ReLISH: Reliable Label Inference via Smoothness Hypothesis

Chen Gong, Dacheng Tao, Keren Fu, Jie Yang

AAAI 2014 pp. 1840-1846

doi:10.1609/AAAI.V28I1.8955 /aaai/2014/gong2014aaai-relish/

Abstract

The smoothness hypothesis is critical for graph-based semi-supervised learning. This paper defines local smoothness, based on which a new algorithm, Reliable Label Inference via Smoothness Hypothesis (ReLISH), is proposed. ReLISH has produced smoother labels than some existing methods for both labeled and unlabeled examples. Theoretical analyses demonstrate good stability and generalizability of ReLISH. Using real-world datasets, our empirical analyses reveal that ReLISH is promising for both transductive and inductive tasks, when compared with representative algorithms, including Harmonic Functions, Local and Global Consistency, Constraint Metric Learning, Linear Neighborhood Propagation, and Manifold Regularization.

PDF AAAI Semantic Scholar

Cite

Text

Gong et al. "ReLISH: Reliable Label Inference via Smoothness Hypothesis." AAAI Conference on Artificial Intelligence, 2014. doi:10.1609/AAAI.V28I1.8955

Markdown

[Gong et al. "ReLISH: Reliable Label Inference via Smoothness Hypothesis." AAAI Conference on Artificial Intelligence, 2014.](https://mlanthology.org/aaai/2014/gong2014aaai-relish/) doi:10.1609/AAAI.V28I1.8955

BibTeX

@inproceedings{gong2014aaai-relish,
  title     = {{ReLISH: Reliable Label Inference via Smoothness Hypothesis}},
  author    = {Gong, Chen and Tao, Dacheng and Fu, Keren and Yang, Jie},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2014},
  pages     = {1840-1846},
  doi       = {10.1609/AAAI.V28I1.8955},
  url       = {https://mlanthology.org/aaai/2014/gong2014aaai-relish/}
}