Learning graphs from data via spectral constraints

spectralGraphTopology provides estimators of the Laplacian and adjacency matrices of graphs by leveraging prior information in their structural form.

Get started now View it on GitHub


Getting started

Dependencies

The R version of spectralGraphTopology is build on top of awesome R packages including Rcpp, RcppEigen, and igraph. All these packages can be installed via CRAN.

Installation

  1. The stable version can be installed via CRAN as
    > install.packages("spectralGraphTopology")
    
  2. The development version can be installed via GitHub as
    devtools::install_github("dppalomar/spectralGraphTopology")
    

    You must have previously installed the devtools package.

Tutorials

  • See the package vignette for a detailed description of the mathematical methods that are available in spectralGraphTopology.

About the project

spectralGraphTopology is developed on GitHub by Ze Vinicius, Daniel Palomar, Jiaxi Ying and Sandeep Kumar.

License

spectralGraphTopology is distributed by an GPL 3.0 License.

Contributing

We welcome all sorts of contributions. Please feel free to open an issue to report a bug or discuss a feature request in our GitHub repo.

Citation

If this package has been useful to you in any way, give us a star on GitHub :) Additionally, if you’ve used spectralGraphTopology on your research, please consider citing the following resource:

  • S. Kumar, J. Ying, J. V. de M. Cardoso and D. P. Palomar (2019). A unified framework for structured graph learning via spectral constraints. https://arxiv.org/pdf/1904.09792.pdf