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.
2022
Lu, Qing; Xu, Xiaowei; Dong, Shunjie; Hao, Cong; Yang, Lei; Zhuo, Cheng; Shi, Yiyu
RT-DNAS: Real-time Constrained Differentiable Neural Architecture Search for 3D Cardiac Cine MRI Segmentation Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2206-04682,
title = {RT-DNAS: Real-time Constrained Differentiable Neural Architecture Search for 3D Cardiac Cine MRI Segmentation},
author = {Qing Lu and Xiaowei Xu and Shunjie Dong and Cong Hao and Lei Yang and Cheng Zhuo and Yiyu Shi},
url = {https://doi.org/10.48550/arXiv.2206.04682},
doi = {10.48550/arXiv.2206.04682},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2206.04682},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Liu, Jiawei; Zhang, Kaiyu; Hu, Weitai; Yang, Qing
Improve Ranking Correlation of Super-net through Training Scheme from One-shot NAS to Few-shot NAS Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2206-05896,
title = {Improve Ranking Correlation of Super-net through Training Scheme from One-shot NAS to Few-shot NAS},
author = {Jiawei Liu and Kaiyu Zhang and Weitai Hu and Qing Yang},
url = {https://doi.org/10.48550/arXiv.2206.05896},
doi = {10.48550/arXiv.2206.05896},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2206.05896},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Eslahi, Samira Vafay; Tao, Jian; Ji, Jim
ERNAS: An Evolutionary Neural Architecture Search for Magnetic Resonance Image Reconstructions Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2206-07280,
title = {ERNAS: An Evolutionary Neural Architecture Search for Magnetic Resonance Image Reconstructions},
author = {Samira Vafay Eslahi and Jian Tao and Jim Ji},
url = {https://doi.org/10.48550/arXiv.2206.07280},
doi = {10.48550/arXiv.2206.07280},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2206.07280},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Yang, Yingguang; Yang, Renyu; Li, Yangyang; Cui, Kai; Yang, Zhiqin; Wang, Yue; Xu, Jie; Xie, Haiyong
RoSGAS: Adaptive Social Bot Detection with Reinforced Self-Supervised GNN Architecture Search Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2206-06757,
title = {RoSGAS: Adaptive Social Bot Detection with Reinforced Self-Supervised GNN Architecture Search},
author = {Yingguang Yang and Renyu Yang and Yangyang Li and Kai Cui and Zhiqin Yang and Yue Wang and Jie Xu and Haiyong Xie},
url = {https://doi.org/10.48550/arXiv.2206.06757},
doi = {10.48550/arXiv.2206.06757},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2206.06757},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Ren, Xuhong; Chen, Jianlang; Juefei-Xu, Felix; Xue, Wanli; Guo, Qing; Ma, Lei; Zhao, Jianjun; Chen, Shengyong
DARTSRepair: Core-failure-set guided DARTS for network robustness to common corruptions Journal Article
In: Pattern Recognition, vol. 131, pp. 108864, 2022, ISSN: 0031-3203.
@article{REN2022108864,
title = {DARTSRepair: Core-failure-set guided DARTS for network robustness to common corruptions},
author = {Xuhong Ren and Jianlang Chen and Felix Juefei-Xu and Wanli Xue and Qing Guo and Lei Ma and Jianjun Zhao and Shengyong Chen},
url = {https://www.sciencedirect.com/science/article/pii/S0031320322003454},
doi = {https://doi.org/10.1016/j.patcog.2022.108864},
issn = {0031-3203},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {Pattern Recognition},
volume = {131},
pages = {108864},
abstract = {Network architecture search (NAS), in particular the differentiable architecture search (DARTS) method, has shown a great power to learn excellent model architectures on the specific dataset of interest. In contrast to using a fixed dataset, in this work, we focus on a different but important scenario for NAS: how to refine a deployed network’s model architecture to enhance its robustness with the guidance of a few collected and misclassified examples that are degraded by some real-world unknown corruptions having a specific pattern (e.g., noise, blur, etc..). To this end, we first conduct an empirical study to validate that the model architectures can be definitely related to the corruption patterns. Surprisingly, by just adding a few corrupted and misclassified examples (e.g., 103 examples) to the clean training dataset (e.g., 5.0×104 examples), we can refine the model architecture and enhance the robustness significantly. To make it more practical, the key problem, i.e., how to select the proper failure examples for the effective NAS guidance, should be carefully investigated. Then, we propose a novel core-failure-set guided DARTS that embeds a K-center-greedy algorithm for DARTS to select suitable corrupted failure examples to refine the model architecture. We use our method for DARTS-refined DNNs on the clean as well as 15 corruptions with the guidance of four specific real-world corruptions. Compared with the state-of-the-art NAS as well as data-augmentation-based enhancement methods, our final method can achieve higher accuracy on both corrupted datasets and the original clean dataset. On some of the corruption patterns, we can achieve as high as over 45% absolute accuracy improvements.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Dervisi, Foteini; Kyriakides, George; Margaritis, Konstantinos
Evaluating Acceleration Techniques for Genetic Neural Architecture Search Proceedings Article
In: Iliadis, Lazaros; Jayne, Chrisina; Tefas, Anastasios; Pimenidis, Elias (Ed.): Engineering Applications of Neural Networks, pp. 3–14, Springer International Publishing, Cham, 2022, ISBN: 978-3-031-08223-8.
