Robust non-negative matrix factorization via joint sparse and graph regularization.

Shizhun Yang, Chenping Hou, Changshui Zhang, Yi Wu, Shifeng Weng

Abstract

In real world applications, we often have to deal with some high-dimensional, sparse and noisy data. In this paper, we aim to handle this kind of complex data by a Robust Non-negative Matrix Factorization via joint Sparse and Graph regularization model (RSGNMF). We provide a novel efficient and elegant iterative updating algorithm with rigorous convergence analysis for RSGNMF model. Experimental results on image data sets demonstrate that our RSGNMF model outperforms existing start-of-art methods.
BibTeX
@inproceedings{yang2013robust,
  author = {Shizhun Yang and Chenping Hou and Changshui Zhang and Yi Wu and Shifeng Weng},
  title = {{Robust non-negative matrix factorization via joint sparse and graph regularization.}},
  booktitle = {IJCNN},
  year = {2013},
  doi = {10.1109/ijcnn.2013.6706859},
}

Loading related content...

Figure