{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T06:58:37Z","timestamp":1775199517068,"version":"3.50.1"},"reference-count":98,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62025603"],"award-info":[{"award-number":["62025603"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1705262"],"award-info":[{"award-number":["U1705262"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072386"],"award-info":[{"award-number":["62072386"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072387"],"award-info":[{"award-number":["62072387"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072389"],"award-info":[{"award-number":["62072389"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62002305"],"award-info":[{"award-number":["62002305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772443"],"award-info":[{"award-number":["61772443"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61802324"],"award-info":[{"award-number":["61802324"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702136"],"award-info":[{"award-number":["61702136"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2019B1515120049"],"award-info":[{"award-number":["2019B1515120049"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021,9,1]]},"DOI":"10.1109\/tpami.2021.3069250","type":"journal-article","created":{"date-parts":[[2021,3,29]],"date-time":"2021-03-29T21:18:51Z","timestamp":1617052731000},"page":"3091-3107","source":"Crossref","is-referenced-by-count":11,"title":["Evolving Fully Automated Machine Learning via Life-Long Knowledge Anchors"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6855-5403","authenticated-orcid":false,"given":"Xiawu","family":"Zheng","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6064-0777","authenticated-orcid":false,"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Sirui","family":"Hong","sequence":"additional","affiliation":[]},{"given":"Huixia","family":"Li","sequence":"additional","affiliation":[]},{"given":"Lang","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Youcheng","family":"Xiong","sequence":"additional","affiliation":[]},{"given":"Jin","family":"Zhou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4309-3166","authenticated-orcid":false,"given":"Yan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xiaoshuai","family":"Sun","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4310-9140","authenticated-orcid":false,"given":"Pengfei","family":"Zhu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5035-3168","authenticated-orcid":false,"given":"Chenglin","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9163-2932","authenticated-orcid":false,"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref38","article-title":"Progressive neural networks","author":"rusu","year":"2016"},{"key":"ref33","article-title":"DARTS: Differentiable architecture search","author":"liu","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-018-0006-z"},{"key":"ref31","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"bengio","year":"2013"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/72.265960"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2781233"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref35","first-page":"507","article-title":"ELLA: An efficient lifelong learning algorithm","author":"ruvolo","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.1994.407413"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref27","first-page":"5365","article-title":"Weight agnostic neural networks","author":"gaier","year":"2019","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref29","first-page":"524","article-title":"The cascade-correlation learning architecture","author":"fahlman","year":"1990","journal-title":"Advances in Neural Information Processing Systems 2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780195099713.001.0001"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"32","DOI":"10.25080\/Majora-14bd3278-006","article-title":"Hyperopt-Sklearn: automatic hyperparameter configuration for Scikit-learn","author":"komer","year":"2014","journal-title":"Proc 13th Python Sci Conf"},{"key":"ref21","first-page":"405","article-title":"Particle swarm model selection","volume":"10","author":"escalante","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref24","first-page":"2951","article-title":"Practical Bayesian optimization of machine learning algorithms","author":"snoek","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref23","first-page":"2755","article-title":"Efficient and robust automated machine learning","author":"feurer","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref26","first-page":"160","article-title":"Deep clustered convolutional kernels","author":"kim","year":"2015","journal-title":"Proc 1st Int Workshop Feature Extraction Modern Questions Challenges"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205586"},{"key":"ref50","first-page":"667","article-title":"Dynamic filter networks","author":"jia","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2657118"},{"key":"ref59","article-title":"AutoCV challenge design and baseline results","author":"liu","year":"2019","journal-title":"Proc Conf sur l’Apprentissage Automatique"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-60428-6_16"},{"key":"ref57","first-page":"430","article-title":"Using a data metric for preprocessing advice for data mining applications","author":"engels","year":"1998","journal-title":"Proc 13th Eur Conf Artif Intell"},{"key":"ref56","first-page":"1128","article-title":"Initializing Bayesian hyperparameter optimization via meta-learning","author":"feurer","year":"2015","journal-title":"Proc Twenty-Ninth AAAI Conf Artif Intell"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-012-5286-7"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73263-1"},{"key":"ref53","first-page":"907","article-title":"Reinforced continual learning","author":"xu","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref52","article-title":"Lifelong learning with dynamically expandable networks","author":"yoon","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref40","first-page":"6470","article-title":"Gradient episodic memory for continual learning","author":"lopez-paz","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref8","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.126"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref9","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"Comput Vis Pattern Recognit"},{"key":"ref46","article-title":"Overcoming