Higher-dimension Tensor Completion via Low-rank Tensor Ring Decomposition
share
The problem of incomplete data is common in signal processing and machine learning. Tensor completion aims to recover an incomplete tensor data from its partially observed entries. In this paper, based on recently proposed tensor ring (TR) decomposition, we propose a new tensor completion approach named tensor ring weighted optimization (TR-WOPT). It finds the latent factors of the incomplete tensor by gradient descent algorithm, then the latent factors are employed to predict the missing entries of the tensor. We conduct tensor completion experiments on synthetic data and real-world data. The simulation results show that TR-WOPT performs well and is robust to high-dimension tensor. Image completion results show that the proposed algorithm outperforms the state-of-the-art algorithms in many situations, especially when the image is tensorized to a higher-dimension, better performance can be obtained from our TR-WOPT algorithm.
READ FULL TEXT
