摘要
为了降低大规模数据集降维的计算代价,提出一种基于平衡分层K均值的正交无监督图嵌入降维方法。该文给出局部保持投影和谱回归等价的充分必要条件;基于平衡分层K-means的锚生成策略,构建加快局部保持投影求解过程的特殊相似矩阵;再结合正交约束,提出正交化无监督大型图嵌入降维方法;在几种公开数据集上进行扩展实验,结果表明提出的方法能够对大规模数据集实现高效快速的降维。
In order to reduce the computational cost of dimensionality reduction of large-scale data sets,an orthogonal unsupervised graph embedding dimensionality reduction algorithm based on balanced hierarchical K-means is proposed.The necessary and sufficient conditions for locally preserving the equivalence of projection and spectral regression were obtained.An anchor generation strategy based on balanced hierarchical K-means was put forward,and a special similarity matrix was constructed to accelerate the process of local preserving projection.Combined with the orthogonal constraints,an orthogonal unsupervised large-scale graph embedding dimension reduction method is proposed.Experiments on several public data sets show that the proposed method can achieve efficient and fast dimensionality reduction for large-scale data sets.
作者
张志丽
古晓明
王文晶
Zhang Zhili;Gu Xiaoming;Wang Wenjing(Shanxi Insititute of Economic Management,Taiyuan 030024,Shanxi,China;Shanxi Vocational University of Engineering Science and Technology,Taiyuan 030000,Shanxi,China)
出处
《计算机应用与软件》
北大核心
2024年第9期348-356,362,共10页
Computer Applications and Software
基金
山西省教育科学规划课题(HLW-20165)。
关键词
数据降维
平衡分层K均值
局部保持投影
无监督大型图嵌入
Data dimension reduction
Balanced hierarchical K-means
Locality preserving projection
Unsupervised large graph embedding