Hauptnavigation

Hess/etal/2019a: The SpectACl of Nonconvex Clustering: a Spectral Approach to Density-Based Clustering

Bibtype Inproceedings
Bibkey Hess/etal/2019a
Author Hess, Sibylle and Duivesteijn, Wouter and Honysz, Philipp-Jan and Morik, Katharina
Ls8autor Hess, Sibylle
Honysz, Philipp
Morik, Katharina
Title The SpectACl of Nonconvex Clustering: a Spectral Approach to Density-Based Clustering
Booktitle AAAI
Abstract When it comes to the clustering of nonconvex shapes, generally two paradigms are used to find the most suitable clustering: minimum cut and maximum density. The most popular algorithms incorporating these paradigms are Spectral Clustering and DBSCAN. Both paradigms have their pros and cons. While minimum cut clusterings are sensitive to noise, density-based clusterings have trouble handling clusters with varying densities. In this paper, we propose \textsc{SpectACl}: a method combining the advantages of both approaches, while solving the two mentioned drawbacks. Our method is easy to implement, such as spectral clustering, and theoretically founded to optimize a proposed density criterion of clusterings. By means of experiments on synthetic and real-world data, we demonstrate that our approach provides robust and reliable clusterings.
Year 2019
Projekt SFB876-C1



  • Privacy Policy
  • Imprint