{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T19:23:42Z","timestamp":1740165822160,"version":"3.37.3"},"reference-count":116,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Funda\u00e7\u00e3o para a Ci\u00eancia e Tecnologia","award":["2020.04588.BD"],"award-info":[{"award-number":["2020.04588.BD"]}]},{"name":"NOVA LINCS of FCT through National Funds","award":["UIDB\/04516\/2020"],"award-info":[{"award-number":["UIDB\/04516\/2020"]}]},{"DOI":"10.13039\/501100008530","name":"Fundo Europeu de Desenvolvimento Regional","doi-asserted-by":"crossref","award":["CENTRO-01-0247-FEDER-113023\u2014DeepNeuronic"],"award-info":[{"award-number":["CENTRO-01-0247-FEDER-113023\u2014DeepNeuronic"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tnnls.2023.3326648","type":"journal-article","created":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T18:12:26Z","timestamp":1698775946000},"page":"2854-2868","source":"Crossref","is-referenced-by-count":1,"title":["Toward Less Constrained Macro-Neural Architecture Search"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5577-1094","authenticated-orcid":false,"given":"Vasco","family":"Lopes","sequence":"first","affiliation":[{"name":"NOVA LINCS, Universidade da Beira Interior, Covilh&#x00E3;, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5133-5025","authenticated-orcid":false,"given":"Lu\u00eds A.","family":"Alexandre","sequence":"additional","affiliation":[{"name":"NOVA LINCS, Universidade da Beira Interior, Covilh&#x00E3;, Portugal"}]}],"member":"263","reference":[{"volume-title":"Torchvision","year":"2021","key":"ref1"},{"key":"ref2","first-page":"1","article-title":"Designing neural network architectures using reinforcement learning","volume-title":"Proc. ICLR","author":"Baker"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5555\/2188385.2188395"},{"key":"ref4","first-page":"1","article-title":"SMASH: One-shot model architecture search through hypernetworks","volume-title":"Proc. ICLR","author":"Brock"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11709"},{"key":"ref6","first-page":"1","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","volume-title":"Proc. ICLR","author":"Cai"},{"key":"ref7","first-page":"1","article-title":"Neural architecture search on ImageNet in four GPU hours: A theoretically inspired perspective","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref8","article-title":"Understanding and accelerating neural architecture search with training-free and theory-grounded metrics","author":"Chen","year":"2021","journal-title":"arXiv:2108.11939"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_12"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00138"},{"key":"ref11","article-title":"DetNAS: Backbone search for object detection","author":"Chen","year":"2019","journal-title":"arXiv:1903.10979"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref13","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv:1708.04552"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3067028"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00378"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00186"},{"key":"ref17","first-page":"1","article-title":"NAS-Bench-201: Extending the scope of reproducible neural architecture search","volume-title":"Proc. ICLR","author":"Dong"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00521"},{"key":"ref19","first-page":"1","article-title":"Efficient multi-objective neural architecture search via Lamarckian evolution","volume-title":"Proc. ICLR","author":"Elsken"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_3"},{"key":"ref21","first-page":"1","article-title":"BOHB: Robust and efficient hyperparameter optimization at scale","volume-title":"Proc. ICML","author":"Falkner"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00572"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3151511"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00332"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref27","first-page":"1","article-title":"Macro neural architecture search revisited","volume-title":"Proc. NeurIPS Workshop Meta-Learn.","author":"Hu"},{"key":"ref28","first-page":"1","article-title":"Efficient forward architecture search","volume-title":"Proc. NeurIPS","author":"Hu"},{"key":"ref29","first-page":"2261","article-title":"Densely connected convolutional networks are a type of deep learning neural network that are used in computer vision","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Huang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01158"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5"},{"key":"ref32","article-title":"SqueezeNet: AlexNet-level accuracy with 50\u00d7 fewer parameters and < 0.5MB model size","author":"Iandola","year":"2016","journal-title":"arXiv:1602.07360"},{"key":"ref33","first-page":"1","article-title":"Neural architecture search with Bayesian optimisation and optimal transport","volume-title":"Proc. NeurIPS","author":"Kandasamy"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09825-6"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1233"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3169897"},{"key":"ref37","first-page":"1","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref38","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. NeurIPS","author":"Krizhevsky"},{"key":"ref39","first-page":"1","article-title":"FractalNet: Ultra-deep neural networks without residuals","volume-title":"Proc. ICLR","author":"Larsson"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3236336"},{"key":"ref42","first-page":"367","article-title":"Random search and reproducibility for neural architecture search","volume-title":"Proc. UAI","author":"Li"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105636"},{"key":"ref44","first-page":"1","article-title":"Generic neural architecture search via regression","volume-title":"Proc. NeurIPS","author":"Li"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084827"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01195"},{"issue":"1","key":"ref47","first-page":"9820","article-title":"Best practices for scientific research on neural architecture search","volume":"21","author":"Lindauer","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00017"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_46"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref51","first-page":"1","article-title":"Hierarchical representations for efficient architecture search","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref52","first-page":"1","article-title":"DARTS: Differentiable architecture