2
$\begingroup$

For my pet project I need to cluster some data which could be easily represented as graph, so I want to use this as an opportunity to educate myself and play with various algorithms. I'd prefer the book on graph clustering as it often more self contained but articles are fine too. Back in the days I used to work in the field of numerical linear algebra so I'd also prefer algebraical view on things (so books which view graph as a matrix with specific properties are more accessible to me).

p.s. I've tried scholar.google.com but was overwhelmed by vast number of results.

$\endgroup$
  • $\begingroup$ I suggest you start from the top. Prefaces and/or first chapters should tell whether the book/article will be useful for you; nobody can make this decision for you. $\endgroup$ – Raphael May 25 '12 at 13:37
4
$\begingroup$

The book The Elements of Statistical Learning by Trevor Hastie, Robert Tibshirani and Jerome Friedman covers a lot of learning and clustering algorithms including various graph clustering algorithms. Algorithms such as Spectral Clustering are phrased algebraically, as is much of the book. The good thing is that a pdf of the book is available from the authors' website, linked above. It has an extensive bibliography to help you beyond what is presented in the book.

There's also an implementation of Spectral Clustering in R which works quite well and has lots of options.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.