Tensor Completion with Side Information: A Riemannian Manifold Approach
Abstract
By restricting the iterate on a nonlinear manifold, the recently proposed Riemannian optimization methods prove to be both efficient and effective in low rank tensor completion problems. However, existing methods fail to exploit the easily accessible side information, due to their format mismatch. Consequently, there is still room for improvement. To fill the gap, in this paper, a novel Riemannian model is proposed to tightly integrate the original model and the side information by overcoming their inconsistency. For this model, an efficient Riemannian conjugate gradient descent solver is devised based on a new metric that captures the curvature of the objective. Numerical experiments suggest that our method is more accurate than the state-of-the-art without compromising the efficiency.
Cite
Text
Zhou et al. "Tensor Completion with Side Information: A Riemannian Manifold Approach." International Joint Conference on Artificial Intelligence, 2017. doi:10.24963/IJCAI.2017/495Markdown
[Zhou et al. "Tensor Completion with Side Information: A Riemannian Manifold Approach." International Joint Conference on Artificial Intelligence, 2017.](https://mlanthology.org/ijcai/2017/zhou2017ijcai-tensor/) doi:10.24963/IJCAI.2017/495BibTeX
@inproceedings{zhou2017ijcai-tensor,
title = {{Tensor Completion with Side Information: A Riemannian Manifold Approach}},
author = {Zhou, Tengfei and Qian, Hui and Shen, Zebang and Zhang, Chao and Xu, Congfu},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2017},
pages = {3539-3545},
doi = {10.24963/IJCAI.2017/495},
url = {https://mlanthology.org/ijcai/2017/zhou2017ijcai-tensor/}
}