{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T20:34:52Z","timestamp":1776112492018,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61832001"],"award-info":[{"award-number":["61832001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,14]]},"DOI":"10.1145\/3534678.3539255","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:12Z","timestamp":1660331172000},"page":"956-966","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["TransBO: Hyperparameter Optimization via Two-Phase Transfer Learning"],"prefix":"10.1145","author":[{"given":"Yang","family":"Li","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}]},{"given":"Yu","family":"Shen","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"given":"Huaijun","family":"Jiang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"given":"Wentao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"given":"Zhi","family":"Yang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"given":"Ce","family":"Zhang","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"given":"Bin","family":"Cui","sequence":"additional","affiliation":[{"name":"Peking University, Zurich, China"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"R\u00e9mi Bardenet M\u00e1ty\u00e1s Brendel Bal\u00e1zs K\u00e9gl and Michele Sebag. 2013. Collaborative hyperparameter tuning. In ICML. 199--207."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68860-0_2"},{"key":"e_1_3_2_2_3_1","first-page":"281","article-title":"Random search for hyper-parameter optimization","author":"Bergstra James","year":"2012","unstructured":"James Bergstra and Yoshua Bengio. 2012. Random search for hyper-parameter optimization. Journal of Machine Learning Research 13, Feb (2012), 281--305.","journal-title":"Journal of Machine Learning Research 13"},{"key":"e_1_3_2_2_4_1","unstructured":"James S Bergstra R\u00e9mi Bardenet Yoshua Bengio and Bal\u00e1zs K\u00e9gl. 2011. Algorithms for hyper-parameter optimization. In Advances in neural information processing systems. 2546--2554."},{"key":"e_1_3_2_2_5_1","unstructured":"Bernd Bischl Martin Binder Michel Lang Tobias Pielok Jakob Richter Stefan Coors Janek Thomas Theresa Ullmann Marc Becker Anne-Laure Boulesteix et al. 2021. Hyperparameter optimization: Foundations algorithms best practices and open challenges. arXiv preprint arXiv:2107.05847 (2021)."},{"key":"e_1_3_2_2_6_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_7_1","volume-title":"International Conference on Learning Representations.","author":"Dong Xuanyi","year":"2019","unstructured":"Xuanyi Dong and Yi Yang. 2019. NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_8_1","volume-title":"BRP-NAS: Prediction-based NAS using GCNs. Advances in Neural Information Processing Systems 33","author":"Dudziak Lukasz","year":"2020","unstructured":"Lukasz Dudziak, Thomas Chau, Mohamed Abdelfattah, Royson Lee, Hyeji Kim, and Nicholas Lane. 2020. BRP-NAS: Prediction-based NAS using GCNs. Advances in Neural Information Processing Systems 33 (2020)."},{"key":"e_1_3_2_2_9_1","volume-title":"BOHB: Robust and Efficient Hyperparameter Optimization at Scale.. In ICML. 1436--1445.","author":"Falkner Stefan","year":"2018","unstructured":"Stefan Falkner, Aaron Klein, and Frank Hutter. 2018. BOHB: Robust and Efficient Hyperparameter Optimization at Scale.. In ICML. 1436--1445."},{"key":"e_1_3_2_2_10_1","unstructured":"Matthias Feurer Aaron Klein Katharina Eggensperger Jost Springenberg Manuel Blum and Frank Hutter. 2015. Efficient and robust automated machine learning. In Advances in neural information processing systems. 2962--2970."},{"key":"e_1_3_2_2_11_1","volume-title":"AutoML Workshop at ICML.","author":"Feurer Matthias","year":"2018","unstructured":"Matthias Feurer, Benjamin Letham, and Eytan Bakshy. 2018. Scalable metalearning for bayesian optimization using ranking-weighted gaussian process ensembles. In AutoML Workshop at ICML."},{"key":"e_1_3_2_2_12_1","volume-title":"Thomas Rainforth, and Noah Goodman.","author":"Foster Adam","year":"2019","unstructured":"Adam Foster, Martin Jankowiak, Elias Bingham, Paul Horsfall, Yee Whye Teh, Thomas Rainforth, and Noah Goodman. 2019. Variational Bayesian optimal experimental design. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098043"},{"key":"e_1_3_2_2_14_1","volume-title":"Deep learning","author":"Goodfellow Ian","unstructured":"Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep learning. MIT press."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.01.012"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Geoffrey Hinton Li Deng Dong Yu George E Dahl Abdel-rahman Mohamed Navdeep Jaitly Andrew Senior Vincent Vanhoucke Patrick Nguyen Tara N Sainath et al. 2012. