.png){kind=icon}
返回
MEL: Efficient Multi-Task Evolutionary Learning for High-Dimensional Feature Selection
.png){kind=icon}
OA
AI
DOI：10.1109/TKDE.2024.3366333.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Feature selection is a crucial step in data mining to enhance model performance by reducing data dimensionality. However, the increasing dimensionality of collected data exacerbates the challenge known as the curse of dimensionality, where computation grows exponentially with the number of dimensions. To tackle this issue, evolutionary computational (EC) approaches have gained popularity due to their simplicity and applicability. Unfortunately, the diverse designs of EC methods result in varying abilities to handle different data, often underutilizing and not sharing information effectively. In this article, we propose a novel approach called PSO-based Multi-task Evolutionary Learning (MEL) that leverages multi-task learning to address these challenges. By incorporating information sharing between different feature selection tasks, MEL achieves enhanced learning ability and efficiency. We evaluate the effectiveness of MEL through extensive experiments on 22 high-dimensional datasets. Comparing against 24 EC approaches, our method exhibits strong competitiveness. In addition, we have open-sourced our code on GitHub.
Keyword:
Feature extraction
Task analysis
Multitasking
Statistics
Sociology
Vectors
Particle swarm optimization
Feature selection
high-dimensional classification
knowledge transfer
multi-task learning
particle swarm optimization
期刊
IF:
10.4
论文数:
6.8K
被引数:
3.2W
机构
引用论文
Kinematic and kinetic differences in the execution of vertical jumps between people with good and poor ankle joint dorsiflexion踝关节背屈良好和不良的人在执行垂直跳跃时的运动学和动力学差异
PREAI
分享收藏分享收藏分享收藏Majority scoring with backward elimination in PLS for high dimensional spectrum data.png)
SCIENTIFIC REPORTS
OAAI
SCIENTIFIC REPORTSIF3.9
OAAI分享收藏
查看更多内容