Towards a configurable and non-hierarchical search space for NAS
Neural Architecture Search (NAS) outperforms handcrafted Neural Network (NN) design. However, current NAS methods generally use hard-coded search spaces, and predefined hierarchical architectures. As a consequence, adapting them to a new problem can be cumbersome, and it is hard to know which of the...
Saved in:
| Published in: | Neural networks Vol. 180; p. 106700 |
|---|---|
| Main Authors: | , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
United States
Elsevier Ltd
01.12.2024
|
| Subjects: | |
| ISSN: | 0893-6080, 1879-2782, 1879-2782 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Neural Architecture Search (NAS) outperforms handcrafted Neural Network (NN) design. However, current NAS methods generally use hard-coded search spaces, and predefined hierarchical architectures. As a consequence, adapting them to a new problem can be cumbersome, and it is hard to know which of the NAS algorithm or the predefined hierarchical structure impacts performance the most. To improve flexibility, and be less reliant on expert knowledge, this paper proposes a NAS methodology in which the search space is easily customizable, and allows for full network search. NAS is performed with Gaussian Process (GP)-based Bayesian Optimization (BO) in a continuous architecture embedding space. This embedding is built upon a Wasserstein Autoencoder, regularized by both a Maximum Mean Discrepancy (MMD) penalization and a Fully Input Convex Neural Network (FICNN) latent predictor, trained to infer the parameter count of architectures. This paper first assesses the embedding’s suitability for optimization by solving 2 computationally inexpensive problems: minimizing the number of parameters, and maximizing a zero-shot accuracy proxy. Then, two variants of complexity-aware NAS are performed on CIFAR-10 and STL-10, based on two different search spaces, providing competitive NN architectures with limited model sizes. |
|---|---|
| AbstractList | Neural Architecture Search (NAS) outperforms handcrafted Neural Network (NN) design. However, current NAS methods generally use hard-coded search spaces, and predefined hierarchical architectures. As a consequence, adapting them to a new problem can be cumbersome, and it is hard to know which of the NAS algorithm or the predefined hierarchical structure impacts performance the most. To improve flexibility, and be less reliant on expert knowledge, this paper proposes a NAS methodology in which the search space is easily customizable, and allows for full network search. NAS is performed with Gaussian Process (GP)-based Bayesian Optimization (BO) in a continuous architecture embedding space. This embedding is built upon a Wasserstein Autoencoder, regularized by both a Maximum Mean Discrepancy (MMD) penalization and a Fully Input Convex Neural Network (FICNN) latent predictor, trained to infer the parameter count of architectures. This paper first assesses the embedding's suitability for optimization by solving 2 computationally inexpensive problems: minimizing the number of parameters, and maximizing a zero-shot accuracy proxy. Then, two variants of complexity-aware NAS are performed on CIFAR-10 and STL-10, based on two different search spaces, providing competitive NN architectures with limited model sizes. Neural Architecture Search (NAS) outperforms handcrafted Neural Network (NN) design. However, current NAS methods generally use hard-coded search spaces, and predefined hierarchical architectures. As a consequence, adapting them to a new problem can be cumbersome, and it is hard to know which of the NAS algorithm or the predefined hierarchical structure impacts performance the most. To improve flexibility, and be less reliant on expert knowledge, this paper proposes a NAS methodology in which the search space is easily customizable, and allows for full network search. NAS is performed with Gaussian Process (GP)-based Bayesian Optimization (BO) in a continuous architecture embedding space. This embedding is built upon a Wasserstein Autoencoder, regularized by both a Maximum Mean Discrepancy (MMD) penalization and a Fully Input Convex Neural Network (FICNN) latent predictor, trained to infer the parameter count of architectures. This paper first assesses the embedding's suitability for optimization by solving 2 computationally inexpensive problems: minimizing the number of parameters, and maximizing a zero-shot accuracy proxy. Then, two variants of complexity-aware NAS are performed on CIFAR-10 and STL-10, based on two different search spaces, providing competitive NN architectures with limited model sizes.Neural Architecture Search (NAS) outperforms handcrafted Neural Network (NN) design. However, current NAS methods generally use hard-coded search spaces, and predefined hierarchical architectures. As a consequence, adapting them to a new problem can be cumbersome, and it is hard to know which of the NAS algorithm or the predefined hierarchical structure impacts performance the most. To improve flexibility, and be less reliant on expert knowledge, this paper proposes a NAS methodology in which the search space is easily customizable, and allows for full network search. NAS is performed with Gaussian Process (GP)-based Bayesian Optimization (BO) in a continuous architecture embedding space. This embedding is built upon a Wasserstein Autoencoder, regularized by both a Maximum Mean Discrepancy (MMD) penalization and a Fully Input Convex Neural Network (FICNN) latent predictor, trained to infer the parameter count of architectures. This paper first assesses the embedding's suitability for optimization by solving 2 computationally inexpensive problems: minimizing the number of parameters, and maximizing a zero-shot accuracy proxy. Then, two variants of complexity-aware NAS are performed on CIFAR-10 and STL-10, based on two different search spaces, providing competitive NN architectures with limited model sizes. |
| ArticleNumber | 106700 |