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal processing magazine 29 6 (2012) 82--97.","DOI":"10.1109\/MSP.2012.2205597"},{"key":"e_1_3_2_2_19_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 1378--1386","author":"Horv\u00e1th Samuel","year":"2021","unstructured":"Samuel Horv\u00e1th, Aaron Klein, Peter Richt\u00e1rik, and C\u00e9dric Archambeau. 2021. Hyperparameter transfer learning with adaptive complexity. In International Conference on Artificial Intelligence and Statistics. PMLR, 1378--1386."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25566-3_40"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008306431147"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-31753-3_9"},{"key":"e_1_3_2_2_23_1","unstructured":"Kirthevasan Kandasamy Gautam Dasarathy Jeff Schneider and Barnab\u00e1s P\u00f3czos. 2017. Multi-fidelity bayesian optimisation with continuous approximations. In ICML. PMLR 1799--1808."},{"key":"e_1_3_2_2_24_1","volume-title":"Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems 30","author":"Ke Guolin","year":"2017","unstructured":"Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_2_25_1","volume-title":"Learning to Transfer Initializations for Bayesian Hyperparameter Optimization. ArXiv abs\/1710.06219","author":"Kim Jungtaek","year":"2017","unstructured":"Jungtaek Kim, Saehoon Kim, and Seungjin Choi. 2017. Learning to Transfer Initializations for Bayesian Hyperparameter Optimization. ArXiv abs\/1710.06219 (2017)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1214\/17-EJS1335SI"},{"key":"e_1_3_2_2_27_1","volume-title":"Jost Tobias Springenberg, and F. Hutter","author":"Klein Aaron","year":"2017","unstructured":"Aaron Klein, S. Falkner, Jost Tobias Springenberg, and F. Hutter. 2017. Learning Curve Prediction with Bayesian Neural Networks. In ICLR."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/192115.192124"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5910"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.14778\/3514061.3514071"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17031"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467061"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476270"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11532"},{"key":"e_1_3_2_2_35_1","volume-title":"SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization. ArXiv abs\/2109.09831","author":"Lindauer Marius Thomas","year":"2021","unstructured":"Marius Thomas Lindauer, Katharina Eggensperger, Matthias Feurer, Andr'e Biedenkapp, Difan Deng, Caroline Benjamins, Ren\u00e9 Sass, and Frank Hutter. 2021. SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization. ArXiv abs\/2109.09831 (2021)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_3_2_2_38_1","unstructured":"David Pardoe and Peter Stone. 2010. Boosting for regression transfer. In ICML. 863--870."},{"key":"e_1_3_2_2_39_1","volume-title":"Scalable hyperparameter transfer learning. Advances in neural information processing systems 31","author":"Perrone Valerio","year":"2018","unstructured":"Valerio Perrone, Rodolphe Jenatton, Matthias W Seeger, and C\u00e9dric Archambeau. 2018. Scalable hyperparameter transfer learning. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_2_40_1","volume-title":"Learning search spaces for bayesian optimization: Another view of hyperparameter transfer learning. Advances in Neural Information Processing Systems 32","author":"Perrone Valerio","year":"2019","unstructured":"Valerio Perrone, Huibin Shen, Matthias W Seeger, Cedric Archambeau, and Rodolphe Jenatton. 2019. Learning search spaces for bayesian optimization: Another view of hyperparameter transfer learning. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_2_41_1","unstructured":"Matthias Poloczek JialeiWang and Peter Frazier. 2017. Multi-information source optimization. In Advances in Neural Information Processing Systems. 4288--4298."},{"key":"e_1_3_2_2_42_1","volume-title":"Advanced lectures on machine learning","author":"Rasmussen Carl Edward","unstructured":"Carl Edward Rasmussen. 2004. Gaussian processes in machine learning. In Advanced lectures on machine learning. Springer, 63--71."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"e_1_3_2_2_44_1","unstructured":"David Salinas Huibin Shen and Valerio Perrone. 2020. A quantile-based approach for hyperparameter transfer learning. In ICML. PMLR 8438--8448."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"crossref","unstructured":"Nicolas Schilling Martin Wistuba Lucas Drumond and Lars Schmidt-Thieme. 