@inproceedings{10.1007/978-3-031-08223-8_1,
title = {Evaluating Acceleration Techniques for Genetic Neural Architecture Search},
author = {Foteini Dervisi and George Kyriakides and Konstantinos Margaritis},
editor = {Lazaros Iliadis and Chrisina Jayne and Anastasios Tefas and Elias Pimenidis},
isbn = {978-3-031-08223-8},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {Engineering Applications of Neural Networks},
pages = {3--14},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {The increase in the available data and computational power has led to the rapid evolution of the field of deep learning over the last few years. However, the success of deep learning methods relies on making appropriate neural architecture choices, which is not a straightforward task and usually requires a time-consuming trial-and-error procedure. Neural architecture search is the process of automating the design of neural network architectures capable of performing well on specific tasks. It is a field that has emerged in order to address the problem of designing efficient neural architectures and is gaining popularity due to the rapid evolution of deep learning, which has led to an increasing need for the discovery of high-performing neural architectures. This paper focuses on evolutionary neural architecture search, which is an efficient but also time-consuming and computationally expensive neural architecture search approach, and aims to pave the way for speeding up such algorithms by assessing the effect of acceleration methods on the overall performance of the neural architecture search procedure as well as on the produced architectures.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Zhang, Wentao; Lin, Zheyu; Shen, Yu; Li, Yang; Yang, Zhi; Cui, Bin
DFG-NAS: Deep and Flexible Graph Neural Architecture Search Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2206-08582,
title = {DFG-NAS: Deep and Flexible Graph Neural Architecture Search},
author = {Wentao Zhang and Zheyu Lin and Yu Shen and Yang Li and Zhi Yang and Bin Cui},
url = {https://doi.org/10.48550/arXiv.2206.08582},
doi = {10.48550/arXiv.2206.08582},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2206.08582},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Xue, Yu; Qin, Jiafeng
Partial Connection Based on Channel Attention for Differentiable Neural Architecture Search Journal Article
In: IEEE Transactions on Industrial Informatics, pp. 1-10, 2022.
@article{9802692,
title = {Partial Connection Based on Channel Attention for Differentiable Neural Architecture Search},
author = {Yu Xue and Jiafeng Qin},
url = {https://ieeexplore.ieee.org/abstract/document/9802692},
doi = {10.1109/TII.2022.3184700},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {IEEE Transactions on Industrial Informatics},
pages = {1-10},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Qin, Yijian; Zhang, Ziwei; Wang, Xin; Zhang, Zeyang; Zhu, Wenwu
NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2206-09166,
title = {NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search},
author = {Yijian Qin and Ziwei Zhang and Xin Wang and Zeyang Zhang and Wenwu Zhu},
url = {https://doi.org/10.48550/arXiv.2206.09166},
doi = {10.48550/arXiv.2206.09166},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2206.09166},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Jung, Harim; Oh, Myeong-Seok; Yang, Cheoljong; Lee, Seong-Whan
Neural Architecture Adaptation for Object Detection by Searching Channel Dimensions and Mapping Pre-trained Parameters Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2206-08509,
title = {Neural Architecture Adaptation for Object Detection by Searching Channel Dimensions and Mapping Pre-trained Parameters},
author = {Harim Jung and Myeong-Seok Oh and Cheoljong Yang and Seong-Whan Lee},
url = {https://doi.org/10.48550/arXiv.2206.08509},
doi = {10.48550/arXiv.2206.08509},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2206.08509},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Risso, Matteo; Burrello, Alessio; Benini, Luca; Macii, Enrico; Poncino, Massimo; Pagliari, Daniele Jahier
Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge Nodes Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2206-08852,
title = {Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge Nodes},
author = {Matteo Risso and Alessio Burrello and Luca Benini and Enrico Macii and Massimo Poncino and Daniele Jahier Pagliari},
url = {https://doi.org/10.48550/arXiv.2206.08852},
doi = {10.48550/arXiv.2206.08852},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2206.08852},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Hasan, Noha W.; Saudi, Ali S.; Khalil, Mahmoud I.; Abbas, Hazem M.
A Genetic Algorithm Approach to Automate Architecture Design for Acoustic Scene Classification Journal Article
In: IEEE Transactions on Evolutionary Computation, pp. 1-1, 2022.
@article{9803192,
title = {A Genetic Algorithm Approach to Automate Architecture Design for Acoustic Scene Classification},
author = {Noha W. Hasan and Ali S. Saudi and Mahmoud I. Khalil and Hazem M. Abbas},
doi = {10.1109/TEVC.2022.3185543},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {IEEE Transactions on Evolutionary Computation},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Lou, Xiaoxuan; Guo, Shangwei; Li, Jiwei; Zhang, Tianwei
Ownership Verification of DNN Architectures via Hardware Cache Side Channels Journal Article
In: IEEE Transactions on Circuits and Systems for Video Technology, pp. 1-1, 2022.
@article{9801864,
title = {Ownership Verification of DNN Architectures via Hardware Cache Side Channels},
author = {Xiaoxuan Lou and Shangwei Guo and Jiwei Li and Tianwei Zhang},
url = {https://ieeexplore.ieee.org/abstract/document/9801864},
doi = {10.1109/TCSVT.2022.3184644},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Perego, Riccardo; Candelieri, Antonio; Archetti, Francesco; Pau, Danilo
AutoTinyML for microcontrollers: Dealing with black-box deployability Journal Article
In: Expert Systems with Applications, vol. 207, pp. 117876, 2022, ISSN: 0957-4174.
@article{PEREGO2022117876,
title = {AutoTinyML for microcontrollers: Dealing with black-box deployability},
author = {Riccardo Perego and Antonio Candelieri and Francesco Archetti and Danilo Pau},
url = {https://www.sciencedirect.com/science/article/pii/S0957417422011289},
doi = {https://doi.org/10.1016/j.eswa.2022.117876},
issn = {0957-4174},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {Expert Systems with Applications},
volume = {207},
pages = {117876},
abstract = {While many companies are currently leveraging on Cloud, data centres and specialized hardware (e.g., GPUs and TPUs) to train very accurate Machine Learning models, the need to deploy and run these models on tiny devices is emerging as the most relevant challenge, with a massive untapped market. Although Automated Machine Learning and Neural Architecture Search frameworks are successfully used to find accurate models by trying a small number of alternatives, they are typically performed on large computational platforms and they cannot directly deal with deployability, leading to an accurate model which could result undeployable on a tiny device. To bridge the gap between these two worlds, we present an approach extending these frameworks to include the constraints related to the limited hardware resources of the tiny device which the trained model has to run on. Experimental results on two benchmark classification tasks and two microcontrollers prove that our AutoTinyML framework can efficiently identify models which are both accurate and deployable, in case accepting a reasonable reduction in accuracy compared to a significant reduction in hardware usages, without applying any quantization techniques of the model.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Gridin, Ivan
Öne-Shot Neural Architecture Search Book Chapter
In: Äutomated Deep Learning Using Neural Network Intelligence: Develop and Design PyTorch and TensorFlow Models Using Python", pp. 257–318, Äpress, Berkeley, CA, 2022, ISBN: 978-1-4842-8149-9.
