A high-order tensor completion algorithm based on Fully-Connected Tensor Network weighted optimization
This addresses tensor completion for applications in deep learning and signal processing, representing an incremental improvement over existing FCTN methods.
The paper tackles the problem of recovering missing data in higher-order tensors by proposing FCTN-WOPT, a new tensor completion method that combines fully-connected tensor network decomposition with weighted optimization. Results show advanced performance on synthetic, image, and video data.
Tensor completion aimes at recovering missing data, and it is one of the popular concerns in deep learning and signal processing. Among the higher-order tensor decomposition algorithms, the recently proposed fully-connected tensor network decomposition (FCTN) algorithm is the most advanced. In this paper, by leveraging the superior expression of the fully-connected tensor network (FCTN) decomposition, we propose a new tensor completion method named the fully connected tensor network weighted optization(FCTN-WOPT). The algorithm performs a composition of the completed tensor by initialising the factors from the FCTN decomposition. We build a loss function with the weight tensor, the completed tensor and the incomplete tensor together, and then update the completed tensor using the lbfgs gradient descent algorithm to reduce the spatial memory occupation and speed up iterations. Finally we test the completion with synthetic data and real data (both image data and video data) and the results show the advanced performance of our FCTN-WOPT when it is applied to higher-order tensor completion.