption prediction and an overall error of 7.443% for the training time prediction, outperforming all the compared methods.},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Pham, Hieu; Le, Quoc V
AutoDropout - Learning Dropout Patterns to Regularize Deep Networks Technical Report
2021.
@techreport{Pham2021_okt,
title = {AutoDropout - Learning Dropout Patterns to Regularize Deep Networks},
author = {Hieu Pham and Quoc V Le},
url = {https://arxiv.org/abs/2101.01761},
year = {2021},
date = {2021-01-01},
volume = {abs/2101.01761},
key = {journals/corr/abs-2101-01761},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Huang, Yufang; Axsom, Kelly M; Lee, John; Subramanian, Lakshminarayanan; Zhang, Yiye
DICE: Deep Significance Clustering for Outcome-Aware Stratification Technical Report
2021.
@techreport{YufangHuang2021_xxi,
title = {DICE: Deep Significance Clustering for Outcome-Aware Stratification},
author = {Yufang Huang and Kelly M Axsom and John Lee and Lakshminarayanan Subramanian and Yiye Zhang},
url = {https://arxiv.org/abs/2101.02344},
year = {2021},
date = {2021-01-01},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Ma, Ailong; Wan, Yuting; Zhong, Yanfei; Wang, Junjue; Zhang, Liangpei
SceneNet: Remote sensing scene classification deep learning network using multi-objective neural evolution architecture search Technical Report
2021, ISSN: 0924-2716.
@techreport{AilongMa2021_voj,
title = {SceneNet: Remote sensing scene classification deep learning network using multi-objective neural evolution architecture search},
author = {Ailong Ma and Yuting Wan and Yanfei Zhong and Junjue Wang and Liangpei Zhang},
url = {https://www.sciencedirect.com/science/article/pii/S0924271620303361},
doi = {https://doi.org/10.1016/j.isprsjprs.2020.11.025},
issn = {0924-2716},
year = {2021},
date = {2021-01-01},
journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
volume = {172},
pages = {171-188},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Yang, Hansi; Yao, Quanming; Kwok, James T
Tensorizing Subgraph Search in the Supernet Technical Report
2021.
@techreport{Yang2021_atf,
title = {Tensorizing Subgraph Search in the Supernet},
author = {Hansi Yang and Quanming Yao and James T Kwok},
url = {https://arxiv.org/abs/2101.01078},
year = {2021},
date = {2021-01-01},
volume = {abs/2101.01078},
key = {journals/corr/abs-2101-01078},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Syed, Muhtadyuzzaman; Srinivasan, Arvind Akpuram
Generalized Latency Performance Estimation for Once-For-All Neural Architecture Search Technical Report
2021.
@techreport{Syed2021_kud,
title = {Generalized Latency Performance Estimation for Once-For-All Neural Architecture Search},
author = {Muhtadyuzzaman Syed and Arvind Akpuram Srinivasan},
url = {https://arxiv.org/abs/2101.00732},
year = {2021},
date = {2021-01-01},
volume = {abs/2101.00732},
key = {journals/corr/abs-2101-00732},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Huang, Hanxun; Ma, Xingjun; Erfani, Sarah M; Bailey, James
Neural Architecture Search via Combinatorial Multi-Armed Bandit Technical Report
2021.
@techreport{Huang2021_aks,
title = {Neural Architecture Search via Combinatorial Multi-Armed Bandit},
author = {Hanxun Huang and Xingjun Ma and Sarah M Erfani and James Bailey},
url = {https://arxiv.org/abs/2101.00336},
year = {2021},
date = {2021-01-01},
volume = {abs/2101.00336},
key = {journals/corr/abs-2101-00336},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Tang, Tianqi; Yu, Xin; Dong, Xuanyi; Yang, Yi
Auto-Navigator: Decoupled Neural Architecture Search for Visual Navigation Technical Report
2021.
