English

Geometric Matrix Completion: A Functional View

Machine Learning 2020-10-01 v1 Computer Vision and Pattern Recognition Social and Information Networks Machine Learning

Abstract

We propose a totally functional view of geometric matrix completion problem. Differently from existing work, we propose a novel regularization inspired from the functional map literature that is more interpretable and theoretically sound. On synthetic tasks with strong underlying geometric structure, our framework outperforms state of the art by a huge margin (two order of magnitude) demonstrating the potential of our approach. On real datasets, we achieve state-of-the-art results at a fraction of the computational effort of previous methods. Our code is publicly available at https://github.com/Not-IITian/functional-matrix-completion

Keywords

Cite

@article{arxiv.2009.14343,
  title  = {Geometric Matrix Completion: A Functional View},
  author = {Abhishek Sharma and Maks Ovsjanikov},
  journal= {arXiv preprint arXiv:2009.14343},
  year   = {2020}
}

Comments

Accepted at GRL workshop, ICML'20. Code: \url{https://github.com/Not-IITian/functional-matrix-completion}