Graph learning for regularized low-rank matrix completion
(2018) 23rd International Symposium on Mathematical Theory of Networks and Systems — Location: Hong Kong (16.July.2018)
Files
0153.pdf
Open Access - Adobe PDF
- 398.41 KB
Details
- Authors
- Abstract
- Low rank matrix completion is the problem of recovering the missing entries of a large data matrix by using the low-rankness assumption. Much attention has been put recently to exploiting correlations between the column/row entities, through side information or data adaptive models, to improve the matrix completion quality. In this paper, we propose a novel graph learning algorithm and apply it to the learning of a graph adjacency matrix from a given, incomplete datamatrix,inawaysuchthattheweightedgraphedgesencode pairwise similarities between the rows/columns of the data matrix. Subsequently we present a graph-regularized low-rank matrix completion method. Experiments on synthetic and real datasets show that this regularized matrix completion approach achieves significant improvement for the matrix completion task.
- Affiliations
Citations
Dong, S., Absil, P.-A., & Gallivan, K. (2018). Graph learning for regularized low-rank matrix completion. MTNS 2018, 460-467. https://hdl.handle.net/2078.5/253762 (Original work published 2018)