@techreport{Tang2021_szq,
title = {Auto-Navigator: Decoupled Neural Architecture Search for Visual Navigation},
author = {Tianqi Tang and Xin Yu and Xuanyi Dong and Yi Yang},
url = {https://openaccess.thecvf.com/content/WACV2021/html/Tang_Auto-Navigator_Decoupled_Neural_Architecture_Search_for_Visual_Navigation_WACV_2021_paper.html},
year = {2021},
date = {2021-01-01},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
pages = {3743-3752},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Zheng, Shuai; Wang, Yabin; Li, Baotong; Li, Xin
A Hardware-adaptive Deep Feature Matching Pipeline for Real-time 3D Reconstruction Journal Article
In: vol. 132, pp. 102984, 2021.
@article{Zheng2021_mdc,
title = {A Hardware-adaptive Deep Feature Matching Pipeline for Real-time 3D Reconstruction},
author = {Shuai Zheng and Yabin Wang and Baotong Li and Xin Li},
url = {https://www.sciencedirect.com/science/article/abs/pii/S0010448520301779},
doi = {10.1016/J.CAD.2020.102984},
year = {2021},
date = {2021-01-01},
volume = {132},
pages = {102984},
key = {journals/cad/ZhengWLL21},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Hosseini, Ramtin; Yang, Xingyi; Xie, Pengtao
DSRNA - Differentiable Search of Robust Neural Architectures Proceedings Article
In: CVPR 2021, 2021.
@inproceedings{Hosseini2020_zbg,
title = {DSRNA - Differentiable Search of Robust Neural Architectures},
author = {Ramtin Hosseini and Xingyi Yang and Pengtao Xie},
url = {https://arxiv.org/abs/2012.06122},
year = {2021},
date = {2021-01-01},
booktitle = {CVPR 2021},
volume = {abs/2012.06122},
key = {journals/corr/abs-2012-06122},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Ruchte, Michael; Zela, Arber; Siems, Julien Niklas; Grabocka, Josif; Hutter, Frank
NASLib: A Modular and Flexible Neural Architecture Search Library Technical Report
2021.
@techreport{MichaelRuchte2021_kjn,
title = {NASLib: A Modular and Flexible Neural Architecture Search Library},
author = {Michael Ruchte and Arber Zela and Julien Niklas Siems and Josif Grabocka and Frank Hutter},
url = {https://openreview.net/forum?id=EohGx2HgNsA},
year = {2021},
date = {2021-01-01},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Shaikh, Azhar; Sinha, Nishant
Learn to Bind and Grow Neural Structures Proceedings Article
In: pp. 119-126, 2021.
@inproceedings{Shaikh2021_sss,
title = {Learn to Bind and Grow Neural Structures},
author = {Azhar Shaikh and Nishant Sinha},
url = {https://arxiv.org/abs/2011.10568},
doi = {10.1145/3430984.3431019},
year = {2021},
date = {2021-01-01},
pages = {119-126},
key = {conf/comad/ShaikhS21},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Lu, Hao; Han, Hu
NAS-HR: search of neural architecture for heart-rate estimation from face videos Technical Report
2021.
@techreport{Lu2021_pdu,
title = {NAS-HR: search of neural architecture for heart-rate estimation from face videos},
author = {Hao Lu and Hu Han},
url = {http://vr-ih.com/vrih/resource/latest_accept/323112704838656.pdf},
doi = {10.1016/j.vrih.2020.10.002},
year = {2021},
date = {2021-01-01},
journal = {Virtual Reality& Intelligent Hardware},
pages = {33--42},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Peng, Daiyi; Dong, Xuanyi; Real, Esteban; Tan, Mingxing; Lu, Yifeng; Liu, Hanxiao; Bender, Gabriel; Kraft, Adam; Liang, Chen; Le, Quoc V
PyGlove - Symbolic Programming for Automated Machine Learning Technical Report
2021.