@inbook{Gridin2022,
title = {Öne-Shot Neural Architecture Search},
author = {Ivan Gridin},
url = {https://doi.org/10.1007/978-1-4842-8149-9_5},
doi = {10.1007/978-1-4842-8149-9_5},
isbn = {978-1-4842-8149-9},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {Äutomated Deep Learning Using Neural Network Intelligence: Develop and Design PyTorch and TensorFlow Models Using Python"},
pages = {257--318},
publisher = {Äpress},
address = {Berkeley, CA},
abstract = {In the previous chapter, we explored Multi-trial Neural Architecture Search, which is a very promising approach. And the reader might wonder why Multi-trial NAS is called that way. Are there any other non-Multi-trial NAS approaches, and is it really possible to search for the optimal neural network architecture in some other way without trying it? It looks pretty natural that the only way to find the optimal solution is to try different elements in the search space. In fact, it turns out that this is not entirely true. There is an approach that allows you to find the best architecture by training some Supernet. And this approach is called One-shot Neural Architecture Search. As the name ``one-shot'' implies, this approach involves only one try or shot. Of course, this ``shot'' is much longer than single neural network training, but nevertheless, it saves a lot of time. In this chapter, we will study what One-shot NAS is and how to design architectures for this approach. We will examine two popular One-shot algorithms: Efficient Neural Architecture Search via Parameter Sharing (ENAS)Efficient neural architecture search via parameter sharing (ENAS) and Differentiable Architecture Search (DARTS)Differentiable architecture search (DARTS). Of course, we will apply these algorithms to solve practical problems.},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Gridin, Ivan
Multi-trial Neural Architecture Search Book Chapter
In: Äutomated Deep Learning Using Neural Network Intelligence: Develop and Design PyTorch and TensorFlow Models Using Python", pp. 185–256, Äpress, Berkeley, CA, 2022, ISBN: 978-1-4842-8149-9.
@inbook{Gridin2022b,
title = {Multi-trial Neural Architecture Search},
author = {Ivan Gridin},
url = {https://doi.org/10.1007/978-1-4842-8149-9_4},
doi = {10.1007/978-1-4842-8149-9_4},
isbn = {978-1-4842-8149-9},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {Äutomated Deep Learning Using Neural Network Intelligence: Develop and Design PyTorch and TensorFlow Models Using Python"},
pages = {185--256},
publisher = {Äpress},
address = {Berkeley, CA},
abstract = {Änd now we come to the most exciting part of this book. As we noted at the end of the last chapter, HPO methods are pretty limited for automating the search for the optimal deep learning models, but Neural Architecture Search (NAS) dispels these limits. This chapter focuses on NAS, one of the most promising areas of automated deep learning. Automatic Neural Architecture Search is increasingly important in finding appropriate deep learning models. Recent researches have proven the NAS effectiveness and found some models that could beat manually tuned ones. NAS is a fairly young discipline in machine learning. It took shape as a separate discipline in 2018. Since then, it has made a significant breakthrough in automating neural network architecture construction that solves a specific problem. The most manual design of neural networks can be replaced by automated architecture search soon, so this area is very up and coming for all data scientists. NAS produced many top computer vision architectures. Architectures like NASNet, EfficientNet, and MobileNet are the result of automated Neural Architecture Search."},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Dudziak, Lukasz; Laskaridis, Stefanos; Fernández-Marqués, Javier
FedorAS: Federated Architecture Search under system heterogeneity Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2206-11239,
title = {FedorAS: Federated Architecture Search under system heterogeneity},
author = {Lukasz Dudziak and Stefanos Laskaridis and Javier Fernández-Marqués},
url = {https://doi.org/10.48550/arXiv.2206.11239},
doi = {10.48550/arXiv.2206.11239},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2206.11239},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Duan, Fenxia; Cao, Chunhong; Gao, Xieping
SA-NAS-BFNR: Spatiotemporal Attention Neural Architecture Search for Task-Based Brain Functional Network Representation Proceedings Article
In: Proceedings of the 2022 International Conference on Multimedia Retrieval, pp. 661–667, Association for Computing Machinery, Newark, NJ, USA, 2022, ISBN: 9781450392389.
@inproceedings{10.1145/3512527.3531421,
title = {SA-NAS-BFNR: Spatiotemporal Attention Neural Architecture Search for Task-Based Brain Functional Network Representation},
author = {Fenxia Duan and Chunhong Cao and Xieping Gao},
url = {https://doi.org/10.1145/3512527.3531421},
doi = {10.1145/3512527.3531421},
isbn = {9781450392389},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {Proceedings of the 2022 International Conference on Multimedia Retrieval},
pages = {661–667},
publisher = {Association for Computing Machinery},
address = {Newark, NJ, USA},
series = {ICMR '22},
abstract = {The spatiotemporal representation of task-based brain functional networks is a key topic in functional magnetic resonance image (fMRI) research. At present, deep learning has been more powerful and flexible in brain functional network research than traditional methods. However, the dominant deep learning models failed in capturing the long-distance dependency (LDD) in task-based fMRI images (tfMRI) due to the time correlation among different task stimuli, the nature between temporal and spatial dimensions, which resulting in inaccurate brain pattern extraction. To address this issue, this paper proposes a spatiotemporal attention neural architecture search (NAS) model for task-based brain functional networks representation (SA-NAS-BFNR), where attention mechanism and gate recurrent unit (GRU) are integrated into a novel framework and GRU structure is searched by the differentiable neural architecture search. This model can not only achieve meaningful brain functional networks (BFNs) by addressing the LDD, but also simplify the existing recurrent structure models in tfMRI. Experiments show that the proposed model is capable of improving the fitting ability between time series and task stimulus sequence, and extracting the BFNs effectively as well.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Chitty-Venkata, Krishna Teja; Emani, Murali; Vishwanath, Venkatram; Somani, Arun K.
Efficient Design Space Exploration for Sparse Mixed Precision Neural Architectures Proceedings Article
In: Proceedings of the 31st International Symposium on High-Performance Parallel and Distributed Computing, pp. 265–276, Association for Computing Machinery, Minneapolis, MN, USA, 2022, ISBN: 9781450391993.