2015. Hyperparameter optimization with factorized multilayer perceptrons. In ECML PKDD. 87--103.","DOI":"10.1007\/978-3-319-23525-7_6"},{"key":"e_1_3_2_2_46_1","volume-title":"Scalable hyperparameter optimization with products of gaussian process experts","author":"Schilling Nicolas","unstructured":"Nicolas Schilling, Martin Wistuba, and Lars Schmidt-Thieme. 2016. Scalable hyperparameter optimization with products of gaussian process experts. In ECML PKDD. Springer, 33--48."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2712906"},{"key":"e_1_3_2_2_48_1","unstructured":"Jasper Snoek Hugo Larochelle and Ryan P Adams. 2012. Practical bayesian optimization of machine learning algorithms. In Advances in neural information processing systems. 2951--2959."},{"key":"e_1_3_2_2_49_1","unstructured":"Jasper Snoek Oren Rippel Kevin Swersky Ryan Kiros Nadathur Satish Narayanan Sundaram Mostofa Patwary Mr Prabhat and Ryan Adams. 2015. Scalable bayesian optimization using deep neural networks. In ICML. PMLR 2171--2180."},{"key":"e_1_3_2_2_50_1","volume-title":"Bayesian optimization with robust Bayesian neural networks. Advances in neural information processing systems 29","author":"Springenberg Jost Tobias","year":"2016","unstructured":"Jost Tobias Springenberg, Aaron Klein, Stefan Falkner, and Frank Hutter. 2016. Bayesian optimization with robust Bayesian neural networks. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_2_51_1","volume-title":"Multi-task bayesian optimization. Advances in neural information processing systems 26","author":"Swersky Kevin","year":"2013","unstructured":"Kevin Swersky, Jasper Snoek, and Ryan P Adams. 2013. Multi-task bayesian optimization. Advances in neural information processing systems 26 (2013)."},{"key":"e_1_3_2_2_52_1","volume-title":"Freeze-thaw Bayesian optimization. arXiv preprint arXiv:1406.3896","author":"Swersky Kevin","year":"2014","unstructured":"Kevin Swersky, Jasper Snoek, and Ryan Prescott Adams. 2014. Freeze-thaw Bayesian optimization. arXiv preprint arXiv:1406.3896 (2014)."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2641190.2641198"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"crossref","unstructured":"Pauli Virtanen Ralf Gommers Travis E Oliphant Matt Haberland Tyler Reddy David Cournapeau Evgeni Burovski Pearu Peterson Warren Weckesser Jonathan Bright et al. 2020. SciPy 1.0: fundamental algorithms for scientific computing in Python. Nature methods 17 3 (2020) 261--272.","DOI":"10.1038\/s41592-020-0772-5"},{"key":"e_1_3_2_2_55_1","unstructured":"YingWei Peilin Zhao and Junzhou Huang. 2021. Meta-learning Hyperparameter Performance Prediction with Neural Processes. In ICML. PMLR 11058--11067."},{"key":"e_1_3_2_2_56_1","volume-title":"Hyperparameter search space pruning--a new component for sequential model-based hyperparameter optimization","author":"Wistuba Martin","unstructured":"Martin Wistuba, Nicolas Schilling, and Lars Schmidt-Thieme. 2015. Hyperparameter search space pruning--a new component for sequential model-based hyperparameter optimization. In ECML PKDD. Springer, 104--119."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2015.20"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"crossref","unstructured":"Martin Wistuba Nicolas Schilling and Lars Schmidt-Thieme. 2016. Two-stage transfer surrogate model for automatic hyperparameter optimization. In ECML PKDD. 199--214.","DOI":"10.1007\/978-3-319-46128-1_13"},{"key":"e_1_3_2_2_59_1","volume-title":"Taking Human out of Learning Applications: A Survey on Automated Machine Learning. ArXiv abs\/1810.13306","author":"Yao Quanming","year":"2018","unstructured":"Quanming Yao, Mengshuo Wang, H. Escalante, I. Guyon, Yi-Qi Hu, Yu-Feng Li, Wei-Wei Tu, Qiang Yang, and Yang Yu. 2018. Taking Human out of Learning Applications: A Survey on Automated Machine Learning. ArXiv abs\/1810.13306 (2018)."},{"key":"e_1_3_2_2_60_1","unstructured":"Dani Yogatama and Gideon Mann. 2014. Efficient transfer learning method for automatic hyperparameter tuning. In Artificial Intelligence and Statistics. 1077--1085."}],"event":{"name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Washington DC USA","acronym":"KDD '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539255","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539255","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:59:58Z","timestamp":1750186798000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539255"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":60,"alternative-id":["10.1145\/3534678.3539255","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539255","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}