@techreport{Peng2021_jau,
title = {PyGlove - Symbolic Programming for Automated Machine Learning},
author = {Daiyi Peng and Xuanyi Dong and Esteban Real and Mingxing Tan and Yifeng Lu and Hanxiao Liu and Gabriel Bender and Adam Kraft and Chen Liang and Quoc V Le},
url = {https://papers.nips.cc/paper/2020/file/012a91467f210472fab4e11359bbfef6-Paper.pdf},
year = {2021},
date = {2021-01-01},
volume = {abs/2101.08809},
key = {journals/corr/abs-2101-08809},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Liu, Jiaheng; Zhou, Shunfeng; Wu, Yichao; Chen, Ken; Ouyang, Wanli; Xu, Dong
Block Proposal Neural Architecture Search Journal Article
In: vol. 30, pp. 15-25, 2021.
@article{Liu2021_gru,
title = {Block Proposal Neural Architecture Search},
author = {Jiaheng Liu and Shunfeng Zhou and Yichao Wu and Ken Chen and Wanli Ouyang and Dong Xu},
url = {https://pubmed.ncbi.nlm.nih.gov/33035163/},
doi = {10.1109/TIP.2020.3028288},
year = {2021},
date = {2021-01-01},
volume = {30},
pages = {15-25},
key = {journals/tip/LiuZWCOX21},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
He, Xin; Wang, Shihao; Ying, Guohao; Zhang, Jiyong; Chu, Xiaowen
Efficient Multi-objective Evolutionary 3D Neural Architecture Search for COVID-19 Detection with Chest CT Scans Technical Report
2021.
@techreport{He2021_lri,
title = {Efficient Multi-objective Evolutionary 3D Neural Architecture Search for COVID-19 Detection with Chest CT Scans},
author = {Xin He and Shihao Wang and Guohao Ying and Jiyong Zhang and Xiaowen Chu},
url = {https://ieeexplore.ieee.org/abstract/document/9207545},
year = {2021},
date = {2021-01-01},
volume = {abs/2101.10667},
key = {journals/corr/abs-2101-10667},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Chu, Xiangxiang; Wang, Xiaoxing; Zhang, Bo; Lu, Shun; Wei, Xiaolin; Yan, Junchi
DARTS-: Robustly Stepping out of Performance Collapse Without Indicators Technical Report
2021.
@techreport{XiangxiangChu2021_pqn,
title = {DARTS-: Robustly Stepping out of Performance Collapse Without Indicators},
author = {Xiangxiang Chu and Xiaoxing Wang and Bo Zhang and Shun Lu and Xiaolin Wei and Junchi Yan},
url = {https://arxiv.org/abs/2009.01027},
year = {2021},
date = {2021-01-01},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Liang, Xinle; Liu, Yang; Luo, Jiahuan; He, Yuanqin; Chen, Tianjian; Yang, Qiang
Self-supervised Cross-silo Federated Neural Architecture Search Technical Report
2021.
@techreport{Liang2021_fxt,
title = {Self-supervised Cross-silo Federated Neural Architecture Search},
author = {Xinle Liang and Yang Liu and Jiahuan Luo and Yuanqin He and Tianjian Chen and Qiang Yang},
url = {https://arxiv.org/abs/2007.01500},
year = {2021},
date = {2021-01-01},
volume = {abs/2101.11896},
key = {journals/corr/abs-2101-11896},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Mittal, Govind; Korus, Pawel; Memon, Nasir D
FiFTy - Large-Scale File Fragment Type Identification Using Convolutional Neural Networks Journal Article
In: vol. 16, pp. 28-41, 2021.
