AutoML.org

Freiburg-Hannover-Tübingen

Literature on Neural Architecture Search

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.

3282 entries « ‹ 46 of 66 › »

2021

1032.

Li, Xiaobin; Jiang, Hongxu; Tian, Fangzheng; Zhang, Yonghua; Miao, Rui; Xu, Donghuan

Optimal FPGA-oriented lightweight network architecture search under multi-objective constraints Proceedings Article

In: 2021 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom), New York City, NY, USA, September 30 - Oct. 3, 2021, pp. 978–983, IEEE, 2021.

1031.

Huang, Zhenhan; Jiang, Chunheng; Chen, Pin-Yu; Gao, Jianxi

Network Graph Based Neural Architecture Search Technical Report

2021.

1030.

Carmichael, Zachariah; Moon, Tim; Jacobs, Sam Ade

Learning Interpretable Models Through Multi-Objective Neural Architecture Search Technical Report

2021.

1029.

Kuang, Huiyu

M-FasterSeg: An Efficient Semantic Segmentation Network Based on Neural Architecture Search Technical Report

2021.

1028.

Kung, Chi-Hsi; Lee, Che-Rung

ADD: A Fine-grained Dynamic Inference Architecture for Semantic Image Segmentation Proceedings Article

In: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4792-4799, 2021.

1027.

Peng, Cheng; Myronenko, Andriy; Hatamizadeh, Ali; Nath, Vishwesh; Siddiquee, Md Mahfuzur Rahman; He, Yufan; Xu, Daguang; Chellappa, Rama; Yang, Dong

HyperSegNAS: Bridging One-Shot Neural Architecture Search with 3D Medical Image Segmentation using HyperNet Technical Report

2021.

1026.

Dong, Xuanyi; Kedziora, David Jacob; Musial, Katarzyna; Gabrys, Bogdan

Automated Deep Learning: Neural Architecture Search Is Not the End Technical Report

2021.

1025.

Shi, Xian; Zhou, Pan; Chen, Wei; Xie, Lei

Efficient Gradient-Based Neural Architecture Search For End-to-End ASR Proceedings Article

In: Companion Publication of the 2021 International Conference on Multimodal Interaction, pp. 91–96, Association for Computing Machinery, Montreal, QC, Canada, 2021, ISBN: 9781450384711.

Abstract | Links | BibTeX

1024.

Muñoz, J. Pablo; Lyalyushkin, Nikolay; Akhauri, Yash; Senina, Anastasia; Kozlov, Alexander; Jain, Nilesh

Enabling NAS with Automated Super-Network Generation Technical Report

2021.

1023.

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

AutoCTS: Automated Correlated Time Series Forecasting - Extended Version Technical Report

2021.

1022.

Khan, Tariq Mahmood; Naqvi, Syed Saud; Meijering, Erik

Leveraging Image Complexity in Macro-Level Neural Network Design for Medical Image Segmentation Technical Report

2021.

1021.

Zhang, Zhida; Huang, Peng; Mao, Xiangyu; Sun, Yongwen; Liu, Yang; Shao, Huiqin

Surface defect detection method based on neural architecture search Proceedings Article

In: 2021 IEEE 3rd International Conference on Frontiers Technology of Information and Computer (ICFTIC), pp. 612-617, 2021.

1020.

Luo, Ziyuan; Nguyen, Minh; Yan, Wei Qi

Sailboat Detection Based on Automated Search Attention Mechanism and Deep Learning Models Proceedings Article

In: 2021 36th International Conference on Image and Vision Computing New Zealand (IVCNZ), pp. 1-6, 2021.

1019.

Wu, Robert (Rupert); Jain, Rohan

QENAS: Q-Learning for Efficient Neural Architecture Search Technical Report

2021.

1018.

Wei, Lanning; Zhao, Huan; He, Zhiqiang

Learn Layer-wise Connections in Graph Neural Networks Technical Report

2021.

1017.

Wang, I Sheng; Chan, Hung-Tse; Hsia, Chih-Hsien

Finger-Vein Recognition Using a NASNet with a Cutout Proceedings Article

In: 2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), pp. 1-2, 2021.

1016.

