Distributed and Incremental Clustering Based on Weighted Affinity Propagation

Xiangliang Zhang 1, * Cyril Furtlehner 1 Michèle Sebag 1
* Corresponding author
1 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
Abstract : A new clustering algorithm Affinity Propagation (AP) is hindered by its quadratic complexity. The Weighted Affinity Propagation (WAP) proposed in this paper is used to eliminate this limitation, support two scalable algorithms. Distributed AP clustering handles large datasets by merging the exemplars learned from subsets. Incremental AP extends AP to online clustering of data streams. The paper validates all proposed algorithms on benchmark and on real-world datasets. Experimental results show that the proposed approaches offer a good trade-off between computational effort and performance.
Complete list of metadatas

https://hal.inria.fr/inria-00287378
Contributor : Xiangliang Zhang <>
Submitted on : Wednesday, June 11, 2008 - 5:09:36 PM
Last modification on : Thursday, April 5, 2018 - 12:30:12 PM
Long-term archiving on : Friday, September 28, 2012 - 3:51:08 PM

File

STAIRS08_vfinal.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00287378, version 1

Collections

Citation

Xiangliang Zhang, Cyril Furtlehner, Michèle Sebag. Distributed and Incremental Clustering Based on Weighted Affinity Propagation. the fourth European Starting AI Researcher Symposium (STAIRS), Jul 2008, Patras, Greece. ⟨inria-00287378⟩

Share

Metrics

Record views

290

Files downloads

427