@article{Mittal2021_rhn,
title = {FiFTy - Large-Scale File Fragment Type Identification Using Convolutional Neural Networks},
author = {Govind Mittal and Pawel Korus and Nasir D Memon},
url = {https://ieeexplore.ieee.org/abstract/document/9122499},
doi = {10.1109/TIFS.2020.3004266},
year = {2021},
date = {2021-01-01},
volume = {16},
pages = {28-41},
key = {journals/tifs/MittalKM21},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Yang, Zhao; Zhang, Shengbing; Li, Ruxu; Li, Chuxi; Wang, Miao; Wang, Danghui; Zhang, Meng
Efficient Resource-Aware Convolutional Neural Architecture Search for Edge Computing with Pareto-Bayesian Optimization Journal Article
In: vol. 21, no. 2, pp. 444, 2021.
@article{Yang2021_olp,
title = {Efficient Resource-Aware Convolutional Neural Architecture Search for Edge Computing with Pareto-Bayesian Optimization},
author = {Zhao Yang and Shengbing Zhang and Ruxu Li and Chuxi Li and Miao Wang and Danghui Wang and Meng Zhang},
url = {https://arxiv.org/abs/1806.07912},
doi = {10.3390/S21020444},
year = {2021},
date = {2021-01-01},
volume = {21},
number = {2},
pages = {444},
key = {journals/sensors/YangZLLWWZ21},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Wei, Tao; Wang, Changhu; Chen, Chang Wen
Modularized Morphing of Deep Convolutional Neural Networks - A Graph Approach Journal Article
In: vol. 70, no. 2, pp. 305-315, 2021.
@article{Wei2021_ghp,
title = {Modularized Morphing of Deep Convolutional Neural Networks - A Graph Approach},
author = {Tao Wei and Changhu Wang and Chang Wen Chen},
url = {https://arxiv.org/abs/1701.03281},
doi = {10.1109/TC.2020.2988006},
year = {2021},
date = {2021-01-01},
volume = {70},
number = {2},
pages = {305-315},
key = {journals/tc/WeiWC21},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Song, Xingyou; Choromanski, Krzysztof; Parker-Holder, Jack; Tang, Yunhao; Peng, Daiyi; Jain, Deepali; Gao, Wenbo; Pacchiano, Aldo; Sarlós, Tamás; Yang, Yuxiang
ES-ENAS - Combining Evolution Strategies with Neural Architecture Search at No Extra Cost for Reinforcement Learning Technical Report
2021.
@techreport{Song2021_xto,
title = {ES-ENAS - Combining Evolution Strategies with Neural Architecture Search at No Extra Cost for Reinforcement Learning},
author = {Xingyou Song and Krzysztof Choromanski and Jack Parker-Holder and Yunhao Tang and Daiyi Peng and Deepali Jain and Wenbo Gao and Aldo Pacchiano and Tamás Sarlós and Yuxiang Yang},
url = {https://arxiv.org/abs/1611.01578},
year = {2021},
date = {2021-01-01},
volume = {abs/2101.07415},
key = {journals/corr/abs-2101-07415},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Rorabaugh, Ariel Keller; -, Silvina Caíno; II, Michael Wyatt R; Johnston, Travis; Taufer, Michela
PEng4NN: An Accurate Performance Estimation Engine for Efficient Automated Neural Network Architecture Search Technical Report
2021.
@techreport{ArielKellerRorabaugh2021_ncl,
title = {PEng4NN: An Accurate Performance Estimation Engine for Efficient Automated Neural Network Architecture Search},
author = {Ariel Keller Rorabaugh and Silvina Caíno - and Michael Wyatt R II and Travis Johnston and Michela Taufer},
url = {https://arxiv.org/abs/2101.04185},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2101.04185},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Zhang, Haokui; Gong, Chengrong; Bai, Yunpeng; Bai, Zongwen; Li, Ying
3D-ANAS: 3D Asymmetric Neural Architecture Search for Fast Hyperspectral Image Classification Miscellaneous
2021.
