版权所有:内蒙古大学图书馆 技术提供:维普资讯• 智图
内蒙古自治区呼和浩特市赛罕区大学西街235号 邮编: 010021
作者机构:Saitama Inst Technol Grad Sch Engn Fukaya Saitama Japan RIKEN Ctr Adv Intelligence Project AIP Tensor Learning Unit Tokyo Japan Guangdong Univ Technol Sch Automat Guangzhou Guangdong Peoples R China Hangzhou Dianzi Univ Sch Comp Sci & Technol Hangzhou Zhejiang Peoples R China
出 版 物:《SIGNAL PROCESSING-IMAGE COMMUNICATION》 (信号处理:图像通信)
年 卷 期:2019年第73卷
页 面:53-61页
核心收录:
基 金:JSPS KAKENHI, Japan [17K00326, 15H04002, 18K04178] JST CREST, Japan [JP-MJCR1784] National Natural Science Foundation of China
主 题:Tensor completion Visual data recovery Tensor train decomposition Higher-order tensorization Gradient-based optimization
摘 要:Tensor train (TT) decomposition has drawn people s attention due to its powerful representation ability and performance stability in high-order tensors. In this paper, we propose a novel approach to recover the missing entries of incomplete data represented by higher-order tensors. We attempt to find the low-rank TT decomposition of the incomplete data which captures the latent features of the whole data and then reconstruct the missing entries. By applying gradient descent algorithms, tensor completion problem is efficiently solved by optimization models. We propose two TT-based algorithms: Tensor Train Weighted Optimization (TT-WOPT) and Tensor Train Stochastic Gradient Descent (IT-SGD) to optimize TT decomposition factors. In addition, a method named Visual Data Tensorization (VDT) is proposed to transform visual data into higher-order tensors, resulting in the performance improvement of our algorithms. The experiments in synthetic data and visual data show high efficiency and performance of our algorithms compared to the state-of-the-art completion algorithms, especially in high-order, high missing rate, and large-scale tensor completion situations.