Fil, Miroslav; Ru, Binxin; Lyle, Clare; Gal, Yarin

DARTS without a Validation Set: Optimizing the Marginal Likelihood Technical Report

2021.

1015.

Xia, Xin; Xiao, Xuefeng; Wang, Xing; Zheng, Min

Progressive Automatic Design of Search Space for One-Shot Neural Architecture Search Proceedings Article

In: WACV2022, 2021.

1014.

Mushtaq, Erum; He, Chaoyang; Ding, Jie; Avestimehr, Salman

SPIDER: Searching Personalized Neural Architecture for Federated Learning Technical Report

2021.

1013.

Wei, Lanning; Zhao, Huan; He, Zhiqiang

Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective Technical Report

2021.

1012.

Wang, Zhaolei; Zhang, Jun; Li, Yue; Gong, Qinghai; Luo, Wuyi; Zhao, Jikang

Automated Reinforcement Learning Based on Parameter Sharing Network Architecture Search Proceedings Article

In: 2021 6th International Conference on Robotics and Automation Engineering (ICRAE), pp. 358-363, 2021.

1011.

Xu, Shuying; Quan, Hongyan

ECT-NAS: Searching Efficient CNN-Transformers Architecture for Medical Image Segmentation Proceedings Article

In: 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 1601-1604, 2021.

1010.

Kulbach, Cedric; Thoma, Steffen

Personalized Neural Architecture Search Proceedings Article

In: 2021 International Conference on Data Mining Workshops (ICDMW), pp. 581-590, 2021.

1009.

Termritthikun, Chakkrit; Xu, Lin; Liu, Yemeng; Lee, Ivan

Neural Architecture Search and Multi-Objective Evolutionary Algorithms for Anomaly Detection Proceedings Article

In: 2021 International Conference on Data Mining Workshops (ICDMW), pp. 1001-1008, 2021.

1008.

Fu, Jun; Hou, Chen; Chen, Zhibo

AutoDerain: Memory-efficient Neural Architecture Search for Image Deraining Proceedings Article

In: 2021 International Conference on Visual Communications and Image Processing (VCIP), pp. 1-5, 2021.

1007.

Xuanhui, Dai; Juan, Chen; Quan, Wen

Network Pruning Based On Architecture Search and Intermediate Representation Proceedings Article

In: 2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), pp. 230-233, 2021.

1006.

Zhang, Jiuling; Ding, Zhiming

Robustifying DARTS by Eliminating Information Bypass Leakage via Explicit Sparse Regularization Proceedings Article

In: 2021 IEEE International Conference on Data Mining (ICDM), pp. 877-885, 2021.

1005.

Ravishankar, Anand; Natarajan, Santhi; Malakreddy, A Bharathi

Pruned Genetic-NAS on GPU Accelerator Platforms with Chaos-on-Edge Hyperparameters Proceedings Article

In: 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 958-963, 2021.

1004.

Hasan, Noha W.; Saudi, Ali S.; Khalil, Mahmoud I.; Abbas, Hazem M.

E-DARTS: Enhanced Differentiable Architecture Search for Acoustic Scene Classification Proceedings Article

In: 2021 16th International Conference on Computer Engineering and Systems (ICCES), pp. 1-6, 2021.

1003.

Zhang, Feifei; Ge, Jidong; Wong, Chifong; Zhang, Sheng; Li, Chuanyi; Luo, Bin

Optimizing Federated Edge Learning on Non-IID Data via Neural Architecture Search Proceedings Article

In: 2021 IEEE Global Communications Conference (GLOBECOM), pp. 1-6, 2021.

1002.

Salam, Hanan; Celiktutan, Oya; Mukherjee, Himadri; Manoranjan, Viswonathan; Ismail, Iman

Fact sheet: Automatic self-reported personality recognition Track Proceedings Article

In: ICCV 2021 Understanding Social Behavior in Dyadic and Small Group Interactions Challenge, 2021.