search","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3100554"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86383-8_44"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-023-06379-w"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119695"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3520304.3528936"},{"key":"ref58","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321729"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3104872"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref62","first-page":"1","article-title":"NAS-Bench-ASR: Reproducible neural architecture search for speech recognition","volume-title":"Proc. ICLR","author":"Mehrotra"},{"key":"ref63","first-page":"1","article-title":"Neural architecture search without training","volume-title":"Proc. ICML","author":"Mellor"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3192169"},{"key":"ref65","first-page":"1","article-title":"Efficient progressive neural architecture search","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Perez-Rua"},{"key":"ref66","first-page":"1","article-title":"Efficient neural architecture search via parameters sharing","volume-title":"Proc. ICML","author":"Pham"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref68","first-page":"1","article-title":"Large-scale evolution of image classifiers","volume-title":"Proc. ICML","author":"Real"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3447582"},{"key":"ref70","first-page":"1","article-title":"Interpretable neural architecture search via Bayesian optimisation with Weisfeiler\u2013Lehman kernels","volume-title":"Proc. ICLR","author":"Ru"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref72","first-page":"1","article-title":"Convolutional neural fabrics","volume-title":"Proc. NeurIPS","author":"Saxena"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1404.7828"},{"key":"ref74","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref75","first-page":"1","article-title":"Bridging the gap between sample-based and one-shot neural architecture search with BONAS","volume-title":"Proc. NeurIPS","author":"Shi"},{"key":"ref76","article-title":"Surrogate NAS benchmarks: Going beyond the limited search spaces of tabular NAS benchmarks","author":"Zela","year":"2020","journal-title":"arXiv:2008.09777"},{"key":"ref77","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. ICLR","author":"Simonyan"},{"key":"ref78","first-page":"1","article-title":"On the importance of initialization and momentum in deep learning","volume-title":"Proc. ICML","author":"Sutskever"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3096658"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref82","first-page":"1","article-title":"Pruning neural networks without any data by iteratively conserving synaptic flow","volume-title":"Proc. NeurIPS","author":"Tanaka"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00368"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3072290"},{"key":"ref85","first-page":"1","article-title":"On redundancy and diversity in cell-based neural architecture search","volume-title":"Proc. ICLR","author":"Wan"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3220699"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3070605"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105698"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3071343"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3124330"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6462"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3151160"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17233"},{"key":"ref94","first-page":"1","article-title":"How powerful are performance predictors in neural architecture search?","volume-title":"Proc. NeurIPS","author":"White"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref96","first-page":"1","article-title":"Stronger NAS with weaker predictors","volume-title":"Proc. NeurIPS","author":"Wu"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/tevc.2023.3264533"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref99","first-page":"1","article-title":"SNAS: Stochastic neural architecture search","volume-title":"Proc. ICLR","author":"Xie"},{"key":"ref100","article-title":"BenchENAS: A benchmarking platform for evolutionary neural architecture search","author":"Xie","year":"2021","journal-title":"arXiv:2108.03856"},{"key":"ref101","first-page":"1","article-title":"PC-DARTS: Partial channel connections for memory-efficient architecture search","volume-title":"Proc. ICLR","author":"Xu"},{"key":"ref102","article-title":"CATE: Computation-aware neural architecture encoding with transformers","author":"Yan","year":"2021","journal-title":"arXiv:2102.07108"},{"key":"ref103","first-page":"1","article-title":"Does unsupervised architecture representation learning help neural architecture search?","volume-title":"Proc. NeurIPS","author":"Yan"},{"key":"ref104","first-page":"1","article-title":"NAS evaluation is frustratingly hard","volume-title":"Proc. ICLR","author":"Yang"},{"key":"ref105","first-page":"1","article-title":"NAS-Bench-101: Towards reproducible neural architecture search","volume-title":"Proc. ICML","author":"Ying"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref107","article-title":"Neural ensemble search for uncertainty estimation and dataset shift","author":"Zaidi","year":"2020","journal-title":"arXiv:2006.08573"},{"key":"ref108","first-page":"1","article-title":"Neural ensemble search for uncertainty estimation and dataset shift","volume-title":"Proc. NeurIPS","author":"Zaidi"},{"key":"ref109","first-page":"1","article-title":"Understanding and robustifying differentiable architecture search","volume-title":"Proc. ICLR","author":"Zela"},{"key":"ref110","first-page":"1","article-title":"Towards automated deep learning: Efficient joint neural architecture and hyperparameter search","volume-title":"Proc. ICML Workshop AutoML","author":"Zela"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01076"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082316"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00257"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082701"},{"key":"ref115","first-page":"1","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. ICLR","author":"Zoph"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10877690\/10302315.pdf?arnumber=10302315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T07:11:25Z","timestamp":1738912285000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10302315\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":116,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3326648","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}