.png){kind=icon}
返回
Interactive Evolutionary Multiobjective Optimization via Learning to Rank
.png){kind=icon}
OA
AI
DOI：10.1109/TEVC.2023.3234269.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In practical multicriterion decision making, it is cumbersome if a decision maker (DM) is asked to choose among a set of tradeoff alternatives covering the whole Pareto-optimal front. This is a paradox in conventional evolutionary multiobjective optimization (EMO) that always aim to achieve a well balance between convergence and diversity. In essence, the ultimate goal of multiobjective optimization is to help a DM identify solution(s) of interest (SOI) achieving satisfactory tradeoffs among multiple conflicting criteria. Bearing this in mind, this article develops a framework for designing preference-based EMO algorithms to find SOI in an interactive manner. Its core idea is to involve human in the loop of EMO. After every several iterations, the DM is invited to elicit her feedback with regard to a couple of incumbent candidates. By collecting such information, her preference is progressively learned by a learning-to-rank neural network and then applied to guide the baseline EMO algorithm. Note that this framework is so general that any existing EMO algorithm can be applied in a plug-in manner. Experiments on 48 benchmark test problems with up to ten objectives and a real-world multiobjective robot control problem fully demonstrate the effectiveness of our proposed algorithms for finding SOI.
Keyword:
Evolutionary multiobjective optimization (EMO)
gradient descent
learning to rank (LTR)
preference modeling
期刊
IF:
12
论文数:
1.9K
被引数:
2.4W
机构
暂无机构信息
引用论文
Linkage Mapping of Resistance to Reniform Nematode in Cotton following Introgression from Gossypium longicalyx (Hutch. & Lee).png)
Crop Science
Crop ScienceIF0
PREAI
分享收藏Refining Estimates of Bird Collision and Electrocution Mortality at Power Lines in the United StatesPLoS ONE
OAAI
PLoS ONEIF0
OAAI分享收藏Using Choquet integral as preference model in interactive evolutionary multiobjective optimization在交互式进化多目标优化中使用Choquet积分作为偏好模型OAAI
OAAI分享收藏
查看更多内容