@inproceedings{10.1145/3502181.3531463,
title = {Efficient Design Space Exploration for Sparse Mixed Precision Neural Architectures},
author = {Krishna Teja Chitty-Venkata and Murali Emani and Venkatram Vishwanath and Arun K. Somani},
url = {https://doi.org/10.1145/3502181.3531463},
doi = {10.1145/3502181.3531463},
isbn = {9781450391993},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {Proceedings of the 31st International Symposium on High-Performance Parallel and Distributed Computing},
pages = {265–276},
publisher = {Association for Computing Machinery},
address = {Minneapolis, MN, USA},
series = {HPDC '22},
abstract = {Pruning and Quantization are two effective Deep Neural Network (DNN) compression methods for efficient inference on various hardware platforms. Pruning refers to removing unimportant weights or nodes, whereas Quantization converts the floating-point parameters to low-bit fixed integer representation. The pruned and low precision models result in smaller and faster inference models on hardware platforms with almost the same accuracy as the unoptimized network. Tensor Cores in Nvidia Ampere 100 (A100) GPU supports (1) 2:4 fine-grained sparse pruning where 2 out of every 4 elements are pruned, and (2) traditional dense multiplication to achieve a good accuracy and performance trade-off. The A100 Tensor Core also takes advantage of 1-bit, 4-bit, and 8-bit multiplication to speed up the inference of a model. Hence, finding the right matrix type (dense or 2:4 sparse) along with the precision for each layer becomes a combinatorial problem. Neural Architecture Search (NAS) can alleviate such problems by automating the architecture design process instead of a brute-force search. In this paper, we propose (i) Mixed Sparse and Precision Search (MSPS), a NAS framework to search for efficient sparse and mixed-precision quantized model within the predefined search space and fixed backbone neural network (Eg. ResNet50), and (ii) Architecture, Sparse and Precision Search (ASPS) to jointly search for kernel size and number of filters, and sparse-precision combination of each layer. We illustrate the effectiveness of our methods targeting A100 Tensor Core on Nvidia GPUs by searching efficient sparse-mixed precision networks on ResNet50 and achieving better accuracy-latency trade-off models compared to the manually designed Uniform Sparse Int8 networks.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Gesmundo, Andrea; Dean, Jeff
muNet: Evolving Pretrained Deep Neural Networks into Scalable Auto-tuning Multitask Systems Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2205-10937,
title = {muNet: Evolving Pretrained Deep Neural Networks into Scalable Auto-tuning Multitask Systems},
author = {Andrea Gesmundo and Jeff Dean},
url = {https://doi.org/10.48550/arXiv.2205.10937},
doi = {10.48550/arXiv.2205.10937},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2205.10937},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Han, Zhu; Hong, Danfeng; Gao, Lianru; Zhang, Bing; Huang, Min; Chanussot, Jocelyn
AutoNAS: Automatic Neural Architecture Search for Hyperspectral Unmixing Journal Article
In: IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-14, 2022.
@article{9807268,
title = {AutoNAS: Automatic Neural Architecture Search for Hyperspectral Unmixing},
author = {Zhu Han and Danfeng Hong and Lianru Gao and Bing Zhang and Min Huang and Jocelyn Chanussot},
url = {https://ieeexplore.ieee.org/abstract/document/9807268},
doi = {10.1109/TGRS.2022.3186480},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
volume = {60},
pages = {1-14},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Seng, Jonas; Prasad, Pooja; Dhami, Devendra Singh; Kersting, Kristian
HANF: Hyperparameter And Neural Architecture Search in Federated Learning Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2206-12342,
title = {HANF: Hyperparameter And Neural Architecture Search in Federated Learning},
author = {Jonas Seng and Pooja Prasad and Devendra Singh Dhami and Kristian Kersting},
url = {https://doi.org/10.48550/arXiv.2206.12342},
doi = {10.48550/arXiv.2206.12342},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2206.12342},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Yu, Yanjiang; Zhang, Puyang; Zhang, Kaihao; Luo, Wenhan; Li, Changsheng; Yuan, Ye; Wang, Guoren
Multi-Prior Learning via Neural Architecture Search for Blind Face Restoration Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2206-13962,
title = {Multi-Prior Learning via Neural Architecture Search for Blind Face Restoration},
author = {Yanjiang Yu and Puyang Zhang and Kaihao Zhang and Wenhan Luo and Changsheng Li and Ye Yuan and Guoren Wang},
url = {https://doi.org/10.48550/arXiv.2206.13962},
doi = {10.48550/arXiv.2206.13962},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2206.13962},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Dong, Peijie; Niu, Xin; Li, Lujun; Xie, Linzhen; Zou, Wenbin; Ye, Tian; Wei, Zimian; Pan, Hengyue
Prior-Guided One-shot Neural Architecture Search Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2206-13329,
title = {Prior-Guided One-shot Neural Architecture Search},
author = {Peijie Dong and Xin Niu and Lujun Li and Linzhen Xie and Wenbin Zou and Tian Ye and Zimian Wei and Hengyue Pan},
url = {https://doi.org/10.48550/arXiv.2206.13329},
doi = {10.48550/arXiv.2206.13329},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2206.13329},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Benmeziane, Hadjer; Niar, Smail; Ouarnoughi, Hamza; Maghraoui, Kaoutar El
Pareto Rank Surrogate Model for Hardware-aware Neural Architecture Search Proceedings Article
In: 2022 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pp. 267-276, 2022.
@inproceedings{9804643,
title = {Pareto Rank Surrogate Model for Hardware-aware Neural Architecture Search},
author = {Hadjer Benmeziane and Smail Niar and Hamza Ouarnoughi and Kaoutar El Maghraoui},
doi = {10.1109/ISPASS55109.2022.00040},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {2022 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)},
pages = {267-276},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Wang, Tianzi; Deng, Jiajun; Geng, Mengzhe; Ye, Zi; Hu, Shoukang; Wang, Yi; Cui, Mingyu; Jin, Zengrui; Liu, Xunying; Meng, Helen
Conformer Based Elderly Speech Recognition System for Alzheimer's Disease Detection Journal Article
In: CoRR, vol. abs/2206.13232, 2022.