@misc{HaokuiZhang2021_uqt,
title = {3D-ANAS: 3D Asymmetric Neural Architecture Search for Fast Hyperspectral Image Classification},
author = {Haokui Zhang and Chengrong Gong and Yunpeng Bai and Zongwen Bai and Ying Li},
url = {https://arxiv.org/abs/2101.04287},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2101.04287},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Gu, Hongyang; Fu, Guangyuan; Li, Jianmin; Zhu, Jun
Auto-ReID+: Searching for a multi-branch ConvNet for person re-identification Journal Article
In: Neurocomputing, vol. 435, pp. 53-66, 2021, ISSN: 0925-2312.
@article{HongyangGu2021_bui,
title = {Auto-ReID+: Searching for a multi-branch ConvNet for person re-identification},
author = {Hongyang Gu and Guangyuan Fu and Jianmin Li and Jun Zhu},
url = {https://www.sciencedirect.com/science/article/pii/S0925231220320178},
doi = {https://doi.org/10.1016/j.neucom.2020.12.105},
issn = {0925-2312},
year = {2021},
date = {2021-01-01},
journal = {Neurocomputing},
volume = {435},
pages = {53-66},
abstract = {In the field of person re-identification (ReID), multi-branch models are more effective in learning robust features than single-branch models. The current popular multi-branch models are based on ResNet or GoogleNet. These networks are designed initially to solve classification problems. There is an essential difference between ReID and classification problems, so it is particularly important to find a corresponding multi-branch backbone for ReID tasks. We propose to automatically search for a multi-branch convolutional neural network (CNN) for ReID tasks utilizing neural architecture search (NAS). First, we designed a multi-resolution, multi-branch macro search architecture that can extract more abundant scale information. Then in the searching process, the early stopping mechanism is proposed to improve the effectiveness and efficiency of the entire searching process. Finally, we experimentally prove on four mainstream datasets that the searched model can achieve state-of-the-art performance with only 5.7 million parameters.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
He, Xin; Wang, Shihao; Chu, Xiaowen; Shi, Shaohuai; Tang, Jiangping; Liu, Xin; Yan, Chenggang; Zhang, Jiyong; Ding, Guiguang
Automated Model Design and Benchmarking of 3D Deep Learning Models for COVID-19 Detection with Chest CT Scans Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2101-05442,
title = {Automated Model Design and Benchmarking of 3D Deep Learning Models for COVID-19 Detection with Chest CT Scans},
author = {Xin He and Shihao Wang and Xiaowen Chu and Shaohuai Shi and Jiangping Tang and Xin Liu and Chenggang Yan and Jiyong Zhang and Guiguang Ding},
url = {https://arxiv.org/abs/2101.05442},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2101.05442},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Zhou, Benjia; Li, Yunan; Wan, Jun
Regional Attention with Architecture-Rebuilt 3D Network for RGB-D Gesture Recognition Technical Report
2021.
@techreport{zhou2021regional,
title = {Regional Attention with Architecture-Rebuilt 3D Network for RGB-D Gesture Recognition},
author = {Benjia Zhou and Yunan Li and Jun Wan},
url = {https://arxiv.org/abs/2102.05348},
year = {2021},
date = {2021-01-01},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Yang, Zhao; Zhang, Shengbing; Li, Ruxu; Li, Chuxi; Wang, Miao; Wang, Danghui; Zhang, Meng
Efficient Resource-Aware Convolutional Neural Architecture Search for Edge Computing with Pareto-Bayesian Optimization Journal Article
In: Sensors, vol. 21, no. 2, 2021, ISSN: 1424-8220.
