In this paper, Sergio Peignier et al. present a bioinspired algorithm to tackle the subspace clustering problem. This problem is recognized as more general and more difficult than clustering, because it consists in simultaneously clustering the data into multiple subspaces and finding a low-dimensional subspace fitting each group of points. The presented solution is an evolutionary algorithm that takes advantage of an evolvable genome structure to detect various numbers of clusters in subspaces of various dimensions. This algorithm yields competitive results with respect to state-of-the-art methods, with the advantage of being easier to tune, with just one parameter related to the application domain.

Reference :
Sergio Peignier, Christophe Rigotti, Guillaume Beslon: Subspace Clustering Using Evolvable Genome Structure. Proceedings of the 2015 Conference on Genetic and Evolutionary Computation Conference (GECCO'15): 575-582, Madrid, Spain, July 11 - 15, 2015, ACM, New York, NY, USA.

Conference website : http://www.sigevo.org/gecco-2015/papers.html