@article{DBLP:journals/corr/abs-2206-13232,
title = {Conformer Based Elderly Speech Recognition System for Alzheimer's Disease Detection},
author = {Tianzi Wang and Jiajun Deng and Mengzhe Geng and Zi Ye and Shoukang Hu and Yi Wang and Mingyu Cui and Zengrui Jin and Xunying Liu and Helen Meng},
url = {https://doi.org/10.48550/arXiv.2206.13232},
doi = {10.48550/arXiv.2206.13232},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2206.13232},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Shen, Junge; Cao, Bin; Zhang, Chi; Wang, Ruxin; Wang, Qi
Remote Sensing Scene Classification Based on Attention-Enabled Progressively Searching Journal Article
In: IEEE Transactions on Geoscience and Remote Sensing, pp. 1-1, 2022.
@article{9807377,
title = {Remote Sensing Scene Classification Based on Attention-Enabled Progressively Searching},
author = {Junge Shen and Bin Cao and Chi Zhang and Ruxin Wang and Qi Wang},
url = {https://ieeexplore.ieee.org/abstract/document/9807377},
doi = {10.1109/TGRS.2022.3186588},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Dahouda, Mwamba Kasongo; Joe, Inwhee
Neural Architecture Search Net-based Feature Extraction with Modular Neural Network for Image Classification of Copper/Cobalt Raw Minerals Journal Article
In: IEEE Access, pp. 1-1, 2022.
@article{9810927,
title = {Neural Architecture Search Net-based Feature Extraction with Modular Neural Network for Image Classification of Copper/Cobalt Raw Minerals},
author = {Mwamba Kasongo Dahouda and Inwhee Joe},
doi = {10.1109/ACCESS.2022.3187420},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {IEEE Access},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Lin, Zhiwei; Liang, Tingting; Xiao, Taihong; Wang, Yongtao; Tang, Zhi; Yang, Ming-Hsuan
FlowNAS: Neural Architecture Search for Optical Flow Estimation Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2207-01271,
title = {FlowNAS: Neural Architecture Search for Optical Flow Estimation},
author = {Zhiwei Lin and Tingting Liang and Taihong Xiao and Yongtao Wang and Zhi Tang and Ming-Hsuan Yang},
url = {https://doi.org/10.48550/arXiv.2207.01271},
doi = {10.48550/arXiv.2207.01271},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2207.01271},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Xie, Xiangning; Liu, Yuqiao; Sun, Yanan; Zhang, Mengjie; Tan, Kay Chen
Architecture Augmentation for Performance Predictor Based on Graph Isomorphism Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2207-00987,
title = {Architecture Augmentation for Performance Predictor Based on Graph Isomorphism},
author = {Xiangning Xie and Yuqiao Liu and Yanan Sun and Mengjie Zhang and Kay Chen Tan},
url = {https://doi.org/10.48550/arXiv.2207.00987},
doi = {10.48550/arXiv.2207.00987},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2207.00987},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Chen, Jingfan; Zhu, Guanghui; Hou, Haojun; Yuan, Chunfeng; Huang, Yihua
AutoGSR: Neural Architecture Search for Graph-Based Session Recommendation Proceedings Article
In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1694–1704, Association for Computing Machinery, Madrid, Spain, 2022, ISBN: 9781450387323.
@inproceedings{10.1145/3477495.3531940,
title = {AutoGSR: Neural Architecture Search for Graph-Based Session Recommendation},
author = {Jingfan Chen and Guanghui Zhu and Haojun Hou and Chunfeng Yuan and Yihua Huang},
url = {https://doi.org/10.1145/3477495.3531940},
doi = {10.1145/3477495.3531940},
isbn = {9781450387323},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval},
pages = {1694–1704},
publisher = {Association for Computing Machinery},
address = {Madrid, Spain},
series = {SIGIR '22},
abstract = {Session-based recommendation aims to predict next click action (e.g., item) of anonymous users based on a fixed number of previous actions. Recently, Graph Neural Networks (GNNs) have shown superior performance in various applications. Inspired by the success of GNNs, tremendous endeavors have been devoted to introduce GNNs into session-based recommendation and have achieved significant results. Nevertheless, due to the highly diverse types of potential information in sessions, existing GNNs-based methods perform differently on different session datasets, leading to the need for efficient design of neural networks adapted to various session recommendation scenarios. To address this problem, we propose Automated neural architecture search for Graph-based Session Recommendation, namely AutoGSR, a framework that provides a practical and general solution to automatically find the optimal GNNs-based session recommendation model. In AutoGSR, we propose two novel GNN operations to build an expressive and compact search space. Building upon the search space, we employ a differentiable search algorithm to search for the optimal graph neural architecture. Furthermore, to consider all types of session information together, we propose to learn the item meta knowledge, which acts as a priori knowledge for guiding the optimization of final session representations. Comprehensive experiments on three real-world datasets demonstrate that AutoGSR is able to find effective neural architectures and achieve state-of-the-art results. To the best of our knowledge, we are the first to study the neural architecture search for the session-based recommendation.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Singh, Anuraj; Nair, Haritha
A Neural Architecture Search for Automated Multimodal Learning Journal Article
In: Expert Systems with Applications, vol. 207, pp. 118051, 2022, ISSN: 0957-4174.
@article{SINGH2022118051,
title = {A Neural Architecture Search for Automated Multimodal Learning},
author = {Anuraj Singh and Haritha Nair},
url = {https://www.sciencedirect.com/science/article/pii/S0957417422012581},
doi = {https://doi.org/10.1016/j.eswa.2022.118051},
issn = {0957-4174},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {Expert Systems with Applications},
volume = {207},
pages = {118051},
abstract = {The boom of artificial intelligence in the past decade is owed to the research and development of deep learning and moreover, that of accessible deep learning. But the goal of Artificial General Intelligence (AGI) cannot be achieved by having application-specific, parameter sensitive neural networks that need to be defined and tuned for every use case. General intelligence also involves understanding different types of data, rather than having dedicated models for each functionality. Thus both automating machine learning while also giving importance to generalizing over multiple modalities has great potential to help move AGI research forward. We propose a generalizable algorithm-Multimodal Neural Architecture Search (MNAS) which can work on multiple modalities and perform architecture search in order to create neural networks that enable classification on multiple types of data for multiclass outputs. The work automates the development of a fusion architecture by building upon existing literature of multimodal learning and neural architecture search. The controller network which predicts the architecture has been designed such that it works on a reward model where the reward is dependent on accuracies of individual networks corresponding to each modality involved. The work shows good results with accuracy comparable to both unimodal classification on same data and manually created multimodal architectures wherein the experiments are performed on multiclass classification problem of image and text modalities. It also uses a shared parameter search graph ensuring that the computational complexity is less compared to several other neural architecture search algorithms.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Theodorakos, Konstantinos; Agudelo, Oscar Mauricio; Schreurs, Joachim; Suykens, Johan A. K.; Moor, Bart De
Island Transpeciation: A Co-Evolutionary Neural Architecture Search, applied to country-scale air-quality forecasting Journal Article
In: IEEE Transactions on Evolutionary Computation, pp. 1-1, 2022.
