A High-Dimensional Multi-Task Multi-Objective Feature Selection Algorithm Based on Feature Redundancy Analysis

ZHU Miao-miao; YAO Xiang-juan; GONG Dun-wei; ZHANG Yan

doi:10.12263/DZXB.20250405

您当前的位置：

首页 >

文章列表页 >

A High-Dimensional Multi-Task Multi-Objective Feature Selection Algorithm Based on Feature Redundancy Analysis

PAPERS | 更新时间：2025-12-10

- A High-Dimensional Multi-Task Multi-Objective Feature Selection Algorithm Based on Feature Redundancy Analysis
- ACTA ELECTRONICA SINICA Vol. 53, Issue 7, Pages: 2342-2357(2025)
- 作者机构：
  
  1.中国矿业大学数学学院，江苏徐州 221116
  2.青岛科技大学自动化与电子工程学院，山东青岛 266061
  3.宿迁学院信息工程学院，江苏宿迁 223800
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62373357)
- DOI：10.12263/DZXB.20250405
  CLC： TP18;O29
- Received：22 May 2025，
  
  Revised：2025-06-27，
  
  Published：25 July 2025
- 稿件说明：
移动端阅览
朱苗苗, 姚香娟, 巩敦卫, 等. 基于特征冗余分析的高维多任务多目标特征选择算法[J]. 电子学报, 2025, 53(07): 2342-2357.

ZHU Miao-miao, YAO Xiang-juan, GONG Dun-wei, et al. A High-Dimensional Multi-Task Multi-Objective Feature Selection Algorithm Based on Feature Redundancy Analysis[J]. Acta Electronica Sinica, 2025, 53(07): 2342-2357.
朱苗苗, 姚香娟, 巩敦卫, 等. 基于特征冗余分析的高维多任务多目标特征选择算法[J]. 电子学报, 2025, 53(07): 2342-2357. DOI：10.12263/DZXB.20250405

ZHU Miao-miao, YAO Xiang-juan, GONG Dun-wei, et al. A High-Dimensional Multi-Task Multi-Objective Feature Selection Algorithm Based on Feature Redundancy Analysis[J]. Acta Electronica Sinica, 2025, 53(07): 2342-2357. DOI：10.12263/DZXB.20250405

摘要

在处理高维分类数据集时，多目标特征选择进化算法存在计算资源耗费高、收敛速度慢的问题.多任务优化作为一种可以有效降低搜索维度、提升搜索效率的手段，已被引入该领域，但现有算法多仅考虑特征重要性，忽视了特征间的冗余关系.针对这一不足，本文提出了一种基于特征冗余分析的多任务多目标特征选择算法MTGA.该算法首先基于特征冗余度对所有特征进行聚类，将高维特征划分为多个冗余度较低的特征簇.随后从各个特征簇中选择少量的重要特征构建多个子任务，在保留关键信息的同时有效剔除大量冗余特征.此外，针对各子任务，设计了基于特征重要性的繁殖算子，并通过知识迁移策略实现不同子任务间的重要特征共享，避免算法陷入局部最优.在14个高维UCI数据集上的对比实验结果表明，所提算法优于多种经典特征选择方法，展现出良好性能.

Abstract

Evolutionary multi-objective feature selection algorithms face challenges such as high computational cost and slow convergence when addressing high-dimensional classification datasets. Multi-task optimization has emerged as an effective paradigm to reduce search dimensionality and improve efficiency

and has been increasingly applied to this domain. Nevertheless

existing approaches predominantly focus on feature importance while neglecting redundancy relationships among features

which may compromise optimization performance. To overcome this limitation

this study proposes a novel evolutionary multi-task multi-objective feature selection algorithm based on feature redundancy analysis

referred to as MTGA. The proposed method first clusters all features according to their redundancy metrics

dividing the high-dimensional space into low-redundancy clusters. Then

different features are selected from each cluster to construct multiple subtasks

thereby preserving key information while eliminating redundancy. For each subtask

a new reproduction operator is designed based on feature importance. Additionally

a knowledge transfer mechanism facilitates the sharing of important features across subtasks

mitigating the risk of premature convergence. To validate the proposed algorithm

extensive experiments are conducted on fourteen high-dimensional UCI benchmark datasets. The results demonstrate that MTGA outperforms multiple classical feature selection methods

exhibiting excellent performance.

关键词

Keywords

references

MNIH V , KAVUKCUOGLU K , SILVER D , et al . Human-level control through deep reinforcement learning [J ] . Nature , 2015 , 518 ( 7540 ): 529 - 533 .

YOUNG T , HAZARIKA D , PORIA S , et al . Recent trends in deep learning based natural language processing [review article] [J ] . IEEE Computational Intelligence Magazine , 2018 , 13 ( 3 ): 55 - 75 .

黄铉 . 特征降维技术的研究与进展 [J ] . 计算机科学 , 2018 , 45 ( B06 ): 16 - 21, 53 .