| Author | Paille, Bruno Sicard, Gilles Guicquero, William Perrin, Mathieu |
| Author_xml | – sequence: 1 givenname: Mathieu orcidid: 0009-0008-3997-0975 surname: Perrin fullname: Perrin, Mathieu email: mat@mathieuperrin.com organization: ST Microelectronics, 12 Rue Jules Horowitz, Grenoble, 38019, France – sequence: 2 givenname: William orcidid: 0000-0001-8925-0441 surname: Guicquero fullname: Guicquero, William email: william.guicquero@cea.fr organization: CEA-LETI, Université Grenoble Alpes, F-38000, 17 Avenue des Martyrs, Grenoble, 38054, France – sequence: 3 givenname: Bruno surname: Paille fullname: Paille, Bruno email: bruno.paille@st.com organization: ST Microelectronics, 12 Rue Jules Horowitz, Grenoble, 38019, France – sequence: 4 givenname: Gilles surname: Sicard fullname: Sicard, Gilles email: gilles.sicard@cea.fr organization: CEA-LETI, Université Grenoble Alpes, F-38000, 17 Avenue des Martyrs, Grenoble, 38054, France |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/39293175$$D View this record in MEDLINE/PubMed |
| BookMark | eNqFkE1PAyEQhomp0bb6D4zZo5etLLBfHoxN41fS6EE9E2AHpdlChV2N_16aVQ8e9DSTyfPOwDNBI-ssIHSU4VmGs-J0NbPQW-hmBBMWR0WJ8Q4aZ1VZp6SsyAiNcVXTtMAV3keTEFYY46JidA_t05rUNCvzMbp4dO_CNyERiXJWm-feC9lCImyTxIPpiwEvvHoxSrRJgG2bhI1QkGjnk7v5wwHa1aINcPhVp-jp6vJxcZMu769vF_NlqmhBulRoVdNC15qVpKgzIkkF8cm5ZiTHoASTwMoGSinzBoAVkjJZ1blSWOpISTpFJ8PejXevPYSOr01Q0LbCgusDp1sDlFDKInr8hfZyDQ3feLMW_oN__zoCbACUdyF40D9IhvlWLl_xQS7fyuWD3Bg7-xVTphOdcbbzwrT_hc-HMERJb9EqD8qAVdAYD6rjjTN_L_gEQWeWrQ |
| CitedBy_id | crossref_primary_10_1016_j_measurement_2025_118571 crossref_primary_10_1016_j_neunet_2025_107819 |
| Cites_doi | 10.1007/978-3-030-86383-8_44 10.1016/j.neucom.2021.10.118 10.1109/TNNLS.2019.2919608 10.1109/TNNLS.2023.3344294 10.5244/C.30.87 10.1038/323533a0 10.1007/s10479-007-0176-2 10.1007/s10994-020-05899-z 10.1007/978-3-030-05318-5_3 10.1109/TNNLS.2021.3123105 10.1609/aaai.v35i12.17233 10.1007/BF02098169 10.1109/TEVC.2020.3024708 10.1609/aaai.v32i1.11709 10.1109/TPAMI.2021.3052758 |
| ContentType | Journal Article |
| Copyright | 2024 Copyright © 2024. Published by Elsevier Ltd. |
| Copyright_xml | – notice: 2024 – notice: Copyright © 2024. Published by Elsevier Ltd. |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1016/j.neunet.2024.106700 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1879-2782 |
| ExternalDocumentID | 39293175 10_1016_j_neunet_2024_106700 S0893608024006245 |
| Genre | Journal Article |
| GroupedDBID | --- --K --M -~X .DC .~1 0R~ 123 186 1B1 1RT 1~. 1~5 29N 4.4 457 4G. 53G 5RE 5VS 6TJ 7-5 71M 8P~ 9JM 9JN AABNK AACTN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXKI AAXLA AAXUO AAYFN ABAOU ABBOA ABCQJ ABDPE ABEFU ABFNM ABFRF ABHFT ABIVO ABJNI ABLJU ABMAC ABXDB ACDAQ ACGFO ACGFS ACIUM ACNNM ACRLP ACZNC ADBBV ADEZE ADGUI ADJOM ADMUD ADRHT AEBSH AECPX AEFWE AEKER AENEX AFJKZ AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJOXV AKRWK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GBOLZ HLZ HMQ HVGLF HZ~ IHE J1W JJJVA K-O KOM KZ1 LG9 LMP M2V M41 MHUIS MO0 MOBAO MVM N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SCC SDF SDG SDP SES SEW SNS SPC SPCBC SSN SST SSV SSW SSZ T5K TAE UAP UNMZH VOH WUQ XPP ZMT ~G- 9DU AATTM AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFPUW AGQPQ AIGII AIIUN AKBMS AKYEP ANKPU APXCP CITATION EFKBS EFLBG ~HD AGCQF AGRNS BNPGV CGR CUY CVF ECM EIF NPM SSH 7X8 |
| ID | FETCH-LOGICAL-c362t-afc936f9f4726912b28e0675f4250eca4be47de7bb5dee46b34b895cc0bf75fb3 |
| ISICitedReferencesCount | 2 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001318038500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0893-6080 1879-2782 |
| IngestDate | Sun Sep 28 00:10:14 EDT 2025 Mon Jul 21 06:02:01 EDT 2025 Tue Nov 18 20:57:22 EST 2025 Sat Nov 29 05:33:09 EST 2025 Sat Nov 09 15:59:23 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Wasserstein autoencoder Neural architecture search Bayesian optimization Convolutional neural network |
| Language | English |
| License | Copyright © 2024. Published by Elsevier Ltd. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c362t-afc936f9f4726912b28e0675f4250eca4be47de7bb5dee46b34b895cc0bf75fb3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0001-8925-0441 0009-0008-3997-0975 |
| PMID | 39293175 |
| PQID | 3106732334 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_3106732334 pubmed_primary_39293175 crossref_primary_10_1016_j_neunet_2024_106700 crossref_citationtrail_10_1016_j_neunet_2024_106700 elsevier_sciencedirect_doi_10_1016_j_neunet_2024_106700 |
| PublicationCentury | 2000 |
| PublicationDate | December 2024 2024-12-00 2024-Dec 20241201 |
| PublicationDateYYYYMMDD | 2024-12-01 |
| PublicationDate_xml | – month: 12 year: 2024 text: December 2024 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Neural networks |
| PublicationTitleAlternate | Neural Netw |
| PublicationYear | 2024 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Huang, Liu, van der Maaten, Weinberger (b33) 2017 Lu, Deb, Boddeti (b51) 2020 Lukasik, Friede, Zela, Hutter, Keuper (b54) 2021 Hutter, Hoos, Leyton-Brown (b35) 2011 Mellor, J., Turner, J., Storkey, A., & Crowley, E. J. (2021). Neural Architecture Search without Training. In Rao, Zhao, Yi, Liu (b61) 2022 Schwarz Schuler, Romaní, Abdel-nasser, Rashwan, Puig (b67) 2022 Karnin, Z. S., Koren, T., & Somekh, O. (2013). Almost Optimal Exploration in Multi-Armed Bandits. In Tan, Chen, Pang, Vasudevan, Sandler, Howard (b71) 2019 Dai, Zhang, Wu, Yin, Sun, Wang (b16) 2019 Ioffe, S., & Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In Szegedy, Liu, Jia, Sermanet, Reed, Anguelov (b70) 2015 Snoek, J., Swersky, K., Zemel, R. S., & Adams, R. P. (2014). Input Warping for Bayesian Optimization of Non-Stationary Functions. In Trockman, Kolter (b76) 2022 Jing, Xu, Zhang (b38) 2022; 486 . Li, Gong, Zhu (b43) 2020 Thost, V., & Chen, J. (2021). Directed Acyclic Graph Neural Networks. In Higgins, I., Matthey, L., Pal, A., Burgess, C. P., Glorot, X., Botvinick, M. M., et al. (2017). Beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. In Schrodi, S., Stoll, D., Ru, B., Sukthanker, R., Brox, T., & Hutter, F. (2023). Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars. In A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, & S. Levine (Eds.) White, Safari, Sukthanker, Ru, Elsken, Zela (b81) 2023 Klein, A., Falkner, S., Springenberg, J. T., & Hutter, F. (2017). Learning Curve Prediction with Bayesian Neural Networks. In Tolstikhin, I. O., Bousquet, O., Gelly, S., & Schölkopf, B. (2018). Wasserstein Auto-Encoders. In Anandalingam, Friesz (b2) 1992; 34 Caillon, Esling (b10) 2021 Baker, B., Gupta, O., Raskar, R., & Naik, N. (2018). Accelerating Neural Architecture Search Using Performance Prediction. In Lu, Sreekumar, Goodman, Banzhaf, Deb, Boddeti (b52) 2021; 43 Cai, H., Chen, T., Zhang, W., Yu, Y., & Wang, J. (2018). Efficient Architecture Search by Network Transformation. In Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes. In Zoph, Vasudevan, Shlens, Le (b96) 2018 Chatzianastasis, Dasoulas, Siolas, Vazirgiannis (b11) 2021 Zhang, C., Ren, M., & Urtasun, R. (2019). Graph HyperNetworks for Neural Architecture Search. In Wan, Dai, Zhang, He, Tian, Xie (b77) 2020 Pham, H., Guan, M., Zoph, B., Le, Q., & Dean, J. (2018). Efficient Neural Architecture Search via Parameters Sharing. In Guo, Zhang, Mu, Heng, Liu, Wei (b27) 2020 [ISSN: 2640-3498]. Chen, W., Gong, X., & Wang, Z. (2021). Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective. In Devries, Taylor (b18) 2017 van den Oord, Vinyals, Kavukcuoglu (b59) 2017 Hacene, Lassance, Gripon, Courbariaux, Bengio (b28) 2020 Lopes, Alexandre (b49) 2023 The GPyOpt authors (b73) 2016 Bender, G., Kindermans, P.-J., Zoph, B., Vasudevan, V., & Le, Q. (2018). Understanding and Simplifying One-Shot Architecture Search. In Real, Aggarwal, Huang, Le (b62) 2019 Li, Sun, Yen, Zhang (b45) 2023; 34 Hu, Shen, Sun (b32) 2018 Luo, Tian, Qin, Chen, Liu (b55) 2018 Li, Jamieson, DeSalvo, Rostamizadeh, Talwalkar (b44) 2017; 18 Xiao, Shen, Tian, Hu (b84) 2023 Frazier (b24) 2018 Yan, Song, Liu, Zhang (b86) 2021; vol. 139 Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space. In He, Zhang, Ren, Sun (b29) 2016 Tan, M., & Le, Q. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In Cai, H., Zhu, L., & Han, S. (2019). ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware. In Gretton, Borgwardt, Rasch, Schölkopf, Smola (b26) 2012; 13 Jing, Xu, Li (b37) 2022 Hundt, Jain, Hager (b34) 2019 Yu, K., Sciuto, C., Jaggi, M., Musat, C., & Salzmann, M. (2020). Evaluating the Search Phase of Neural Architecture Search. In Lin, Wang, Sun, Chen, Sun, Qian (b46) 2021 Coiffier, Hacene, Gripon (b13) 2020 Zhang, Jiang, Cui, Garnett, Chen (b91) 2019 Goodfellow, Pouget-Abadie, Mirza, Xu, Warde-Farley, Ozair (b25) 2014 Falkner, S., Klein, A., & Hutter, F. (2018). BOHB: Robust and Efficient Hyperparameter Optimization at Scale. In Brock, A., Lim, T., Ritchie, J. M., & Weston, N. (2018). SMASH: One-Shot Model Architecture Search through HyperNetworks. In Lopes, V., Alirezazadeh, S., & Alexandre, L. A. (2021). EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search. In Zhang, Zhou, Lin, Sun (b94) 2018 Colson, Marcotte, Savard (b14) 2007; 153 Sun, Xue, Zhang, Yen (b69) 2020; 31 Wei, Niu, Tang, Wang, Hu, Liang (b78) 2022 White, Zela, Ru, Liu, Hutter (b82) 2021 Zagoruyko, S., & Komodakis, N. (2016). Wide Residual Networks. In Zoph, B., & Le, Q. V. (2017). Neural Architecture Search with Reinforcement Learning. In Balestriero, Pesenti, LeCun (b4) 2021 Cai, H., Gan, C., Wang, T., Zhang, Z., & Han, S. (2020). Once-for-All: Train One Network and Specialize It for Efficient Deployment. In Wu, Dai, Zhang, Wang, Sun, Wu (b83) 2019 Elsken, T., Metzen, J. H., & Hutter, F. (2019). Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution. In Xie, S., Zheng, H., Liu, C., & Lin, L. (2019). SNAS: Stochastic Neural Architecture Search. In Domhan, T., Springenberg, J. T., & Hutter, F. (2015). Speeding up Automatic Hyperparameter Optimization of Deep Neural Networks by Extrapolation of Learning Curves. In Rustamov (b64) 2019 Dai, Wan, Zhang, Wu, He, Wei (b15) 2021 Dong, Zhang, Li, Chen (b20) 2022 Lu, Whalen, Dhebar, Deb, Goodman, Banzhaf (b53) 2021; 25 Kandasamy, Neiswanger, Schneider, Poczos, Xing (b39) 2018 Moriconi, Deisenroth, Kumar (b58) 2020; 109 Yan, Zheng, Ao, Zeng, Zhang (b87) 2020 Liu, H., Simonyan, K., & Yang, Y. (2019). DARTS: Differentiable Architecture Search. In Wei, T., Wang, C., Rui, Y., & Chen, C. W. (2016). Network Morphism. In Amos, B., Xu, L., & Kolter, J. Z. (2017). Input Convex Neural Networks. In Elsken, T., Metzen, J., & Hutter, F. (2018). Simple and Efficient Architecture Search for Convolutional Neural Networks. In Yu, Y., Chen, J., Gao, T., & Yu, M. (2019). DAG-GNN: DAG Structure Learning with Graph Neural Networks. In White, C., Neiswanger, W., & Savani, Y. (2021). BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search. In Liu, Zoph, Neumann, Shlens, Hua, Li (b48) 2018 Howard, Sandler, Chen, Wang, Chen, Tan (b31) 2019 Rumelhart, Hinton, Williams (b63) 1986; 323 Devlin, Chang, Lee, Toutanova (b17) 2019 Sandler, Howard, Zhu, Zhmoginov, Chen (b65) 2018 Zhang, Yang, Jiang, Zhu, Liu (b93) 2020 Dong (10.1016/j.neunet.2024.106700_b20) 2022 He (10.1016/j.neunet.2024.106700_b29) 2016 Lopes (10.1016/j.neunet.2024.106700_b49) 2023 Coiffier (10.1016/j.neunet.2024.106700_b13) 2020 Dai (10.1016/j.neunet.2024.106700_b16) 2019 Liu (10.1016/j.neunet.2024.106700_b48) 2018 Hundt (10.1016/j.neunet.2024.106700_b34) 2019 Frazier (10.1016/j.neunet.2024.106700_b24) 2018 Huang (10.1016/j.neunet.2024.106700_b33) 2017 10.1016/j.neunet.2024.106700_b68 10.1016/j.neunet.2024.106700_b22 10.1016/j.neunet.2024.106700_b66 10.1016/j.neunet.2024.106700_b23 10.1016/j.neunet.2024.106700_b1 10.1016/j.neunet.2024.106700_b21 Rao (10.1016/j.neunet.2024.106700_b61) 2022 Zhang (10.1016/j.neunet.2024.106700_b93) 2020 10.1016/j.neunet.2024.106700_b3 10.1016/j.neunet.2024.106700_b30 10.1016/j.neunet.2024.106700_b74 10.1016/j.neunet.2024.106700_b5 Hu (10.1016/j.neunet.2024.106700_b32) 2018 10.1016/j.neunet.2024.106700_b72 10.1016/j.neunet.2024.106700_b7 10.1016/j.neunet.2024.106700_b6 Colson (10.1016/j.neunet.2024.106700_b14) 2007; 153 10.1016/j.neunet.2024.106700_b9 10.1016/j.neunet.2024.106700_b8 Lukasik (10.1016/j.neunet.2024.106700_b54) 2021 Hacene (10.1016/j.neunet.2024.106700_b28) 2020 Lu (10.1016/j.neunet.2024.106700_b53) 2021; 25 Chatzianastasis (10.1016/j.neunet.2024.106700_b11) 2021 Li (10.1016/j.neunet.2024.106700_b43) 2020 10.1016/j.neunet.2024.106700_b19 Lu (10.1016/j.neunet.2024.106700_b52) 2021; 43 Sandler (10.1016/j.neunet.2024.106700_b65) 2018 Devries (10.1016/j.neunet.2024.106700_b18) 2017 10.1016/j.neunet.2024.106700_b57 Jing (10.1016/j.neunet.2024.106700_b37) 2022 10.1016/j.neunet.2024.106700_b12 10.1016/j.neunet.2024.106700_b56 Moriconi (10.1016/j.neunet.2024.106700_b58) 2020; 109 10.1016/j.neunet.2024.106700_b60 Yan (10.1016/j.neunet.2024.106700_b86) 2021; vol. 139 Jing (10.1016/j.neunet.2024.106700_b38) 2022; 486 Schwarz Schuler (10.1016/j.neunet.2024.106700_b67) 2022 van den Oord (10.1016/j.neunet.2024.106700_b59) 2017 Caillon (10.1016/j.neunet.2024.106700_b10) 2021 Anandalingam (10.1016/j.neunet.2024.106700_b2) 1992; 34 Devlin (10.1016/j.neunet.2024.106700_b17) 2019 Lin (10.1016/j.neunet.2024.106700_b46) 2021 Wan (10.1016/j.neunet.2024.106700_b77) 2020 White (10.1016/j.neunet.2024.106700_b81) 2023 Yan (10.1016/j.neunet.2024.106700_b87) 2020 Kandasamy (10.1016/j.neunet.2024.106700_b39) 2018 10.1016/j.neunet.2024.106700_b47 10.1016/j.neunet.2024.106700_b88 Guo (10.1016/j.neunet.2024.106700_b27) 2020 10.1016/j.neunet.2024.106700_b89 10.1016/j.neunet.2024.106700_b42 Lu (10.1016/j.neunet.2024.106700_b51) 2020 The GPyOpt authors (10.1016/j.neunet.2024.106700_b73) 2016 Trockman (10.1016/j.neunet.2024.106700_b76) 2022 10.1016/j.neunet.2024.106700_b95 Hutter (10.1016/j.neunet.2024.106700_b35) 2011 10.1016/j.neunet.2024.106700_b50 Zhang (10.1016/j.neunet.2024.106700_b91) 2019 10.1016/j.neunet.2024.106700_b92 10.1016/j.neunet.2024.106700_b90 Dai (10.1016/j.neunet.2024.106700_b15) 2021 Howard (10.1016/j.neunet.2024.106700_b31) 2019 Zhang (10.1016/j.neunet.2024.106700_b94) 2018 Luo (10.1016/j.neunet.2024.106700_b55) 2018 Sun (10.1016/j.neunet.2024.106700_b69) 2020; 31 Goodfellow (10.1016/j.neunet.2024.106700_b25) 2014 Wei (10.1016/j.neunet.2024.106700_b78) 2022 Rustamov (10.1016/j.neunet.2024.106700_b64) 2019 Gretton (10.1016/j.neunet.2024.106700_b26) 2012; 13 10.1016/j.neunet.2024.106700_b79 10.1016/j.neunet.2024.106700_b36 White (10.1016/j.neunet.2024.106700_b82) 2021 Real (10.1016/j.neunet.2024.106700_b62) 2019 10.1016/j.neunet.2024.106700_b75 10.1016/j.neunet.2024.106700_b40 10.1016/j.neunet.2024.106700_b41 10.1016/j.neunet.2024.106700_b85 10.1016/j.neunet.2024.106700_b80 Xiao (10.1016/j.neunet.2024.106700_b84) 2023 Li (10.1016/j.neunet.2024.106700_b44) 2017; 18 Rumelhart (10.1016/j.neunet.2024.106700_b63) 1986; 323 Szegedy (10.1016/j.neunet.2024.106700_b70) 2015 Li (10.1016/j.neunet.2024.106700_b45) 2023; 34 Tan (10.1016/j.neunet.2024.106700_b71) 2019 Wu (10.1016/j.neunet.2024.106700_b83) 2019 Zoph (10.1016/j.neunet.2024.106700_b96) 2018 Balestriero (10.1016/j.neunet.2024.106700_b4) 2021 |
| References_xml | – reference: Zagoruyko, S., & Komodakis, N. (2016). Wide Residual Networks. In – volume: 34 start-page: 3832 year: 2023 end-page: 3846 ident: b45 article-title: Automatic design of convolutional neural network architectures under resource constraints publication-title: IEEE Transactions on Neural Networks and Learning Systems – year: 2014 ident: b25 article-title: Generative adversarial networks – reference: . [ISSN: 2640-3498]. – year: 2022 ident: b20 article-title: PACE: A parallelizable computation encoder for directed acyclic graphs publication-title: International conference on machine learning – year: 2019 ident: b34 article-title: Sharpdarts: Faster and more accurate differentiable architecture search – volume: 486 start-page: 189 year: 2022 end-page: 199 ident: b38 article-title: A neural architecture generator for efficient search space publication-title: Neurocomputing – year: 2018 ident: b94 article-title: ShuffleNet: An extremely efficient convolutional neural network for mobile devices publication-title: IEEE conference on computer vision and pattern recognition – year: 2018 ident: b39 article-title: Neural architecture search with Bayesian optimisation and optimal transport publication-title: Advances in neural information processing systems (neurIPS) – reference: Schrodi, S., Stoll, D., Ru, B., Sukthanker, R., Brox, T., & Hutter, F. (2023). Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars. In A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, & S. Levine (Eds.), – reference: Snoek, J., Swersky, K., Zemel, R. S., & Adams, R. P. (2014). Input Warping for Bayesian Optimization of Non-Stationary Functions. In – start-page: 1 year: 2023 end-page: 13 ident: b84 article-title: PP-NAS: Searching for plug-and-play blocks on convolutional neural networks publication-title: IEEE Transactions on Neural Networks and Learning Systems – volume: 13 start-page: 723 year: 2012 end-page: 773 ident: b26 article-title: A kernel two-sample test publication-title: Journal of Machine Learning Research – volume: 25 start-page: 277 year: 2021 end-page: 291 ident: b53 article-title: Multiobjective evolutionary design of deep convolutional neural networks for image classification publication-title: IEEE Transactions on Evolutionary Computation – volume: 109 start-page: 1925 year: 2020 end-page: 1943 ident: b58 article-title: High-dimensional Bayesian optimization using low-dimensional feature spaces publication-title: Machine Learning – reference: Domhan, T., Springenberg, J. T., & Hutter, F. (2015). Speeding up Automatic Hyperparameter Optimization of Deep Neural Networks by Extrapolation of Learning Curves. In – reference: Yu, K., Sciuto, C., Jaggi, M., Musat, C., & Salzmann, M. (2020). Evaluating the Search Phase of Neural Architecture Search. In – volume: 18 start-page: 185:1 