ML Anthology

Label Propagation Through Linear Neighborhoods

Fei Wang, Changshui Zhang
ICML 2006 pp. 985-992
doi:10.1145/1143844.1143968 /icml/2006/wang2006icml-label/

Abstract

A novel semi-supervised learning approach is proposed based on a linear neighborhood model, which assumes that each data point can be linearly reconstructed from its neighborhood. Our algorithm, named Linear Neighborhood Propagation (LNP), can propagate the labels from the labeled points to the whole dataset using these linear neighborhoods with sufficient smoothness. We also derive an easy way to extend LNP to out-of-sample data. Promising experimental results are presented for synthetic data, digit and text classification tasks.

PDF ICML Semantic Scholar

Cite

Text

Wang and Zhang. "Label Propagation Through Linear Neighborhoods." International Conference on Machine Learning, 2006. doi:10.1145/1143844.1143968

Markdown

[Wang and Zhang. "Label Propagation Through Linear Neighborhoods." International Conference on Machine Learning, 2006.](https://mlanthology.org/icml/2006/wang2006icml-label/) doi:10.1145/1143844.1143968

BibTeX

@inproceedings{wang2006icml-label,
  title     = {{Label Propagation Through Linear Neighborhoods}},
  author    = {Wang, Fei and Zhang, Changshui},
  booktitle = {International Conference on Machine Learning},
  year      = {2006},
  pages     = {985-992},
  doi       = {10.1145/1143844.1143968},
  url       = {https://mlanthology.org/icml/2006/wang2006icml-label/}
}