Abstract | Links | BibTeX

@inproceedings{8bd8f43c88834128b77c4707d609d8b8,

title = {Fact sheet: Automatic self-reported personality recognition Track},

author = {Hanan Salam and Oya Celiktutan and Himadri Mukherjee and Viswonathan Manoranjan and Iman Ismail},

url = {https://nyuscholars.nyu.edu/en/publications/fact-sheet-automatic-self-reported-personality-recognition-track},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

booktitle = {ICCV 2021 Understanding Social Behavior in Dyadic and Small Group Interactions Challenge},

abstract = {Smart phones, voice assistants, and home robots are becoming more intelligent every day to support humans in their daily routines and tasks. Achieving the user acceptance and success of such technologies makes it necessary for them to be socially informed, responsive, and responsible. They need to understand human behaviour and socio-emotional states and adapt themselves to their user’s profiles (eg, personality) and preferences. Motivated by this, there has been a significant effort in recognising personality from multimodal data in the last decade [1],[2]. However, to the best of our knowledge, the methods so far have focused on one-fits-all approaches only and performed personality recognition without taking into consideration the user’s profiles (eg, gender and age). In this paper, we took a different approach, and we argued that one-fits-all approach does not work sufficiently for personality recognition as previous research showed that there are significant gender differences in personality traits. For example, women tend to report higher scores for extraversion, agreeableness and neuroticsm as compared to men [3]. Building upon these findings, we first clustered the participants into two profiles based on their gender, namely, female and male, and then used Neural Architecture Search (NAS) to automatically design a model for each profile to recognise personality. A separate network was designed and trained with visual and text features. The final prediction was obtained by aggregating the results of both video and text modalities. Figure 1 presents the overview of our proposed approach.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

1001.

Phan, Quan Minh; Luong, Ngoc Hoang

Efficiency Enhancement of Evolutionary Neural Architecture Search via Training-Free Initialization Proceedings Article

In: 2021 8th NAFOSTED Conference on Information and Computer Science (NICS), pp. 138-143, 2021.

1000.

Wang, Zhehui; Luo, Tao; Li, Miqing; Zhou, Joey Tianyi; Goh, Rick Siow Mong; Zhen, Liangli

Evolutionary Multi-Objective Model Compression for Deep Neural Networks Journal Article

In: IEEE Computational Intelligence Magazine, vol. 16, no. 3, pp. 10-21, 2021.

999.

Soni, Ashutosh; Patidar, Tushar; M, Rajesh Kumar; P, Bharath K; S, Balaji; Rajendran, Rajkamal

Iris Recognition using Hough Transform and Neural Architecture Search Network Proceedings Article

In: 2021 Innovations in Power and Advanced Computing Technologies (i-PACT), pp. 1-5, 2021.

998.

Wu, Xuan; Zhang, Xiuyi; Jia, Linhan; Chen, Liang; Liang, Yanchun; Zhou, You; Wu, Chunguo

Neural Architecture Search based on Cartesian Genetic Programming Coding Method Journal Article

In: Neural and Evolutionary Computing, 2021.

997.

Waqas, Asim; Rasool, Ghulam; Farooq, Hamza; Bouaynaya, Nidhal C.

Exploring Robustness of Neural Networks through Graph Measures Technical Report

2021.

996.

Saxena, Nayan; Wu, Robert; Jain, Rohan

Towards One Shot Search Space Poisoning in Neural Architecture Search Technical Report

2021.

995.

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

AutoCTS: Automated Correlated Time Series Forecasting Journal Article

In: Proc. VLDB Endow., vol. 15, no. 4, pp. 971–983, 2021.

994.

Tang, Shiyu; Gong, Ruihao; Wang, Yan; Liu, Aishan; Wang, Jiakai; Chen, Xinyun; Yu, Fengwei; Liu, Xianglong; Song, Dawn; Yuille, Alan L.; Torr, Philip H. S.; Tao, Dacheng

RobustART: Benchmarking Robustness on Architecture Design and Training Techniques Technical Report

2021.

993.

Salinas, Nelly Rosaura Palacios; Baratchi, Mitra; Rijn, Jan N.; Vollrath, Andreas

Automated Machine Learning for Satellite Data: Integrating Remote Sensing Pre-trained Models into AutoML Systems Proceedings Article

In: Dong, Yuxiao; Kourtellis, Nicolas; Hammer, Barbara; Lozano, José Antonio (Ed.): Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track - European Conference, ECML PKDD 2021, Bilbao, Spain, September 13-17, 2021, Proceedings, Part V, pp. 447–462, Springer, 2021.

