@inproceedings{1b45ab4be7824f2eb7923fc71df6ca8b,
title = "SimplePPT: A simple principal tree algorithm",
abstract = "Many scientific datasets are of high dimension, and the analysis usually requires visual manipulation by retaining the most important structures of data. Principal curve is a widely used approach for this purpose. However, many existing methods work only for data with structures that are not self-intersected, which is quite restrictive for real applications. To address this issue, we develop a new model, which captures the local information of the underlying graph structure based on reversed graph embedding. A generalization bound is derived that show that the model is consistent if the number of data points is sufficiently large. As a special case, a principal tree model is proposed and a new algorithm is developed that learns a tree structure automatically from data. The new algorithm is simple and parameter-free with guaranteed convergence. Experimental results on synthetic and breast cancer datasets show that the proposed method compares favorably with baselines and can discover a breast cancer progression path with multiple branches.",
keywords = "Cancer progression path, Principal curve, Principal graph, Reversed graph embedding",
author = "Qi Mao and Le Yang and Li Wang and Steve Goodison and Yijun Sun",
note = "Publisher Copyright: Copyright {\textcopyright} SIAM.; SIAM International Conference on Data Mining 2015, SDM 2015 ; Conference date: 30-04-2015 Through 02-05-2015",
year = "2015",
doi = "10.1137/1.9781611974010.89",
language = "English (US)",
series = "SIAM International Conference on Data Mining 2015, SDM 2015",
publisher = "Society for Industrial and Applied Mathematics Publications",
pages = "792--800",
editor = "Suresh Venkatasubramanian and Jieping Ye",
booktitle = "SIAM International Conference on Data Mining 2015, SDM 2015",
address = "United States",
}