TransBO: Hyperparameter Optimization via Two-Phase Transfer Learning

被引:6
作者
Li, Yang [1 ]
Shen, Yu [2 ]
Jiang, Huaijun [2 ]
Zhang, Wentao [2 ]
Yang, Zhi [2 ]
Zhang, Ce [3 ]
Cui, Bin [4 ]
机构
[1] Peking Univ Tencent Data Platform, Tencent Inc, Technol & Engn Grp, Sch CS, Beijing, Peoples R China
[2] Peking Univ, Sch CS, Beijing, Peoples R China
[3] Swiss Fed Inst Technol, DS3Lab, Dept Comp Sci, Syst Grp, Zurich, Switzerland
[4] Peking Univ, Sch CS, Inst Computat Social Sci, Beijing, Peoples R China
来源
PROCEEDINGS OF THE 28TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2022 | 2022年
基金
中国国家自然科学基金;
关键词
hyperparameter optimization; black-box optimization; bayesian optimization; transfer learning;
D O I
10.1145/3534678.3539255
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
With the extensive applications of machine learning models, automatic hyperparameter optimization (HPO) has become increasingly important. Motivated by the tuning behaviors of human experts, it is intuitive to leverage auxiliary knowledge from past HPO tasks to accelerate the current HPO task. In this paper, we propose TransBO, a novel two-phase transfer learning framework for HPO, which can deal with the complementary nature among source tasks and dynamics during knowledge aggregation issues simultaneously. This framework extracts and aggregates source and target knowledge jointly and adaptively, where the weights can be learned in a principled manner. The extensive experiments, including static and dynamic transfer learning settings and neural architecture search, demonstrate the superiority of TransBO over the state-of-the-arts.
引用
收藏
页码:956 / 966
页数:11
相关论文
共 60 条
[1]  
[Anonymous], 2015, DATA MINING ICDM 201, DOI DOI 10.1109/ICDM.2015.20
[2]  
[Anonymous], 2017, ADV NEURAL INFORM PR
[3]  
[Anonymous], 2015, ECML PKDD, DOI DOI 10.1007/978-3-319-23525-7_7
[4]  
Aydore S, 2019, ADV NEUR IN, V32
[5]  
Bardenet R., 2013, P INT C MACHINE LEAR, V28, P199, DOI [DOI 10.5555/3042817.3042916, 10.5555/3042817.3042916]
[6]  
Bennett CJ, 2008, PRIVACY ADVOCATES: RESISTING THE SPREAD OF SURVEILLANCE, P25
[7]  
Bergstra J., 2011, P 2011 ANN C NEURAL, V24, DOI DOI 10.5555/2986459.2986743
[8]  
Bergstra J, 2012, J MACH LEARN RES, V13, P281
[9]  
Bischl Bernd, 2021, ARXIV210705847
[10]  
Devlin J, 2019, 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, P4171