@article{9820773,
title = {Island Transpeciation: A Co-Evolutionary Neural Architecture Search, applied to country-scale air-quality forecasting},
author = {Konstantinos Theodorakos and Oscar Mauricio Agudelo and Joachim Schreurs and Johan A. K. Suykens and Bart De Moor},
url = {https://ieeexplore.ieee.org/abstract/document/9820773},
doi = {10.1109/TEVC.2022.3189500},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {IEEE Transactions on Evolutionary Computation},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Zhu, Guanghui; Cheng, Feng; Lian, Defu; Yuan, Chunfeng; Huang, Yihua
NAS-CTR: Efficient Neural Architecture Search for Click-Through Rate Prediction Proceedings Article
In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 332–342, Association for Computing Machinery, Madrid, Spain, 2022, ISBN: 9781450387323.
@inproceedings{10.1145/3477495.3532030,
title = {NAS-CTR: Efficient Neural Architecture Search for Click-Through Rate Prediction},
author = {Guanghui Zhu and Feng Cheng and Defu Lian and Chunfeng Yuan and Yihua Huang},
url = {https://doi.org/10.1145/3477495.3532030},
doi = {10.1145/3477495.3532030},
isbn = {9781450387323},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval},
pages = {332–342},
publisher = {Association for Computing Machinery},
address = {Madrid, Spain},
series = {SIGIR '22},
abstract = {Click-Through Rate (CTR) prediction has been widely used in many machine learning tasks such as online advertising and personalization recommendation. Unfortunately, given a domain-specific dataset, searching effective feature interaction operations and combinations from a huge candidate space requires significant expert experience and computational costs. Recently, Neural Architecture Search (NAS) has achieved great success in discovering high-quality network architectures automatically. However, due to the diversity of feature interaction operations and combinations, the existing NAS-based work that treats the architecture search as a black-box optimization problem over a discrete search space suffers from low efficiency. Therefore, it is essential to explore a more efficient architecture search method. To achieve this goal, we propose NAS-CTR, a differentiable neural architecture search approach for CTR prediction. First, we design a novel and expressive architecture search space and a continuous relaxation scheme to make the search space differentiable. Second, we formulate the architecture search for CTR prediction as a joint optimization problem with discrete constraints on architectures and leverage proximal iteration to solve the constrained optimization problem. Additionally, a straightforward yet effective method is proposed to eliminate the aggregation of skip connections. Extensive experimental results reveal that NAS-CTR can outperform the SOTA human-crafted architectures and other NAS-based methods in both test accuracy and search efficiency.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Luo, Xiangzhong; Liu, Di; Kong, Hao; Huai, Shuo; Chen, Hui; Liu, Weichen
SurgeNAS: A Comprehensive Surgery on Hardware-Aware Differentiable Neural Architecture Search Journal Article
In: IEEE Transactions on Computers, pp. 1-14, 2022.
@article{9817049,
title = {SurgeNAS: A Comprehensive Surgery on Hardware-Aware Differentiable Neural Architecture Search},
author = {Xiangzhong Luo and Di Liu and Hao Kong and Shuo Huai and Hui Chen and Weichen Liu},
url = {https://ieeexplore.ieee.org/abstract/document/9817049},
doi = {10.1109/TC.2022.3188175},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {IEEE Transactions on Computers},
pages = {1-14},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Cai, Lei; Fu, Yuli; Huo, Wanliang; Xiang, Youjun; Zhu, Tao; Zhang, Ying; Zeng, Huanqiang
Multi-scale Attentive Image De-raining Networks via Neural Architecture Search Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2207-00728,
title = {Multi-scale Attentive Image De-raining Networks via Neural Architecture Search},
author = {Lei Cai and Yuli Fu and Wanliang Huo and Youjun Xiang and Tao Zhu and Ying Zhang and Huanqiang Zeng},
url = {https://doi.org/10.48550/arXiv.2207.00728},
doi = {10.48550/arXiv.2207.00728},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2207.00728},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Sun, Xuewei; Li, Guohou; Qu, Peixin; Xie, Xiwang; Pan, Xipeng; Zhang, Weidong
Research on plant disease identification based on CNN Journal Article
In: Cognitive Robotics, 2022, ISSN: 2667-2413.
@article{SUN2022,
title = {Research on plant disease identification based on CNN},
author = {Xuewei Sun and Guohou Li and Peixin Qu and Xiwang Xie and Xipeng Pan and Weidong Zhang},
url = {https://www.sciencedirect.com/science/article/pii/S2667241322000143},
doi = {https://doi.org/10.1016/j.cogr.2022.07.001},
issn = {2667-2413},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {Cognitive Robotics},
abstract = {Traditional digital image processing methods extract disease features manually, which have low efficiency and low recognition accuracy. To solve this problem, In this paper, we propose a convolutional neural network architecture FL-EfficientNet (Focal loss EfficientNet), which is used for multi-category identification of plant disease images. Firstly, through the Neural Architecture Search technology, the network width, network depth, and image resolution are adaptively adjusted according to a group of composite coefficients, to improve the balance of network dimension and model stability; Secondly, the valuable features in the disease image are extracted by introducing the moving flip bottleneck convolution and attention mechanism; Finally, the Focal loss function is used to replace the traditional Cross-Entropy loss function, to improve the ability of the network model to focus on the samples that are not easy to identify. The experiment uses the public data set new plant diseases dataset (NPDD) and compares it with ResNet50, DenseNet169, and EfficientNet. The experimental results show that the accuracy of FL-EfficientNet in identifying 10 diseases of 5 kinds of crops is 99.72%, which is better than the above comparison network. At the same time, FL-EfficientNet has the fastest convergence speed, and the training time of 15 epochs is 4.7 h.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Zhang, Wentao; Lin, Zheyu; Shen, Yu; Li, Yang; Yang, Zhi; Cui, Bin
DFG-NAS: Deep and Flexible Graph Neural Architecture Search Proceedings Article
In: Proceedings of the 39th International Conference on MachineLearning, 2022.
