From Joint Feature Selection and Self-Representation Learning to Robust Multi-view Subspace Clustering
From Joint Feature Selection and Self-Representation Learning to Robust Multi-view Subspace Clustering
复制标题
DOI：
10.1109/icdm.2019.00183
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Hui Yan;Siyu Liu;Philip S. Yu
中科院分区：
文献类型：
--
作者：
Hui Yan;Siyu Liu;Philip S. Yu
在大数据时代，我们可以更容易地访问来自异构特征空间的多视图表示的数据，其中每个视图通常是未标记的，部分甚至充满噪声。这些独特的挑战和属性促使我们开发一种新的强大的多视图子空间聚类框架（RMSC），它通过扩展我们的联合特征选择和自表示模型（JFSSR）来学习具有理想子空间结构的共识亲和矩阵。具体地说，RMSC学习不同视图之间的一致性图，这些视图具有恰好k个连接的组件（k是聚类的数量），这些组件由块对角自表示矩阵编码。此外，我们强调l2; 1-范数最小化损失函数，以减少冗余和不相关的功能，并隐式地分配一个自适应的权重，每个视图，而不引入额外的参数。最后，一个交替优化算法来解决非凸制定的目标。在合成数据和真实世界基准数据集上的大量实证结果表明，RMSC始终优于几种代表性的多视图聚类方法。
In era of big data, we have easier access to the data with multi-view representations from heterogeneous feature spaces, where each view is often unlabeled, partial and even full of noises. These unique challenges and properties motivate us to develop a novel robust multi-view subspace clustering framework (RMSC), which learns a consensus affinity matrix with the ideal subspace structure, by extending our joint feature selection and self-representation model (JFSSR). Concretely, RMSC learns the consensus graph across diverse views with exactly k connected components (k is the number of clusters), which is encoded by a block diagonal self-representation matrix. Besides, we emphasize l2;1-norm minimization on the loss function to reduce redundant and irrelevant features, and implicitly assign an adaptive weight to each view without introducing additional parameters. Lastly, an alternating optimization algorithm is derived to solve the nonconvex formulated objective. Extensive empirical results on both synthetic data and real-world benchmark data sets show that RMSC consistently outperforms several representative multiview clustering approaches.