Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/71665
Title: Robust clustering as ensembles of affinity relations
Authors: Liu, H. 
Latecki, L.J.
Yan, S. 
Issue Date: 2010
Citation: Liu, H.,Latecki, L.J.,Yan, S. (2010). Robust clustering as ensembles of affinity relations. Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010 : -. ScholarBank@NUS Repository.
Abstract: In this paper, we regard clustering as ensembles of κ-ary affinity relations and clusters correspond to subsets of objects with maximal average affinity relations. The average affinity relation of a cluster is relaxed and well approximated by a constrained homogenous function. We present an efficient procedure to solve this optimization problem, and show that the underlying clusters can be robustly revealed by using priors systematically constructed from the data. Our method can automatically select some points to form clusters, leaving other points un-grouped; thus it is inherently robust to large numbers of outliers, which has seriously limited the applicability of classical methods. Our method also provides a unified solution to clustering from κ-ary affinity relations with κ ≥ 2, that is, it applies to both graph-based and hypergraph-based clustering problems. Both theoretical analysis and experimental results show the superiority of our method over classical solutions to the clustering problem, especially when there exists a large number of outliers.
Source Title: Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010
URI: http://scholarbank.nus.edu.sg/handle/10635/71665
ISBN: 9781617823800
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.