| 块对角子空间聚类中成对约束的主动式学习 |
| |
| 引用本文： | 解子奇,王立宏,李嫚. 块对角子空间聚类中成对约束的主动式学习[J]. 山东大学学报(工学版), 2021, 51(2): 65-73. DOI: 10.6040/j.issn.1672-3961.0.2020.182 |
| |
| 作者姓名： | 解子奇 王立宏 李嫚 |
| |
| 作者单位： | 烟台大学计算机与控制工程学院,山东烟台264005 |
| |
| 基金项目： | 国家自然科学基金资助项目(61773331,72072154) |
| |
| 摘 要： | 针对块对角表示(block diagonal representation, BDR)子空间聚类算法在对子空间重叠的高维数据聚类时效果较差的问题,提出成对约束的块对角子空间聚类(constrained subspace clustering with block diagonal representation, CBDR)算法,设计主动式学习策略,获取用户提供的少量数据点成对信息,以改进BDR算法的性能,给出CBDR算法的目标函数和求解过程。在测试集上的试验结果表明,CBDR算法的聚类错误率和归一化互信息指标比BDR和SBDR(structured block diagonal representation)算法好,而且主动式选取点对方法优于随机选取点对方法,使用少于5‰的约束信息可降低BDR的聚类错误率达到5%以上。
|
| 关 键 词： | 子空间聚类 主动式学习 成对约束 块对角表示 约束聚类 |
Active learning of pairwise constraints in block diagonal subspace clustering |
| |
| XIE Ziqi,WANG Lihong,LI Man. Active learning of pairwise constraints in block diagonal subspace clustering[J]. Journal of Shandong University of Technology, 2021, 51(2): 65-73. DOI: 10.6040/j.issn.1672-3961.0.2020.182 |
| |
| Authors: | XIE Ziqi WANG Lihong LI Man |
| |
| Affiliation: | School of Computer and Control Engineering, Yantai University, Yantai 264005, Shandong, China |
| |
| Abstract: | Focusing on the poor performance of subspace clustering by block diagonal representation(BDR)on high-dimensional data with overlapped subspaces, an active learning strategy was designed to obtain partial pairwise information among a few data points. A pairwise constrained block diagonal representation algorithm(CBDR)was proposed to improve the performance of the BDR algorithm. The objective function and solution process of the CBDR were given. The experimental results on the test datasets showed that the CBDR algorithm reduced the clustering error by more than 5% with less than 5‰ constraint information in terms of clustering error and normalized mutual information, which significantly outperformed the compared algorithms, i.e., BDR, SBDR(structured block diagonal representation)with random selection of pairwise constraints. |
| |
| Keywords: | subspace clustering active learning pairwise constraints block diagonal representation constrained clustering |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《山东大学学报(工学版)》浏览原始摘要信息 |
|
点击此处可从《山东大学学报(工学版)》下载全文 |
|
