A tutorial on spectral clustering Export

@article{citeulike:2158149, abstract = {Abstract\ \  In recent years, spectral clustering has become one of the most popular modern clustering algorithms. It is simple to implement, can be solved efficiently by standard linear algebra software, and very often outperforms traditional clustering algorithms such as the k-means algorithm. On the first glance spectral clustering appears slightly mysterious, and it is not obvious to see why it works at all and what it really does. The goal of this tutorial is to give some intuition on those questions. We describe different graph Laplacians and their basic properties, present the most common spectral clustering algorithms, and derive those algorithms from scratch by several different approaches. Advantages and disadvantages of the different spectral clustering algorithms are discussed.}, author = {von Luxburg, Ulrike}, citeulike-article-id = {2158149}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/s11222-007-9033-z}, citeulike-linkout-1 = {http://www.springerlink.com/content/jq1g17785n783661}, day = {11}, doi = {10.1007/s11222-007-9033-z}, journal = {Statistics and Computing}, keywords = {clustering, ir, linalg, spectral, survey}, month = {December}, number = {4}, pages = {395--416}, posted-at = {2009-05-19 13:47:16}, priority = {0}, title = {A tutorial on spectral clustering}, url = {http://dx.doi.org/10.1007/s11222-007-9033-z}, volume = {17}, year = {2007} }

TY - JOUR ID - citeulike:2158149 L3 - citeulike-article-id:2158149 N2 - Abstract   In recent years, spectral clustering has become one of the most popular modern clustering algorithms. It is simple to implement, can be solved efficiently by standard linear algebra software, and very often outperforms traditional clustering algorithms such as the k-means algorithm. On the first glance spectral clustering appears slightly mysterious, and it is not obvious to see why it works at all and what it really does. The goal of this tutorial is to give some intuition on those questions. We describe different graph Laplacians and their basic properties, present the most common spectral clustering algorithms, and derive those algorithms from scratch by several different approaches. Advantages and disadvantages of the different spectral clustering algorithms are discussed. IS - 4 JF - Statistics and Computing EP - 416 TI - A tutorial on spectral clustering VL - 17 SP - 395 KW - clustering KW - ir KW - linalg KW - spectral KW - survey AU - von Luxburg, Ulrike PY - 2007/12/11/ UR - http://dx.doi.org/10.1007/s11222-007-9033-z ER -