@article{s21020444,
title = {Efficient Resource-Aware Convolutional Neural Architecture Search for Edge Computing with Pareto-Bayesian Optimization},
author = {Zhao Yang and Shengbing Zhang and Ruxu Li and Chuxi Li and Miao Wang and Danghui Wang and Meng Zhang},
url = {https://www.mdpi.com/1424-8220/21/2/444},
doi = {10.3390/s21020444},
issn = {1424-8220},
year = {2021},
date = {2021-01-01},
journal = {Sensors},
volume = {21},
number = {2},
abstract = {With the development of deep learning technologies and edge computing, the combination of them can make artificial intelligence ubiquitous. Due to the constrained computation resources of the edge device, the research in the field of on-device deep learning not only focuses on the model accuracy but also on the model efficiency, for example, inference latency. There are many attempts to optimize the existing deep learning models for the purpose of deploying them on the edge devices that meet specific application requirements while maintaining high accuracy. Such work not only requires professional knowledge but also needs a lot of experiments, which limits the customization of neural networks for varied devices and application scenarios. In order to reduce the human intervention in designing and optimizing the neural network structure, multi-objective neural architecture search methods that can automatically search for neural networks featured with high accuracy and can satisfy certain hardware performance requirements are proposed. However, the current methods commonly set accuracy and inference latency as the performance indicator during the search process, and sample numerous network structures to obtain the required neural network. Lacking regulation to the search direction with the search objectives will generate a large number of useless networks during the search process, which influences the search efficiency to a great extent. Therefore, in this paper, an efficient resource-aware search method is proposed. Firstly, the network inference consumption profiling model for any specific device is established, and it can help us directly obtain the resource consumption of each operation in the network structure and the inference latency of the entire sampled network. Next, on the basis of the Bayesian search, a resource-aware Pareto Bayesian search is proposed. Accuracy and inference latency are set as the constraints to regulate the search direction. With a clearer search direction, the overall search efficiency will be improved. Furthermore, cell-based structure and lightweight operation are applied to optimize the search space for further enhancing the search efficiency. The experimental results demonstrate that with our method, the inference latency of the searched network structure reduced 94.71% without scarifying the accuracy. At the same time, the search efficiency increased by 18.18%.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Weng, Yu; Chen, Zehua; Zhou, Tianbao
Improved differentiable neural architecture search for single image super-resolution Journal Article
In: Peer-to-Peer Networking and Applications, 2021.
@article{journals/PPNA/Weng21,
title = {Improved differentiable neural architecture search for single image super-resolution},
author = {Yu Weng and Zehua Chen and Tianbao Zhou},
url = {https://doi.org/10.1007/s12083-020-01048-4},
doi = {10.1007/s12083-020-01048-4},
year = {2021},
date = {2021-01-01},
journal = {Peer-to-Peer Networking and Applications},
abstract = {Deep learning has shown prominent superiority over other machine learning algorithms in Single Image Super-Resolution (SISR). In order to reduce the efforts and resources cost on manually designing deep architecture, we use differentiable neural architecture search (DARTS) on SISR. Since neural architecture search was originally used for classification tasks, our experiments show that direct usage of DARTS on super-resolutions tasks will give rise to many skip connections in the search architecture, which results in the poor performance of final architecture. Thus, it is necessary for DARTS to have made some improvements for the application in the field of SISR. According to characteristics of SISR, we remove redundant operations and redesign some operations in the cell to achieve an improved DARTS. Then we use the improved DARTS to search convolution cells as a nonlinear mapping part of super-resolution network. The new super-resolution architecture shows its effectiveness on benchmark datasets and DIV2K dataset.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Liu, Jia; Jin, Yaochu
Multi-objective Search of Robust Neural Architectures against Multiple Types of Adversarial Attacks Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2101-06507,
title = {Multi-objective Search of Robust Neural Architectures against Multiple Types of Adversarial Attacks},
author = {Jia Liu and Yaochu Jin},
url = {https://arxiv.org/abs/2101.06507},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2101.06507},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Wu, Yan; Huang, Zhiwu; Kumar, Suryansh; Sukthanker, Rhea Sanjay; Timofte, Radu; Gool, Luc Van
Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2101-06658,
title = {Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution},
author = {Yan Wu and Zhiwu Huang and Suryansh Kumar and Rhea Sanjay Sukthanker and Radu Timofte and Luc Van Gool},
url = {https://arxiv.org/abs/2101.06658},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2101.06658},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}