@inproceedings{DBLP:journals/corr/abs-2206-08582b,
title = {DFG-NAS: Deep and Flexible Graph Neural Architecture Search},
author = {Wentao Zhang and Zheyu Lin and Yu Shen and Yang Li and Zhi Yang and Bin Cui},
url = {https://proceedings.mlr.press/v162/zhang22s/zhang22s.pdf},
doi = {10.48550/arXiv.2206.08582},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {Proceedings of the 39th International Conference on MachineLearning},
journal = {CoRR},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Sun, Zihao; Hu, Yu; Lu, Shun; Yang, Longxing; Mei, Jilin; Han, Yinhe; Li, Xiaowei
AGNAS: Attention-Guided Micro and Macro-Architecture Search Proceedings Article
In: Chaudhuri, Kamalika; Jegelka, Stefanie; Song, Le; Szepesvári, Csaba; Niu, Gang; Sabato, Sivan (Ed.): International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, pp. 20777–20789, PMLR, 2022.
@inproceedings{DBLP:conf/icml/Sun0LYMHL22,
title = {AGNAS: Attention-Guided Micro and Macro-Architecture Search},
author = {Zihao Sun and Yu Hu and Shun Lu and Longxing Yang and Jilin Mei and Yinhe Han and Xiaowei Li},
editor = {Kamalika Chaudhuri and Stefanie Jegelka and Le Song and Csaba Szepesvári and Gang Niu and Sivan Sabato},
url = {https://proceedings.mlr.press/v162/sun22a.html},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {International Conference on Machine Learning, ICML 2022, 17-23 July
2022, Baltimore, Maryland, USA},
volume = {162},
pages = {20777--20789},
publisher = {PMLR},
series = {Proceedings of Machine Learning Research},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Greenwood, Bryson; McDonnell, Tyler
Surrogate-Assisted Neuroevolution Proceedings Article
In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 1048–1056, Association for Computing Machinery, Boston, Massachusetts, 2022, ISBN: 9781450392372.
@inproceedings{10.1145/3512290.3528703,
title = {Surrogate-Assisted Neuroevolution},
author = {Bryson Greenwood and Tyler McDonnell},
url = {https://doi.org/10.1145/3512290.3528703},
doi = {10.1145/3512290.3528703},
isbn = {9781450392372},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference},
pages = {1048–1056},
publisher = {Association for Computing Machinery},
address = {Boston, Massachusetts},
series = {GECCO '22},
abstract = {Though Neuroevolution (NE) and Neural Architecture Search (NAS) have emerged as techniques for automating the design of neural networks, they are expensive and time consuming: they require training many neural networks and have largely resisted the benefits of surrogate-based optimization approaches, as it is difficult to model the performance of variable network architectures. We propose a novel and general framework for surrogate-assisted search of neural architectures consisting of two components: (1) an algorithm which leverages grammars to generate tensor representations of variable neural network topologies; and an evolutionary algorithm which employs a surrogate model to expedite architecture search using active learning. We demonstrate that our model can produce accurate performance predictions for unseen architectures, realizing a 5x reduction in the total compute required for search while improving asymptotic performance. We also illustrate that the surrogate models are transferable to new domains via a real-world transfer learning case study using industrial time series data.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Yang, Longxing; Hu, Yu; Lu, Shun; Sun, Zihao; Mei, Jilin; Han, Yinhe; Li, Xiaowei
Searching for BurgerFormer with Micro-Meso-Macro Space Design Proceedings Article
In: Chaudhuri, Kamalika; Jegelka, Stefanie; Song, Le; Szepesvári, Csaba; Niu, Gang; Sabato, Sivan (Ed.): International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, pp. 25055–25069, PMLR, 2022.
@inproceedings{DBLP:conf/icml/Yang0LSMHL22,
title = {Searching for BurgerFormer with Micro-Meso-Macro Space Design},
author = {Longxing Yang and Yu Hu and Shun Lu and Zihao Sun and Jilin Mei and Yinhe Han and Xiaowei Li},
editor = {Kamalika Chaudhuri and Stefanie Jegelka and Le Song and Csaba Szepesvári and Gang Niu and Sivan Sabato},
url = {https://proceedings.mlr.press/v162/yang22f.html},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {International Conference on Machine Learning, ICML 2022, 17-23 July
2022, Baltimore, Maryland, USA},
volume = {162},
pages = {25055--25069},
publisher = {PMLR},
series = {Proceedings of Machine Learning Research},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Wu, Yanling; Tang, Baoping; Deng, Lei; Li, Qikang
Distillation-enhanced fast neural architecture search method for edge-side fault diagnosis of wind turbine gearboxes Journal Article
In: Expert Systems with Applications, vol. 208, pp. 118049, 2022, ISSN: 0957-4174.
