Affiliations: [a] School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China
| [b] Public Experimental Teaching Center, Sun Yat-sen University, Guangzhou, China
Correspondence:
[*]
Corresponding author. Zhengming Ma, School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China. E-mail: [email protected].
Note: [1] This work was supported in part by Science and Technology Program of Guangzhou, China under Grant 68000-42050001 and National Natural Science Foundation of China under Grant 61773022.
Abstract: Tensor data are becoming more and more common in machine learning. Compared with vector data, the curse of dimensionality of tensor data is more serious. The motivation of this paper is to combine Hilbert-Schmidt Independence Criterion (HSIC) and tensor algebra to create a new dimensionality reduction algorithm for tensor data. There are three contributions in this paper. (1) An HSIC-based algorithm is proposed in which the dimension-reduced tensor is determined by maximizing HSIC between the dimension-reduced and high-dimensional tensors. (2) A tensor algebra-based algorithm is proposed, in which the high-dimensional tensor are projected onto a subspace and the projection coordinate is set to be the dimension-reduced tensor. The subspace is determined by minimizing the distance between the high-dimensional tensor data and their projection in the subspace. (3) By combining the above two algorithms, a new dimensionality reduction algorithm, called PDMHSIC, is proposed, in which the dimensionality reduction must satisfy two criteria at the same time: HSIC maximization and subspace projection distance minimization. The proposed algorithm is a new attempt to combine HSIC with other algorithms to create new algorithms and has achieved better experimental results on 8 commonly-used datasets than the other 7 well-known algorithms.