HUANG X . Research and development of feature dimensionality reduction [J ] . Computer Science , 2018 , 45 ( B06 ): 16 - 21, 53 . (in Chinese)

LI J D , CHENG K W , WANG S H , et al . Feature selection: A data perspective [J ] . ACM Computing Surveys , 2018 , 50 ( 6 ): 1 - 45 .

刘晓明 , 李丞正旭 , 吴少聪 , 等 . 文本分类算法及其应用场景研究综述 [J ] . 计算机学报 , 2024 , 47 ( 6 ): 1244 - 1287 .

LIU X M , LI C Z X , WU S C , et al . A survey of text classification algorithms and application scenarios [J ] . Chinese Journal of Computers , 2024 , 47 ( 6 ): 1244 - 1287 . (in Chinese)

GUYON I , ELISSEEFF A . An introduction to variable and feature selection [J ] . Journal of Machine Learning Research , 2003 ( 3 ): 1157 - 1182 .

PENG H C , LONG F H , DING C . Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2005 , 27 ( 8 ): 1226 - 1238 .

HANCER E , XUE B , ZHANG M . Differential evolution for filter feature selection based on information theory and feature ranking [J ] . Knowledge-Based Systems , 2018 , 140 : 103 - 119 .

JIANG L X , KONG G G , LI C Q . Wrapper framework for test-cost-sensitive feature selection [J ] . IEEE Transactions on Systems, Man, and Cybernetics: Systems , 2021 , 51 ( 3 ): 1747 - 1756 .

GUYON I , WESTON J , BARNHILL S , et al . Gene selection for cancer classification using support vector machines [J ] . Machine Learning , 2002 , 46 ( 1 ): 389 - 422 .

王艳丽 , 梁静 , 薛冰 , 等 . 基于进化计算的特征选择方法研究概述 [J ] . 郑州大学学报(工学版) , 2020 , 41 ( 1 ): 49 - 57 .

WANG Y L , LIANG J , XUE B , et al . Research on evolutionary computation for feature selection [J ] . Journal of Zhengzhou University (Engineering Science) , 2020 , 41 ( 1 ): 49 - 57 . (in Chinese)

高慧敏 , 王云鹤 , 卞闯 , 等 . 基于混合进化算法的特征选择方法研究 [J ] . 电子学报 , 2023 , 51 ( 6 ): 1619 - 1636 .

GAO H M , WANG Y H , BIAN C , et al . Research on feature selection based on hybrid evolutionary algorithm [J ] . Acta Electronica Sinica , 2023 , 51 ( 6 ): 1619 - 1636 . (in Chinese)

TAN F , FU X Z , ZHANG Y Q , et al . A genetic algorithm-based method for feature subset selection [J ] . Soft Computing , 2008 , 12 ( 2 ): 111 - 120 .

XUE B , ZHANG M J , BROWNE W N . Particle swarm optimisation for feature selection in classification: Novel initialisation and updating mechanisms [J ] . Applied Soft Computing , 2014 , 18 : 261 - 276 .

KASHEF S , NEZAMABADI-POUR H . An advanced ACO algorithm for feature subset selection [J ] . Neurocomputing , 2015 , 147 : 271 - 279 .

JIAO R W , NGUYEN B H , XUE B , et al . A survey on evolutionary multiobjective feature selection in classification: Approaches, applications, and challenges [J ] . IEEE Transactions on Evolutionary Computation , 2024 , 28 ( 4 ): 1156 - 1176 .

NGUYEN B H , XUE B , ANDREAE P , et al . Multiple reference points-based decomposition for multiobjective feature selection in classification: Static and dynamic mechanisms [J ] . IEEE Transactions on Evolutionary Computation , 2020 , 24 ( 1 ): 170 - 184 .

XU H , XUE B , ZHANG M J . A duplication analysis-based evolutionary algorithm for biobjective feature selection [J ] . IEEE Transactions on Evolutionary Computation , 2021 , 25 ( 2 ): 205 - 218 .

HAN F , CHEN W T , LING Q H , et al . Multi-objective particle swarm optimization with adaptive strategies for feature selection [J ] . Swarm and Evolutionary Computation , 2021 , 62 : 100847 .

CHEN K , XUE B , ZHANG M , et al . Evolutionary multitasking for feature selection in high-dimensional classification via particle swarm optimization [J ] . IEEE Transactions on Evolutionary Computation , 2021 , 26 ( 3 ): 446 - 460 .

李豪 , 汪磊 , 张元侨 , 等 . 演化多任务优化研究综述 [J ] . 软件学报 , 2023 , 34 ( 2 ): 509 - 538 .

LI H , WANG L , ZHANG Y Q , et al . Survey of evolutionary multitasking optimization [J ] . Journal of Software , 2023 , 34 ( 2 ): 509 - 538 . (in Chinese)

林炜星 , 王宇嘉 , 陈万芬 , 等 . 基于多因子粒子群的高维数据特征选择算法 [J ] . 计算机工程与应用 , 2021 , 57 ( 22 ): 199 - 207 .

