| 引用本文: | 王振宇,王磊.融合PLS子空间对齐和种群重用的多任务优化算法[J].控制理论与应用,2025,42(11):2363~2373.[点击复制] |
| WANG Zhen-yu,WANG Lei.An multi-task optimization algorithm based on PLS subspace alignment and reuse population[J].Control Theory & Applications,2025,42(11):2363~2373.[点击复制] |
|
| 融合PLS子空间对齐和种群重用的多任务优化算法 |
| An multi-task optimization algorithm based on PLS subspace alignment and reuse population |
| 摘要点击 2086 全文点击 125 投稿时间：2024-11-28 修订日期：2025-11-04 |
| 查看全文 查看/发表评论 下载PDF阅读器 HTML |
| DOI编号 10.7641/CTA.2025.40598 |
| 2025,42(11):2363-2373 |
| 中文关键词 多任务优化 知识转移 子空间对齐 种群重用 传感器覆盖问题 |
| 英文关键词 multi-task optimization knowledge transfer subspace alignment reuse population sensor coverage prob lem |
| 基金项目 国家自然科学基金项目(62176146)资助. |
|
| 中文摘要 |
| 通过利用跨任务的知识转移,多任务优化可以实现比传统单任务优化更好的收敛性能.然而,在多任务优
化中,搜索空间和优化场景的偏差以及干扰知识转移的噪声,都可能导致有效知识转移效率的降低,甚至出现负向
迁移. 为解决此问题,本文提出一种基于最小二乘法(PLS)子空间对齐和种群重用机制的多任务优化算法(PR
MTEA). 首先,通过引入PLS子空间投影策略,将高维任务搜索空间向低维空间转化,并建立各任务所拥有种群的特
定低维子空间;其次,实时调整子空间Bregman散度获取对齐矩阵,实现跨任务知识转移;最后,设计基于Residual残
差结构的种群重用机制,避免出现负向迁移和陷入局部最优情况,并提高算法的收敛性能.实验结果表明:与其
他4种先进多任务优化算法进行相比,PR-MTEA具有更好的收敛性能和快速搜索能力.另外,通过传感器覆盖问题
进行测试分析,进一步验证算法的可行性和适用性. |
| 英文摘要 |
| By using cross-task knowledge transfer, multi-task optimization can achieve better convergence performance
than traditional single-task optimization. However, in multi-task optimization, the deviation of the search space and opti
mization scenarios, as well as noise that may interfere with knowledge transfer, can lead to a decrease in the efficiency of
effective knowledge transfer and even negative transfer. An multi-task optimization algorithm based on partial least squares
(PLS) subspace alignment and reuse population mechanism (PR-MTEA) is proposed to solve the problem. Firstly, by intro
ducing the PLS subspace projection strategy, the high-dimensional task search space is transformed into a low-dimensional
space and specific low-dimensional subspaces are established for each task’s population. Secondly, real-time adjustment of
the Bregman divergence of the subspace is used to obtain an alignment matrix and achieve cross-task knowledge transfer.
Finally, a population reuse mechanism based on the Residual structure is designed to avoid negative transfer and getting
stuck in local optima, as well as to improve the convergence of the algorithm. Comparative experimental results with four
other advanced multi-task algorithms show that PR-MTEA has better convergence performance and faster search ability.
In addition, sensor coverage problem is conducted to test and analyze the feasibility and applicability of the improved
algorithm. |
|
|
|
|
|