Efficient Nonnegative Tucker Decompositions: Algorithms and Uniqueness

04/17/2014
by   Guoxu Zhou, et al.
0

Nonnegative Tucker decomposition (NTD) is a powerful tool for the extraction of nonnegative parts-based and physically meaningful latent components from high-dimensional tensor data while preserving the natural multilinear structure of data. However, as the data tensor often has multiple modes and is large-scale, existing NTD algorithms suffer from a very high computational complexity in terms of both storage and computation time, which has been one major obstacle for practical applications of NTD. To overcome these disadvantages, we show how low (multilinear) rank approximation (LRA) of tensors is able to significantly simplify the computation of the gradients of the cost function, upon which a family of efficient first-order NTD algorithms are developed. Besides dramatically reducing the storage complexity and running time, the new algorithms are quite flexible and robust to noise because any well-established LRA approaches can be applied. We also show how nonnegativity incorporating sparsity substantially improves the uniqueness property and partially alleviates the curse of dimensionality of the Tucker decompositions. Simulation results on synthetic and real-world data justify the validity and high efficiency of the proposed NTD algorithms.

READ FULL TEXT

page 2

page 10

page 12

page 13

research
02/10/2023

Fast Learnings of Coupled Nonnegative Tensor Decomposition Using Optimal Gradient and Low-rank Approximation

Nonnegative tensor decomposition has been widely applied in signal proce...
research
09/17/2019

Nonnegative Canonical Polyadic Decomposition with Rank Deficient Factors

Recently, there is an emerging interest for applications of tensor facto...
research
07/31/2020

Geometric All-Way Boolean Tensor Decomposition

Boolean tensor has been broadly utilized in representing high dimensiona...
research
09/06/2021

Fast Hypergraph Regularized Nonnegative Tensor Ring Factorization Based on Low-Rank Approximation

For the high dimensional data representation, nonnegative tensor ring (N...
research
12/27/2018

Sparse Nonnegative CANDECOMP/PARAFAC Decomposition in Block Coordinate Descent Framework: A Comparison Study

Nonnegative CANDECOMP/PARAFAC (NCP) decomposition is an important tool t...
research
10/06/2020

Improving Nonparametric Density Estimation with Tensor Decompositions

While nonparametric density estimators often perform well on low dimensi...
research
11/01/2017

Tensor Valued Common and Individual Feature Extraction: Multi-dimensional Perspective

A novel method for common and individual feature analysis from exceeding...

Please sign up or login with your details

Forgot password? Click here to reset