@article{WU2022118049,
title = {Distillation-enhanced fast neural architecture search method for edge-side fault diagnosis of wind turbine gearboxes},
author = {Yanling Wu and Baoping Tang and Lei Deng and Qikang Li},
url = {https://www.sciencedirect.com/science/article/pii/S0957417422012593},
doi = {https://doi.org/10.1016/j.eswa.2022.118049},
issn = {0957-4174},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {Expert Systems with Applications},
volume = {208},
pages = {118049},
abstract = {Deep learning methods have been widely applied for fault diagnosis of wind turbine gearboxes. However, a new model requires experts to be empirically handcrafted, which is time consuming and labor-intensive. In addition, excessive attention is paid to diagnostic accuracy, and manual models often have high complexity, making their deployment in edge devices difficult. Accordingly, a novel method based on a distillation-enhanced fast neural architecture search is proposed for edge-side fault diagnosis of wind turbine gearboxes. First, a multibranch parallel fast neural architecture search framework is designed to build diagnosis models quickly and automatically. Meanwhile, an automatic distillation technology is proposed to empower the fast neural architecture search framework so that the searched model can achieve a balance between lightweight and high diagnostic accuracy to meet the lightweight deployment requirements for edge devices. The feasibility and effectiveness of the proposed method were verified using a gearbox dataset from a drivetrain diagnostics simulator (DDS) and measured data from a wind farm.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Sapkota, Suman; Bhattarai, Binod
Noisy Heuristics NAS: A Network Morphism based Neural Architecture Search using Heuristics Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2207-04467,
title = {Noisy Heuristics NAS: A Network Morphism based Neural Architecture Search using Heuristics},
author = {Suman Sapkota and Binod Bhattarai},
url = {https://doi.org/10.48550/arXiv.2207.04467},
doi = {10.48550/arXiv.2207.04467},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2207.04467},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Garcia-Garcia, Cosijopii; Escalante, Hugo Jair; Morales-Reyes, Alicia
CGP-NAS: Real-based solutions encoding for multi-objective evolutionary neural architecture search Proceedings Article
In: GECCO 2022, 2022.
@inproceedings{garcia2022cgp,
title = {CGP-NAS: Real-based solutions encoding for multi-objective evolutionary neural architecture search},
author = {Cosijopii Garcia-Garcia and Hugo Jair Escalante and Alicia Morales-Reyes},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {GECCO 2022},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Rodrigues, Nuno M.; Malan, Katherine M.; Ochoa, Gabriela; Vanneschi, Leonardo; Silva, Sara
Fitness landscape analysis of convolutional neural network architectures for image classification Journal Article
In: Information Sciences, 2022, ISSN: 0020-0255.
@article{RODRIGUES2022,
title = {Fitness landscape analysis of convolutional neural network architectures for image classification},
author = {Nuno M. Rodrigues and Katherine M. Malan and Gabriela Ochoa and Leonardo Vanneschi and Sara Silva},
url = {https://www.sciencedirect.com/science/article/pii/S0020025522007290},
doi = {https://doi.org/10.1016/j.ins.2022.07.040},
issn = {0020-0255},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {Information Sciences},
abstract = {The global structure of the hyperparameter spaces of neural networks is not well understood and it is therefore not clear which hyperparameter search algorithm will be most effective. In this paper we analyze the landscapes of convolutional neural network architecture search spaces to provide insight into appropriate search algorithms for these spaces. Using a classical fitness landscape analysis approach (fitness distance correlation) and a more recent tool (local optima networks) we study the global structure of these spaces. Our analysis on six image classification datasets reveals that the landscapes are multi-modal, but with relatively few local optima from which it is not hard to escape with a simple perturbation operator. This led us to explore the performance of iterated local search, which we found to more effectively search the training landscapes than three evolutionary algorithm variants. Evolutionary algorithms, however, outperformed iterated local search in terms of generalization on problems with larger discrepancies between the training and testing landscapes.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
You, Haoran; Li, Baopu; Sun, Zhanyi; Ouyang, Xu; Lin, Yingyan
SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning Proceedings Article
In: ECCV 2022, 2022.
@inproceedings{DBLP:journals/corr/abs-2207-03677,
title = {SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning},
author = {Haoran You and Baopu Li and Zhanyi Sun and Xu Ouyang and Yingyan Lin},
url = {https://doi.org/10.48550/arXiv.2207.03677},
doi = {10.48550/arXiv.2207.03677},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {ECCV 2022},
journal = {CoRR},
volume = {abs/2207.03677},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Liu, Li; Cai, Xing; Li, Ge; Li, Thomas H
DKNAS: A Practical Deep Keypoint Extraction Framework Based on Neural Architecture Search Proceedings Article
In: 2022 International Conference on Robotics and Automation (ICRA), pp. 5643-5649, 2022.
@inproceedings{9812101,
title = {DKNAS: A Practical Deep Keypoint Extraction Framework Based on Neural Architecture Search},
author = {Li Liu and Xing Cai and Ge Li and Thomas H Li},
url = {https://ieeexplore.ieee.org/abstract/document/9812101},
doi = {10.1109/ICRA46639.2022.9812101},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {2022 International Conference on Robotics and Automation (ICRA)},
pages = {5643-5649},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
You, Haoran; Li, Baopu; Sun, Zhanyi; Ouyang, Xu; Lin, Yingyan
SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2207-03677b,
title = {SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning},
author = {Haoran You and Baopu Li and Zhanyi Sun and Xu Ouyang and Yingyan Lin},
url = {https://doi.org/10.48550/arXiv.2207.03677},
doi = {10.48550/arXiv.2207.03677},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2207.03677},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Shen, Haozhe; Li, Wenjun; Li, Yilin; Yue, Keqiang; Li, Ruixue; Li, Yuhang
Research on Compression of Teacher Guidance Network Use Global Differential Computing Neural Architecture Search Proceedings Article
In: 2022 5th International Conference on Artificial Intelligence and Big Data (ICAIBD), pp. 526-531, 2022.
@inproceedings{9820338,
title = {Research on Compression of Teacher Guidance Network Use Global Differential Computing Neural Architecture Search},
author = {Haozhe Shen and Wenjun Li and Yilin Li and Keqiang Yue and Ruixue Li and Yuhang Li},
url = {https://ieeexplore.ieee.org/abstract/document/9820338},
doi = {10.1109/ICAIBD55127.2022.9820338},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {2022 5th International Conference on Artificial Intelligence and Big Data (ICAIBD)},
pages = {526-531},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Cavagnero, Niccolò; Robbiano, Luca; Caputo, Barbara; Averta, Giuseppe
FreeREA: Training-Free Evolution-based Architecture Search Technical Report
2022.
@techreport{DBLP:journals/corr/abs-2207-05135,
title = {FreeREA: Training-Free Evolution-based Architecture Search},
author = {Niccolò Cavagnero and Luca Robbiano and Barbara Caputo and Giuseppe Averta},
url = {https://doi.org/10.48550/arXiv.2207.05135},
doi = {10.48550/arXiv.2207.05135},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2207.05135},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}