2022年5月7日 · First, the SLMEA explores the mapping relationship between data and labels by constructing a pseudo label matrix, and at the same time, it combines learning in sparse low-dimensional space to gradually characterize the relationship between features and clusters.

2024年3月4日 · 近年来，为解决大规模优化问题，出现了许多多目标进化算法（MOEAs），这些算法基于变量分组、问题转换、新变异操作和概率模型。 这些MOEAs从多种角度接近高维决策空间，包括基于变量分组的MOEAs的分而治之搜索、基于问题转换的MOEAs的降维、基于新变异操作的MOEAs的旋转不变性以及通过基于概率模型的MOEAs增强收敛性。 然而，在仅使用少数 函数 评估时，它们在大规模SMOPs上的性能会恶化，因为这些算法没有考虑SMOPs最优解的稀疏 …

SLMEA serves as the first attempt for super-large-scale multi-objective optimization; SLMEA solves problems with up to one million variables in the experiments; SLMEA is a totally black-box algorithm without using problem-specific information; SLMEA has simple procedures that can be fully accelerated by GPUs

2024年7月1日 · SLMEA (Tian et al., 2023) is an algorithm customized for dealing with sparse LSMOPs whose search space is extremely large. It achieves the dimensionality reduction by suggesting a sparsity similarity based fast clustering method, which enables it to solve the problems having 1,000,000 decision variables.

dimensional representation with maximum entropy adaptive graph (SLMEA). Firstly, the SLMEA combi-nes the sparse transform representation with pseudo-label matrix learning to optimize,...

2020年6月30日 · 多目标优化问题（MaOP）是指涉及三个以上同时要优化的冲突目标的问题，这些问题广泛存在于实际应用中，例如工程设计 [1]，空中交通管制 [2]，地下水监测 [3]和分子设计 [4]。 一般而言，MaOPs不能通过大多数旨在解决通常只涉及2-3个目标 [5]- [9]的传统多目标优化问题（MOP）的多目标进化算法（MOEA）来解决。 这主要是因为两个问题， 第一个问题是 收敛压力 的损失，这主要是由称为“主支配阻力”的现象引起的 [1]。 这是由于以下事实：在超多目标 …

2025年2月1日 · Therefore, this paper proposes a sparse large-scale multi-objective evolutionary algorithm based on sparsity detection. The proposed algorithm uses the two-layer encoding scheme with a specialized focus on finding the positions of sparse non-zero variables by optimizing the binary vector.

The comparative results, based on four performance indicators—hypervolume (HV), inverted generational distance (IGD), averaged Hausdorff distance $\left ({{ \Delta _{p} }}\right)$ , and spread—reveal that SLMEA emerged as the best algorithm, not only for RWMOP-BEV but also across other benchmark sets, including DTLZ problems and other real ...

2025年2月16日 · SLMEA算法，即Self-Organizing Localized Feature Extraction and Mining Algorithm，是一种新颖的高效数据挖掘算法。 它结合了自组织映射（Self-Organizing Map, SOM）和局部特征提取（Localized Feature Extraction, LFE）的方法，旨在解决传统数据挖掘算法在处理高维、复杂数据时的局限性

2024年5月8日 · SLMEA is specialized for super-large-scale sparse multi-objective problems. For fair comparisons, all algorithms adopt the maximum number of function evaluations ( MaxFE ) of 20000 and the population size ( N ) of 200.