992.

Lyu, Fuyuan; Tang, Xing; Guo, Huifeng; Tang, Ruiming; He, Xiuqiang; Zhang, Rui; Liu, Xue

Memorize, Factorize, or be Na$backslash$ Technical Report

2021.

991.

Zhang, Lijun; Liu, Xiao; Guan, Hui

AutoMTL: A Programming Framework for Automated Multi-Task Learning Proceedings Article

In: NeurIPS 2022, 2021.

990.

Schiessler, Elisabeth J.; Aydin, Roland C.; Linka, Kevin; Cyron, Christian J.

Neural network surgery: Combining training with topology optimization Journal Article

In: Neural Networks, vol. 144, pp. 384-393, 2021, ISSN: 0893-6080.

Abstract | Links | BibTeX

@article{SCHIESSLER2021384,

title = {Neural network surgery: Combining training with topology optimization},

author = {Elisabeth J. Schiessler and Roland C. Aydin and Kevin Linka and Christian J. Cyron},

url = {https://www.sciencedirect.com/science/article/pii/S0893608021003476},

doi = {https://doi.org/10.1016/j.neunet.2021.08.034},

issn = {0893-6080},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {Neural Networks},

volume = {144},

pages = {384-393},

abstract = {With ever increasing computational capacities, neural networks become more and more proficient at solving complex tasks. However, picking a sufficiently good network topology usually relies on expert human knowledge. Neural architecture search aims to reduce the extent of expertise that is needed. Modern architecture search techniques often rely on immense computational power, or apply trained meta-controllers for decision making. We develop a framework for a genetic algorithm that is both computationally cheap and makes decisions based on mathematical criteria rather than trained parameters. It is a hybrid approach that fuses training and topology optimization together into one process. Structural modifications that are performed include adding or removing layers of neurons, with some re-training applied to make up for any incurred change in input–output behaviour. Our ansatz is tested on several benchmark datasets with limited computational overhead compared to training only the baseline. This algorithm can achieve a significant increase in accuracy (as compared to a fully trained baseline), rescue insufficient topologies that in their current state are only able to learn to a limited extent, and dynamically reduce network size without loss in achieved accuracy. On standard ML datasets, accuracy improvements compared to baseline performance can range from 20% for well performing starting topologies to more than 40% in case of insufficient baselines, or reduce network size by almost 15%.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

2020

989.

Hu, Mentao; Liu, Li; Wang, Wei; Liu, Yao

APENAS: An Asynchronous Parallel Evolution Based Multi-objective Neural Architecture Search Proceedings Article

In: 2020 IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA), 2020.

988.

Sadiq, Sulaiman; Maji, Partha; Hare, Jonathon; Merrett, Geoff

DEff-ARTS: differentiable efficient ARchiTecture search Technical Report

2020.

987.

Borrego-Carazo, J; Castells-Rufas, D; Carrabina, J; Biempica, E

Extending SpArSe: Automatic Gesture Recognition Architectures for Embedded Devices Proceedings Article

In: 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 7-12, 2020.

Abstract | Links | BibTeX

986.

Liu, Hao; Li, Dong; Peng, JinZhang; Zhao, Qingjie; Tian, Lu; Shan, Yi

MTNAS: Search Multi-Task Networks for Autonomous Driving Technical Report

2020.

985.

Miriyala, Srinivas Soumitri; Banerjee, Raja; Mitra, Kishalay

Uncertainty quantification using Auto-tuned Surrogates of CFD model Simulating Supersonic flow over tactical missile body Proceedings Article

In: pp. 2885-2892, 2020.

984.

Miriyala, Srinivas Soumitri; Chowdhury, Subhankar; Pujari, NagaSree Keerthi; Mitra, Kishalay

Optimally designed Variational Autoencoders for Efficient Wind Characteristics Modelling Proceedings Article

In: pp. 2869-2876, 2020.

983.

Garciarena, Unai; Santana, Roberto; Mendiburu, Alexander

EvoFlow - A Python library for evolving deep neural network architectures in tensorflow Proceedings Article

In: pp. 2288-2295, 2020.

3282 entries « ‹ 46 of 66 › »