ACM Transactions on Knowledge Discovery from Data (TKDD)
Evaluating clustering in subspace projections of high dimensional data
Proceedings of the VLDB Endowment
Hi-index | 0.00 |
We present an algorithm for generating subspace clusterings of large data sets with many attributes. An evolutionary algorithm is used to form groups of relevant attributes. Those groups are replaced by their centroids, making it possible to cluster the objects in a much lower dimensional space. Preliminary experiments with scalable synthetic data sets suggest that the algorithm generates competitive clusterings while scaling quite well.