year: 2017 end-page: 185:52 ident: b44 article-title: Hyperband: A novel bandit-based approach to hyperparameter optimization publication-title: Journal of Machine Learning Research (JMLR) – reference: Xie, S., Zheng, H., Liu, C., & Lin, L. (2019). SNAS: Stochastic Neural Architecture Search. In – year: 2019 ident: b83 article-title: Fbnet: Hardware-aware efficient ConvNet design via differentiable neural architecture search publication-title: IEEE conference on computer vision and pattern recognition – volume: 323 start-page: 533 year: 1986 end-page: 536 ident: b63 article-title: Learning representations by back-propagating errors publication-title: Nature – reference: Klein, A., Falkner, S., Springenberg, J. T., & Hutter, F. (2017). Learning Curve Prediction with Bayesian Neural Networks. In – year: 2021 ident: b11 article-title: Graph-based neural architecture search with operation embeddings publication-title: IEEE international conference on computer vision – year: 2019 ident: b17 article-title: BERT: Pre-training of deep bidirectional transformers for language understanding publication-title: Conference of the North American chapter of the association for computational linguistics: human language technologies – year: 2020 ident: b51 article-title: MUXConv: Information multiplexing in convolutional neural networks publication-title: IEEE conference on computer vision and pattern recognition – reference: Baker, B., Gupta, O., Raskar, R., & Naik, N. (2018). Accelerating Neural Architecture Search Using Performance Prediction. In – year: 2021 ident: b54 article-title: Smooth variational graph embeddings for efficient neural architecture search publication-title: International joint conference on neural networks – volume: 34 start-page: 1 year: 1992 end-page: 11 ident: b2 article-title: Hierarchical optimization: an introduction publication-title: Annals of Operations Research – year: 2020 ident: b13 article-title: ThriftyNets : Convolutional neural networks with tiny parameter budget – year: 2021 ident: b82 article-title: How powerful are performance predictors in neural architecture search? publication-title: Advances in neural information processing systems (NeurIPS) – year: 2023 ident: b81 article-title: Neural architecture search: insights from 1000 papers – year: 2016 ident: b29 article-title: Deep residual learning for image recognition publication-title: IEEE conference on computer vision and pattern recognition – year: 2018 ident: b48 article-title: Progressive neural architecture search publication-title: European conference on computer vision – year: 2019 ident: b71 article-title: MnasNet: Platform-aware neural architecture search for mobile publication-title: IEEE conference on computer vision and pattern recognition – reference: Brock, A., Lim, T., Ritchie, J. M., & Weston, N. (2018). SMASH: One-Shot Model Architecture Search through HyperNetworks. In – reference: White, C., Neiswanger, W., & Savani, Y. (2021). BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search. In – year: 2017 ident: b33 article-title: Densely connected convolutional networks publication-title: IEEE conference on computer vision and pattern recognition – year: 2021 ident: b46 article-title: Zen-NAS: A zero-shot NAS for high-performance image recognition publication-title: IEEE international conference on computer vision – reference: Amos, B., Xu, L., & Kolter, J. Z. (2017). Input Convex Neural Networks. In – reference: Higgins, I., Matthey, L., Pal, A., Burgess, C. P., Glorot, X., Botvinick, M. M., et al. (2017). Beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. In – reference: Zhang, C., Ren, M., & Urtasun, R. (2019). Graph HyperNetworks for Neural Architecture Search. In – reference: Mellor, J., Turner, J., Storkey, A., & Crowley, E. J. (2021). Neural Architecture Search without Training. In – year: 2021 ident: b10 article-title: RAVE: A variational autoencoder for fast and high-quality neural audio synthesis – start-page: 3114 year: 2022 end-page: 3120 ident: b37 article-title: Graph masked autoencoder enhanced predictor for neural architecture search publication-title: Proceedings of the thirty-first international joint conference on artificial intelligence – reference: Falkner, S., Klein, A., & Hutter, F. (2018). BOHB: Robust and Efficient Hyperparameter Optimization at Scale. In – year: 2018 ident: b24 article-title: A tutorial on Bayesian optimization – year: 2020 ident: b28 article-title: Attention based pruning for shift networks publication-title: International conference on pattern recognition – year: 2022 ident: b67 article-title: Grouped pointwise convolutions reduce parameters in convolutional neural networks publication-title: International conference on soft computing – year: 2019 ident: b62 article-title: Regularized evolution for image classifier architecture search publication-title: AAAI conference on artificial intelligence – volume: 43 start-page: 2971 year: 2021 end-page: 2989 ident: b52 article-title: Neural architecture transfer publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) – reference: Liu, H., Simonyan, K., & Yang, Y. (2019). DARTS: Differentiable Architecture Search. In – volume: vol. 139 start-page: 11670 year: 2021 end-page: 11681 ident: b86 article-title: CATE: computation-aware neural architecture encoding with transformers publication-title: Proceedings of the 38th international conference on machine learning – reference: Elsken, T., Metzen, J. H., & Hutter, F. (2019). Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution. In – year: 2018 ident: b65 article-title: MobileNetV2: Inverted residuals and linear bottlenecks publication-title: IEEE conference on computer vision and pattern recognition – reference: Zoph, B., & Le, Q. V. (2017). Neural Architecture Search with Reinforcement Learning. In – year: 2020 ident: b87 article-title: Does unsupervised architecture representation learning help neural architecture search? publication-title: Advances in neural information processing systems (neurIPS) – year: 2020 ident: b93 article-title: Fast hardware-aware neural architecture search publication-title: IEEE conference on computer vision and pattern recognition – reference: Pham, H., Guan, M., Zoph, B., Le, Q., & Dean, J. (2018). Efficient Neural Architecture Search via Parameters Sharing. In – year: 2016 ident: b73 article-title: GPyOpt: A Bayesian optimization framework in Python – year: 2021 ident: b15 article-title: FBNetV3: Joint architecture-recipe search using predictor pretraining publication-title: IEEE conference on computer vision and pattern recognition – reference: Wei, T., Wang, C., Rui, Y., & Chen, C. W. (2016). Network Morphism. In – reference: Tan, M., & Le, Q. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In – year: 2017 ident: b18 article-title: Improved regularization of convolutional neural networks with cutout – reference: Cai, H., Zhu, L., & Han, S. (2019). ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware. In – reference: Ioffe, S., & Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In – year: 2020 ident: b43 article-title: Neural graph embedding for neural architecture search publication-title: AAAI conference on artificial intelligence – year: 2018 ident: b32 article-title: Squeeze-and-excitation networks publication-title: IEEE conference on computer vision and pattern recognition – volume: 153 start-page: 235 year: 2007 end-page: 256 ident: b14 article-title: An overview of bilevel optimization publication-title: Annals of Operations Research – reference: Yu, Y., Chen, J., Gao, T., & Yu, M. (2019). DAG-GNN: DAG Structure Learning with Graph Neural Networks. In – year: 2011 ident: b35 article-title: Sequential model-based optimization for general algorithm configuration publication-title: Learning and intelligent optimization – reference: Elsken, T., Metzen, J., & Hutter, F. (2018). Simple and Efficient Architecture Search for Convolutional Neural Networks. In – reference: Karnin, Z. S., Koren, T., & Somekh, O. (2013). Almost Optimal Exploration in Multi-Armed Bandits. In – reference: Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes. In – year: 2020 ident: b27 article-title: Single path one-shot neural architecture search with uniform sampling publication-title: European conference on computer vision – year: 2018 ident: b96 article-title: Learning transferable architectures for scalable image recognition publication-title: IEEE conference on computer vision and pattern recognition – reference: Chen, W., Gong, X., & Wang, Z. (2021). Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective. In – year: 2015 ident: b70 article-title: Going deeper with convolutions publication-title: IEEE conference on computer vision and pattern recognition – reference: Thost, V., & Chen, J. (2021). Directed Acyclic Graph Neural Networks. In – year: 2021 ident: b4 article-title: Learning in high dimension always amounts to extrapolation – year: 2019 ident: b31 article-title: Searching for MobileNetV3 publication-title: International conference on computer vision – reference: Tolstikhin, I. O., Bousquet, O., Gelly, S., & Schölkopf, B. (2018). Wasserstein Auto-Encoders. In – year: 2022 ident: b61 article-title: CR-LSO: Convex neural architecture optimization in the latent space of graph variational autoencoder with input convex neural networks – year: 2019 ident: b16 article-title: ChamNet: Towards efficient network design through platform-aware model adaptation publication-title: IEEE conference on computer vision and pattern recognition – reference: Lopes, V., Alirezazadeh, S., & Alexandre, L. A. (2021). EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search. In – year: 2019 ident: b64 article-title: Closed-form expressions for maximum mean discrepancy with applications to wasserstein auto-encoders – reference: Bender, G., Kindermans, P.-J., Zoph, B., Vasudevan, V., & Le, Q. (2018). Understanding and Simplifying One-Shot Architecture Search. In – start-page: 1 year: 2023 end-page: 15 ident: b49 article-title: Toward less constrained macro-neural architecture search publication-title: IEEE transactions on neural networks and learning systems – year: 2017 ident: b59 article-title: Neural discrete representation learning publication-title: Advances in neural information processing systems (NeurIPS) – year: 2020 ident: b77 article-title: FBNetV2: Differentiable neural architecture search for spatial and channel dimensions publication-title: IEEE conference on computer vision and pattern recognition – year: 2018 ident: b55 article-title: Neural architecture optimization publication-title: Advances in neural information processing systems (neurIPS) – reference: . – reference: Cai, H., Chen, T., Zhang, W., Yu, Y., & Wang, J. (2018). Efficient Architecture Search by Network Transformation. In – reference: Cai, H., Gan, C., Wang, T., Zhang, Z., & Han, S. (2020). Once-for-All: Train One Network and Specialize It for Efficient Deployment. In – reference: Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space. In – year: 2019 ident: b91 article-title: D-VAE: A variational autoencoder for directed acyclic graphs publication-title: Advances in neural information processing systems (neurIPS) – volume: 31 start-page: 1242 year: 2020 end-page: 1254 ident: b69 article-title: Completely automated CNN architecture design based on blocks publication-title: IEEE Transactions on Neural Networks and Learning Systems – year: 2022 ident: b76 article-title: Patches are all you need? – start-page: 1 year: 2022 end-page: 15 ident: b78 article-title: NPENAS: Neural predictor guided evolution for neural architecture search publication-title: IEEE Transactions on Neural Networks and Learning Systems – year: 2014 ident: 10.1016/j.neunet.2024.106700_b25 – year: 2017 ident: 10.1016/j.neunet.2024.106700_b18 – year: 2022 ident: 10.1016/j.neunet.2024.106700_b61 – ident: 10.1016/j.neunet.2024.106700_b50 doi: 10.1007/978-3-030-86383-8_44 – ident: 10.1016/j.neunet.2024.106700_b95 – year: 2019 ident: 10.1016/j.neunet.2024.106700_b16 