TY - JOUR
T1 - Dynamic exploration–exploitation trade-off in active learning regression with Bayesian hierarchical modeling
AU - Islam, Upala Junaida
AU - Paynabar, Kamran
AU - Runger, George
AU - Iquebal, Ashif Sikandar
N1 - Publisher Copyright:
© Copyright © 2024 “IISE”.
PY - 2025
Y1 - 2025
N2 - Active learning provides a framework to adaptively query the most informative experiments towards learning an unknown black-box function. Various approaches of active learning have been proposed in the literature, however, they either focus on exploration or exploitation in the design space. Methods that do consider exploration–exploitation simultaneously employ fixed or ad-hoc measures to control the trade-off that may not be optimal. In this article, we develop a Bayesian hierarchical approach, referred to as BHEEM, to dynamically balance the exploration-exploitation trade-off as more data points are queried. To sample from the posterior distribution of the trade-off parameter, we subsequently formulate an approximate Bayesian computation approach based on the linear dependence of queried data in the feature space. Simulated and real-world examples show the proposed approach achieves at least 21% and 11% average improvement when compared to pure exploration and exploitation strategies, respectively. More importantly, we note that by optimally balancing the trade-off between exploration and exploitation, BHEEM performs better or at least as well as either pure exploration or pure exploitation.
AB - Active learning provides a framework to adaptively query the most informative experiments towards learning an unknown black-box function. Various approaches of active learning have been proposed in the literature, however, they either focus on exploration or exploitation in the design space. Methods that do consider exploration–exploitation simultaneously employ fixed or ad-hoc measures to control the trade-off that may not be optimal. In this article, we develop a Bayesian hierarchical approach, referred to as BHEEM, to dynamically balance the exploration-exploitation trade-off as more data points are queried. To sample from the posterior distribution of the trade-off parameter, we subsequently formulate an approximate Bayesian computation approach based on the linear dependence of queried data in the feature space. Simulated and real-world examples show the proposed approach achieves at least 21% and 11% average improvement when compared to pure exploration and exploitation strategies, respectively. More importantly, we note that by optimally balancing the trade-off between exploration and exploitation, BHEEM performs better or at least as well as either pure exploration or pure exploitation.
KW - Active learning regression
KW - Bayesian hierarchical model
KW - approximate Bayesian computation
KW - exploration-exploitation trade-off
UR - http://www.scopus.com/inward/record.url?scp=85190881007&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85190881007&partnerID=8YFLogxK
U2 - 10.1080/24725854.2024.2332910
DO - 10.1080/24725854.2024.2332910
M3 - Article
AN - SCOPUS:85190881007
SN - 2472-5854
VL - 57
SP - 393
EP - 407
JO - IISE Transactions
JF - IISE Transactions
IS - 4
ER -