Tensor Factorization Using Auxiliary Information
Abstract
Most of the existing analysis methods for tensors (or multi-way arrays) only assume that tensors to be completed are of low rank. However, for example, when they are applied to tensor completion problems, their prediction accuracy tends to be significantly worse when only limited entries are observed. In this paper, we propose to use relationships among data as auxiliary information in addition to the low-rank assumption to improve the quality of tensor decomposition. We introduce two regularization approaches using graph Laplacians induced from the relationships, and design iterative algorithms for approximate solutions. Numerical experiments on tensor completion using synthetic and benchmark datasets show that the use of auxiliary information improves completion accuracy over the existing methods based only on the low-rank assumption, especially when observations are sparse.
Cite
Text
Narita et al. "Tensor Factorization Using Auxiliary Information." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2011. doi:10.1007/978-3-642-23783-6_32Markdown
[Narita et al. "Tensor Factorization Using Auxiliary Information." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2011.](https://mlanthology.org/ecmlpkdd/2011/narita2011ecmlpkdd-tensor/) doi:10.1007/978-3-642-23783-6_32BibTeX
@inproceedings{narita2011ecmlpkdd-tensor,
title = {{Tensor Factorization Using Auxiliary Information}},
author = {Narita, Atsuhiro and Hayashi, Kohei and Tomioka, Ryota and Kashima, Hisashi},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2011},
pages = {501-516},
doi = {10.1007/978-3-642-23783-6_32},
url = {https://mlanthology.org/ecmlpkdd/2011/narita2011ecmlpkdd-tensor/}
}