A Local Non-Negative Pursuit Method for Intrinsic Manifold Structure Preservation
Abstract
The local neighborhood selection plays a crucial role for most representation based manifold learning algorithms. This paper reveals that an improper selection of neighborhood for learning representation will introduce negative components in the learnt representations. Importantly, the representations with negative components will affect the intrinsic manifold structure preservation. In this paper, a local non-negative pursuit (LNP) method is proposed for neighborhood selection and non-negative representations are learnt. Moreover, it is proved that the learnt representations are sparse and convex. Theoretical analysis and experimental results show that the proposed method achieves or outperforms the state-of-the-art results on various manifold learning problems.
Cite
Text
Chen et al. "A Local Non-Negative Pursuit Method for Intrinsic Manifold Structure Preservation." AAAI Conference on Artificial Intelligence, 2014. doi:10.1609/AAAI.V28I1.8966Markdown
[Chen et al. "A Local Non-Negative Pursuit Method for Intrinsic Manifold Structure Preservation." AAAI Conference on Artificial Intelligence, 2014.](https://mlanthology.org/aaai/2014/chen2014aaai-local/) doi:10.1609/AAAI.V28I1.8966BibTeX
@inproceedings{chen2014aaai-local,
title = {{A Local Non-Negative Pursuit Method for Intrinsic Manifold Structure Preservation}},
author = {Chen, Dongdong and Lv, Jian Cheng and Yi, Zhang},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2014},
pages = {1745-1751},
doi = {10.1609/AAAI.V28I1.8966},
url = {https://mlanthology.org/aaai/2014/chen2014aaai-local/}
}