article-title: ChamNet: Towards efficient network design through platform-aware model adaptation – ident: 10.1016/j.neunet.2024.106700_b66 – ident: 10.1016/j.neunet.2024.106700_b8 – ident: 10.1016/j.neunet.2024.106700_b47 – volume: 486 start-page: 189 year: 2022 ident: 10.1016/j.neunet.2024.106700_b38 article-title: A neural architecture generator for efficient search space publication-title: Neurocomputing doi: 10.1016/j.neucom.2021.10.118 – year: 2019 ident: 10.1016/j.neunet.2024.106700_b34 – year: 2021 ident: 10.1016/j.neunet.2024.106700_b46 article-title: Zen-NAS: A zero-shot NAS for high-performance image recognition – ident: 10.1016/j.neunet.2024.106700_b5 – volume: 13 start-page: 723 year: 2012 ident: 10.1016/j.neunet.2024.106700_b26 article-title: A kernel two-sample test publication-title: Journal of Machine Learning Research – ident: 10.1016/j.neunet.2024.106700_b1 – volume: 31 start-page: 1242 issue: 4 year: 2020 ident: 10.1016/j.neunet.2024.106700_b69 article-title: Completely automated CNN architecture design based on blocks publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2019.2919608 – ident: 10.1016/j.neunet.2024.106700_b19 – year: 2021 ident: 10.1016/j.neunet.2024.106700_b4 – year: 2021 ident: 10.1016/j.neunet.2024.106700_b82 article-title: How powerful are performance predictors in neural architecture search? – ident: 10.1016/j.neunet.2024.106700_b57 – ident: 10.1016/j.neunet.2024.106700_b72 – ident: 10.1016/j.neunet.2024.106700_b30 – year: 2020 ident: 10.1016/j.neunet.2024.106700_b43 article-title: Neural graph embedding for neural architecture search – year: 2019 ident: 10.1016/j.neunet.2024.106700_b17 article-title: BERT: Pre-training of deep bidirectional transformers for language understanding – ident: 10.1016/j.neunet.2024.106700_b75 – year: 2021 ident: 10.1016/j.neunet.2024.106700_b15 article-title: FBNetV3: Joint architecture-recipe search using predictor pretraining – year: 2020 ident: 10.1016/j.neunet.2024.106700_b77 article-title: FBNetV2: Differentiable neural architecture search for spatial and channel dimensions – year: 2018 ident: 10.1016/j.neunet.2024.106700_b39 article-title: Neural architecture search with Bayesian optimisation and optimal transport – ident: 10.1016/j.neunet.2024.106700_b79 – year: 2020 ident: 10.1016/j.neunet.2024.106700_b51 article-title: MUXConv: Information multiplexing in convolutional neural networks – year: 2019 ident: 10.1016/j.neunet.2024.106700_b64 – year: 2015 ident: 10.1016/j.neunet.2024.106700_b70 article-title: Going deeper with convolutions – start-page: 1 year: 2022 ident: 10.1016/j.neunet.2024.106700_b78 article-title: NPENAS: Neural predictor guided evolution for neural architecture search publication-title: IEEE Transactions on Neural Networks and Learning Systems – start-page: 1 year: 2023 ident: 10.1016/j.neunet.2024.106700_b84 article-title: PP-NAS: Searching for plug-and-play blocks on convolutional neural networks publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2023.3344294 – ident: 10.1016/j.neunet.2024.106700_b23 – ident: 10.1016/j.neunet.2024.106700_b60 – year: 2019 ident: 10.1016/j.neunet.2024.106700_b62 article-title: Regularized evolution for image classifier architecture search – ident: 10.1016/j.neunet.2024.106700_b40 – ident: 10.1016/j.neunet.2024.106700_b12 – ident: 10.1016/j.neunet.2024.106700_b85 – ident: 10.1016/j.neunet.2024.106700_b90 doi: 10.5244/C.30.87 – ident: 10.1016/j.neunet.2024.106700_b89 – volume: 323 start-page: 533 issue: 6088 year: 1986 ident: 10.1016/j.neunet.2024.106700_b63 article-title: Learning representations by back-propagating errors publication-title: Nature doi: 10.1038/323533a0 – year: 2020 ident: 10.1016/j.neunet.2024.106700_b93 article-title: Fast hardware-aware neural architecture search – year: 2021 ident: 10.1016/j.neunet.2024.106700_b10 – ident: 10.1016/j.neunet.2024.106700_b92 – year: 2016 ident: 10.1016/j.neunet.2024.106700_b73 – year: 2022 ident: 10.1016/j.neunet.2024.106700_b67 article-title: Grouped pointwise convolutions reduce parameters in convolutional neural networks – year: 2020 ident: 10.1016/j.neunet.2024.106700_b13 – year: 2020 ident: 10.1016/j.neunet.2024.106700_b27 article-title: Single path one-shot neural architecture search with uniform sampling – year: 2018 ident: 10.1016/j.neunet.2024.106700_b32 article-title: Squeeze-and-excitation networks – ident: 10.1016/j.neunet.2024.106700_b74 – start-page: 1 year: 2023 ident: 10.1016/j.neunet.2024.106700_b49 article-title: Toward less constrained macro-neural architecture search – year: 2018 ident: 10.1016/j.neunet.2024.106700_b65 article-title: MobileNetV2: Inverted residuals and linear bottlenecks – volume: 153 start-page: 235 issue: 1 year: 2007 ident: 10.1016/j.neunet.2024.106700_b14 article-title: An overview of bilevel optimization publication-title: Annals of Operations Research doi: 10.1007/s10479-007-0176-2 – volume: 18 start-page: 185:1 year: 2017 ident: 10.1016/j.neunet.2024.106700_b44 article-title: Hyperband: A novel bandit-based approach to hyperparameter optimization publication-title: Journal of Machine Learning Research (JMLR) – ident: 10.1016/j.neunet.2024.106700_b68 – year: 2018 ident: 10.1016/j.neunet.2024.106700_b55 article-title: Neural architecture optimization – year: 2020 ident: 10.1016/j.neunet.2024.106700_b28 article-title: Attention based pruning for shift networks – start-page: 3114 year: 2022 ident: 10.1016/j.neunet.2024.106700_b37 article-title: Graph masked autoencoder enhanced predictor for neural architecture search – ident: 10.1016/j.neunet.2024.106700_b41 – year: 2020 ident: 10.1016/j.neunet.2024.106700_b87 article-title: Does unsupervised architecture representation learning help neural architecture search? – year: 2018 ident: 10.1016/j.neunet.2024.106700_b96 article-title: Learning transferable architectures for scalable image recognition – volume: 109 start-page: 1925 issue: 9–10 year: 2020 ident: 10.1016/j.neunet.2024.106700_b58 article-title: High-dimensional Bayesian optimization using low-dimensional