LIN W X , WANG Y J , CHEN W F , et al . High-dimensional data feature selection algorithm based on multifactor particle swarm optimization [J ] . Computer Engineering and Applications , 2021 , 57 ( 22 ): 199 - 207 . (in Chinese)

LI L J , XUAN M L , LIN Q Z , et al . An evolutionary multitasking algorithm with multiple filtering for high-dimensional feature selection [J ] . IEEE Transactions on Evolutionary Computation , 2023 , 27 ( 4 ): 802 - 816 .

FENG Y , FENG L , LIU S , et al . Towards multi-objective high-dimensional feature selection via evolutionary multitasking [J ] . Swarm and Evolutionary Computation , 2024 , 89 : 101618 .

LIN J B , CHEN Q , XUE B , et al . Evolutionary multitasking for multiobjective feature selection in classification [J ] . IEEE Transactions on Evolutionary Computation , 2024 , 28 ( 6 ): 1852 - 1866 .

XU H , XUE B , ZHANG M J . An adaptive initialization and multitasking based evolutionary algorithm for bi-objective feature selection in classification [J ] . Complex & Intelligent Systems , 2025 , 11 ( 7 ): 310 .

张梦婷 , 杜建强 , 罗计根 , 等 . 多目标优化特征选择研究综述 [J ] . 计算机工程与应用 , 2023 , 59 ( 3 ): 23 - 32 .

ZHANG M T , DU J Q , LUO J G , et al . Research on feature selection of multi-objective optimization [J ] . Computer Engineering and Applications , 2023 , 59 ( 3 ): 23 - 32 . (in Chinese)

王朝 , 黄慧涛 , 张晶 , 等 . 基于解空间降维的大规模约束多目标进化算法 [J ] . 电子学报 , 2023 , 51 ( 11 ): 3120 - 3127 .

WANG C , HUANG H T , ZHANG J , et al . A large-scale constrained multi-objective optimization algorithm based on solution space reduction [J ] . Acta Electronica Sinica , 2023 , 51 ( 11 ): 3120 - 3127 . (in Chinese)

YU L , LIU H . Feature selection for high-dimensional data: A fast correlation-based filter solution [C ] // Proceedings of the 20th International Conference on Machine Learning (ICML-03) . California : AAAI , 2003 : 856 - 863 .

COVER T M . Elements of Information Theory [M ] . New Jersey : John Wiley & Sons , 1999 .

ARTHUR D , VASSILVITSKII S . K-means++: The Advantages of Careful Seeding [R ] . California : Stanford University , 2008 .

JAIN A K . Data clustering: 50 years beyond K-means [J ] . Pattern Recognition Letters , 2010 , 31 ( 8 ): 651 - 666 .

ZHANG Q F , LI H . MOEA/D: A multiobjective evolutionary algorithm based on decomposition [J ] . IEEE Transactions on Evolutionary Computation , 2007 , 11 ( 6 ): 712 - 731 .

DEB K , PRATAP A , AGARWAL S , et al . A fast and elitist multiobjective genetic algorithm: NSGA-II [J ] . IEEE Transactions on Evolutionary Computation , 2002 , 6 ( 2 ): 182 - 197 .

CHENG F , CHU F X , XU Y , et al . A steering-matrix-based multiobjective evolutionary algorithm for high-dimensional feature selection [J ] . IEEE Transactions on Cybernetics , 2022 , 52 ( 9 ): 9695 - 9708 .

CHENG F , CUI J , WANG Q , et al . A variable granularity search-based multiobjective feature selection algorithm for high-dimensional data classification [J ] . IEEE Transactions on Evolutionary Computation , 2022 , 27 ( 2 ): 266 - 280 .

JIAO R W , XUE B , ZHANG M J . Solving multiobjective feature selection problems in classification via problem reformulation and duplication handling [J ] . IEEE Transactions on Evolutionary Computation , 2024 , 28 ( 4 ): 846 - 860 .

KOHAVI R , JOHN G H . Wrappers for feature subset selection [J ] . Artificial Intelligence , 1997 , 97 ( 1/2 ): 273 - 324 .

ZITZLER E . Evolutionary Algorithms for Multi-Objective Optimization: Methods and Applications [M ] . Ithaca : Shaker , 1999 .

BOSMAN P A N , THIERENS D . The balance between proximity and diversity in multiobjective evolutionary algorithms [J ] . IEEE Transactions on Evolutionary Computation , 2003 , 7 ( 2 ): 174 - 188 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Stepwise Diversity Metric for MOEA

Multi-Objective Chaotic Evolutionary Algorithm

A Study on How to Use Angle Information to Include Decision Maker's Preferences

Related Author

ZHU Qing-bao

BAO Pei-ming

YANG Ping

XIE Jiong-liang

ZHENG Jin-hua

LI Mi-qing

LI Jing

LEI De-ming

Related Institution

Nanjing Normal University Computer Department

Institute of Information Engineering,Xiangtan University

Intelligent Transportation Systems Center,Wuhan University of Technology

School of Automation, Wuhan University of Technology

Institution of Automation,Shanghai Jiaotong University

⁰