TY - JOUR
T1 - Detecting Hidden and Irrelevant Objectives in Interactive Multiobjective Optimization
AU - Shavarani, Seyed Mahdi
AU - López-Ibáñez, Manuel
AU - Allmendinger, Richard
PY - 2024/4
Y1 - 2024/4
N2 - Evolutionary multi-objective optimization algorithms (EMOAs) typically assume that all objectives that are relevant to the decision-maker (DM) are optimized by the EMOA. In some scenarios, however, there are irrelevant objectives that are optimized by the EMOA but ignored by the DM, as well as, hidden objectives that the DM considers when judging the utility of solutions but are not optimized. This discrepancy between the EMOA and the DM’s preferences may impede the search for the most-preferred solution and waste resources evaluating irrelevant objectives. Research on objective reduction has focused so far on the structure of the problem and correlations between objectives and neglected the role of the DM. We formally define here the concepts of irrelevant and hidden objectives and propose methods for detecting them, based on uni-variate feature selection and recursive feature elimination, that use the preferences already elicited when a DM interacts with a ranking-based interactive EMOA (iEMOA). We incorporate the detection methods into an iEMOA capable of dynamically switching the objectives being optimized. Our experiments show that this approach can efficiently identify which objectives are relevant to the DM and reduce the number of objectives being optimized, while keeping and often improving the utility, according to the DM, of the best solution found.
AB - Evolutionary multi-objective optimization algorithms (EMOAs) typically assume that all objectives that are relevant to the decision-maker (DM) are optimized by the EMOA. In some scenarios, however, there are irrelevant objectives that are optimized by the EMOA but ignored by the DM, as well as, hidden objectives that the DM considers when judging the utility of solutions but are not optimized. This discrepancy between the EMOA and the DM’s preferences may impede the search for the most-preferred solution and waste resources evaluating irrelevant objectives. Research on objective reduction has focused so far on the structure of the problem and correlations between objectives and neglected the role of the DM. We formally define here the concepts of irrelevant and hidden objectives and propose methods for detecting them, based on uni-variate feature selection and recursive feature elimination, that use the preferences already elicited when a DM interacts with a ranking-based interactive EMOA (iEMOA). We incorporate the detection methods into an iEMOA capable of dynamically switching the objectives being optimized. Our experiments show that this approach can efficiently identify which objectives are relevant to the DM and reduce the number of objectives being optimized, while keeping and often improving the utility, according to the DM, of the best solution found.
KW - Dimension reduction
KW - feature selection
KW - hidden objectives
KW - interactive multiobjective optimization
KW - irrelevant objectives
KW - machine learning
UR - https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=pure_starter&SrcAuth=WosAPI&KeyUT=WOS:001196821000007&DestLinkType=FullRecord&DestApp=WOS_CPL
UR - http://www.scopus.com/inward/record.url?scp=85153797308&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/27b489cb-d0e5-3682-9824-3fc70649d026/
U2 - 10.1109/tevc.2023.3269348
DO - 10.1109/tevc.2023.3269348
M3 - Article
SN - 1089-778X
VL - 28
SP - 544
EP - 557
JO - IEEE Transactions on Evolutionary Computation
JF - IEEE Transactions on Evolutionary Computation
IS - 2
ER -