feature spaces publication-title: Machine Learning doi: 10.1007/s10994-020-05899-z – ident: 10.1016/j.neunet.2024.106700_b3 – year: 2019 ident: 10.1016/j.neunet.2024.106700_b83 article-title: Fbnet: Hardware-aware efficient ConvNet design via differentiable neural architecture search – ident: 10.1016/j.neunet.2024.106700_b22 doi: 10.1007/978-3-030-05318-5_3 – ident: 10.1016/j.neunet.2024.106700_b88 – year: 2023 ident: 10.1016/j.neunet.2024.106700_b81 – year: 2019 ident: 10.1016/j.neunet.2024.106700_b71 article-title: MnasNet: Platform-aware neural architecture search for mobile – year: 2019 ident: 10.1016/j.neunet.2024.106700_b91 article-title: D-VAE: A variational autoencoder for directed acyclic graphs – year: 2021 ident: 10.1016/j.neunet.2024.106700_b54 article-title: Smooth variational graph embeddings for efficient neural architecture search – year: 2016 ident: 10.1016/j.neunet.2024.106700_b29 article-title: Deep residual learning for image recognition – ident: 10.1016/j.neunet.2024.106700_b36 – volume: 34 start-page: 3832 issue: 8 year: 2023 ident: 10.1016/j.neunet.2024.106700_b45 article-title: Automatic design of convolutional neural network architectures under resource constraints publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2021.3123105 – ident: 10.1016/j.neunet.2024.106700_b80 doi: 10.1609/aaai.v35i12.17233 – volume: 34 start-page: 1 year: 1992 ident: 10.1016/j.neunet.2024.106700_b2 article-title: Hierarchical optimization: an introduction publication-title: Annals of Operations Research doi: 10.1007/BF02098169 – year: 2021 ident: 10.1016/j.neunet.2024.106700_b11 article-title: Graph-based neural architecture search with operation embeddings – volume: 25 start-page: 277 issue: 2 year: 2021 ident: 10.1016/j.neunet.2024.106700_b53 article-title: Multiobjective evolutionary design of deep convolutional neural networks for image classification publication-title: IEEE Transactions on Evolutionary Computation doi: 10.1109/TEVC.2020.3024708 – ident: 10.1016/j.neunet.2024.106700_b21 doi: 10.1007/978-3-030-05318-5_3 – year: 2011 ident: 10.1016/j.neunet.2024.106700_b35 article-title: Sequential model-based optimization for general algorithm configuration – year: 2022 ident: 10.1016/j.neunet.2024.106700_b20 article-title: PACE: A parallelizable computation encoder for directed acyclic graphs – ident: 10.1016/j.neunet.2024.106700_b9 – year: 2017 ident: 10.1016/j.neunet.2024.106700_b33 article-title: Densely connected convolutional networks – ident: 10.1016/j.neunet.2024.106700_b7 doi: 10.1609/aaai.v32i1.11709 – ident: 10.1016/j.neunet.2024.106700_b42 – ident: 10.1016/j.neunet.2024.106700_b6 – year: 2019 ident: 10.1016/j.neunet.2024.106700_b31 article-title: Searching for MobileNetV3 – volume: 43 start-page: 2971 issue: 9 year: 2021 ident: 10.1016/j.neunet.2024.106700_b52 article-title: Neural architecture transfer publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) doi: 10.1109/TPAMI.2021.3052758 – year: 2022 ident: 10.1016/j.neunet.2024.106700_b76 – ident: 10.1016/j.neunet.2024.106700_b56 – year: 2017 ident: 10.1016/j.neunet.2024.106700_b59 article-title: Neural discrete representation learning – year: 2018 ident: 10.1016/j.neunet.2024.106700_b48 article-title: Progressive neural architecture search – year: 2018 ident: 10.1016/j.neunet.2024.106700_b24 – year: 2018 ident: 10.1016/j.neunet.2024.106700_b94 article-title: ShuffleNet: An extremely efficient convolutional neural network for mobile devices – volume: vol. 139 start-page: 11670 year: 2021 ident: 10.1016/j.neunet.2024.106700_b86 article-title: CATE: computation-aware neural architecture encoding with transformers |
| SSID | ssj0006843 |
| Score | 2.4552727 |
| Snippet | Neural Architecture Search (NAS) outperforms handcrafted Neural Network (NN) design. However, current NAS methods generally use hard-coded search spaces, and... |
| SourceID | proquest pubmed crossref elsevier |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 106700 |
| SubjectTerms | Algorithms Bayes Theorem Bayesian optimization Convolutional neural network Humans Neural architecture search Neural Networks, Computer Normal Distribution Wasserstein autoencoder |
| Title | Towards a configurable and non-hierarchical search space for NAS |
| URI | https://dx.doi.org/10.1016/j.neunet.2024.106700 https://www.ncbi.nlm.nih.gov/pubmed/39293175 https://www.proquest.com/docview/3106732334 |
| Volume | 180 |
| WOSCitedRecordID | wos001318038500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1879-2782 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0006843 issn: 0893-6080 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV07b9swECYcp0OXvh_uI2CBohsNWaREcmtQOH3AdTs4haYSIkUFNgzZla0gP79HUZKdNkHSoYsg0KRI8z6d7o73QOhtwGVELbOEyiwmLAsFSWUsSZjFOnA1r3QdX_FjwqdTkSTye6_3s42FOV_yohAXF3L9X0kNbUBsFzr7D-TuHgoNcA9EhyuQHa63I3ztCLtxUY-rIp-fVWUdHeUM5KDqE1f7uj49qMMhvc0DuIrxyb-nTV3iRZvUqc7KUXhf8c2Oj5alzz3w1Tkv2qrz4qnmBj40PnamMeXsHVItve-yy3aw6kw7sBDvXv_R_X7JDBGyPZcOzzkFBwpzX0loaK9o69htsMcwR3Wc0JW83JsVFsPCVvA3h27S4a775dTZ02_q5HQyUbNxMnu3_kVcVTF3-t6UWDlAhyGPpOijw-PP4-RL962OhQ_BaBfaBlfWHoB_T3yd8HKdclILKbMH6F6jXeBjj4qHqGeLR-h-W7kDN4z8MXrfgASneB8kGECC_wQJ9iDBNUgwgAQDSJ6g05Px7MMn0tTSIAZElC1JcyNpnMuc8TCWo1CHwjplMQeeHViTMm0ZzyzXOsqsZbGmTAsZGRPoHHpp-hT1YX77HGETxYyzMBepcVnuc3gaS4XIZE6zUarFANF2k5RpEs27eidL1XoULpTfWuW2VvmtHSDSjVr7RCs39Oft_qtGWPRCoAL83DDyTUsuBbzUHZClhV1VG0VdBxpSygbomadjtxanRzhZ-8UtRr9Ed3evyCvU35aVfY3umPPtfFMeoQOeiKMGib8BjdaeDg |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Towards+a+configurable+and+non-hierarchical+search+space+for+NAS&rft.jtitle=Neural+networks&rft.au=Perrin%2C+Mathieu&rft.au=Guicquero%2C+William&rft.au=Paille%2C+Bruno&rft.au=Sicard%2C+Gilles&rft.date=2024-12-01&rft.issn=1879-2782&rft.eissn=1879-2782&rft.volume=180&rft.spage=106700&rft_id=info:doi/10.1016%2Fj.neunet.2024.106700&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0893-6080&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0893-6080&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0893-6080&client=summon |