catastrophic forgetting for continual learning via model adaptation","author":"hu","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref45","first-page":"4548","article-title":"Overcoming catastrophic forgetting with hard attention to the task","author":"serr\u00e0","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00332"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref42","first-page":"3987","article-title":"Continual learning through synaptic intelligence","author":"zenke","year":"2017","journal-title":"Proc 34thInt Conf Mach Learn"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"kirkpatrick","year":"2017","journal-title":"Proc Nat Acad Sci USA"},{"key":"ref44","article-title":"Pathnet: Evolution channels gradient descent in super neural networks","author":"fernando","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"ref73","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Human Lang Technol"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139058452"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref70","first-page":"6662","article-title":"Fast autoaugment","author":"lim","year":"2019","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref76","article-title":"Mel-spectrogram augmentation for sequence to sequence voice conversion","author":"hwang","year":"2020"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00139"},{"key":"ref74","article-title":"Kapre: On-GPU audio preprocessing layers for a quick implementation of deep neural network models with Keras","author":"choi","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref75","first-page":"37","article-title":"Audio spectrogram representations for processing with convolutional neural networks","author":"wyse","year":"2017","journal-title":"Proc 1st Int Workshop Deep Learn Music Joint with IJCNN"},{"key":"ref78","article-title":"Dynamic distribution pruning for efficient network architecture search","author":"zheng","year":"2019"},{"key":"ref79","author":"kleinbaum","year":"2002","journal-title":"Logistic Regression"},{"key":"ref60","article-title":"SPEA2: Improving the strength Pareto evolutionary algorithm","author":"zitzler","year":"2001","journal-title":"TIK Report No 103"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref61","first-page":"8007","article-title":"AutoML-Zero: Evolving machine learning algorithms from scratch","author":"real","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref64","article-title":"The kinetics human action video dataset","author":"kay","year":"2017"},{"key":"ref65","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"liu","year":"2019"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref69","first-page":"113","article-title":"Autoaugment: Learning augmentation policies from data","author":"cubuk","year":"2019","journal-title":"Proc IEEE Comput Vis Pattern Recogn"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2014.10.002"},{"key":"ref94","first-page":"202","article-title":"Scaling up the accuracy of naive-bayes classifiers: A decision-tree hybrid.","author":"kohavi","year":"1996","journal-title":"Proc Int Conf Knowl Disc Data Mining"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref92","article-title":"The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions","volume":"5","author":"tschandl","year":"2018","journal-title":"Data Science Journal"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.46"},{"key":"ref90","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref98","first-page":"2546","article-title":"Algorithms for hyper-parameter optimization","author":"bergstra","year":"2011","journal-title":"Proc 24th Int Conf Neural Inf Process Syst"},{"key":"ref96","first-page":"19","article-title":"Results of the active learning challenge","author":"guyon","year":"2011","journal-title":"Proc Active Learn Exp Des Workshop Conjunction AISTATS"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.419"},{"key":"ref10","article-title":"Taking human out of learning applications: A survey on automated machine learning","author":"yao","year":"2018","journal-title":"Artif Intell"},{"key":"ref11","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487629"},{"key":"ref13","article-title":"Neural architecture search with reinforcement learning","author":"zoph","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref14","first-page":"139","article-title":"Autoprognosis: Automated clinical prognostic modeling via Bayesian optimization with structured kernel learning","author":"alaa","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref15","first-page":"1","article-title":"P4ML: A phased performance-based pipeline planner for automated machine learning","author":"gil","year":"2018","journal-title":"Proc Int Conf Mach Learn Workshop"},{"key":"ref16","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref82","first-page":"3149","article-title":"LightGBM: A highly efficient gradient boosting decision tree","author":"ke","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2908812.2908918"},{"key":"ref81","article-title":"Catboost: Gradient boosting with categorical features support","author":"dorogush","year":"2018","journal-title":"Proc 32nd Conf Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref19","first-page":"367","article-title":"Random search and reproducibility for neural architecture search","author":"li","year":"2019","journal-title":"Proc Conf Uncertainty of Artificial Intelligence"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1023\/A:1018628609742"},{"key":"ref89","article-title":"Snapshot ensembles: Train 1, get M for free","author":"huang","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref85","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"Proc NIPS Workshop Deep Learn"},{"key":"ref86","first-page":"161","article-title":"The tradeoffs of large scale learning","author":"bottou","year":"2008","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"ref88","first-page":"1504","article-title":"Equilibrated adaptive learning rates for non-convex optimization","author":"dauphin","year":"2015","journal-title":"Proc Adv Conf Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9506969\/09388886.pdf?arnumber=9388886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:49:23Z","timestamp":1652194163000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9388886\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,1]]},"references-count":98,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3069250","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,1]]}}}