Robust Kernel Sparse Subspace Clustering

Kopriva, Ivica (2025) Robust Kernel Sparse Subspace Clustering. In: Mathews, John, (ed.) ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Piscataway, NJ, IEEE, .

PDF - Accepted Version - article Available under License Creative Commons Attribution. Download (243kB)

Abstract

Kernel methods are widely used in pattern recognition, including subspace clustering (SC). They transform nonlinear problems in the input data space into linear ones in a high-dimensional feature space. This transformation, achieved through the kernel trick, makes computationally tractable nonlinear algorithms possible. However, kernelizing linear algorithms through the kernel trick is infeasible in case of gross sparse corruptions that are modeled by the -norm of the error term. To address this, we propose, for the first time, a robust kernel sparse SC (RKSSC) algorithm for data with gross sparse corruptions. We validated the proposed approach on two well-known datasets, using the linear robust SSC algorithm and nonlinear (kernel-based) SSC algorithm as baseline models. According to the Wilcoxon test, the RKSSC's algorithm clustering performance is statistically significantly better than baselines.

Item Type:	Conference or workshop item published in conference proceedings (UNSPECIFIED)
Uncontrolled Keywords:	Robust kernel sparse subspace clustering; Nonlinear projection trick; Kernel Trick
Subjects:	TECHNICAL SCIENCES TECHNICAL SCIENCES > Computing TECHNICAL SCIENCES > Computing > Artificial Intelligence
Divisions:	Division of Electronics
Projects:	Project title Project leader Project code Project type Development of algorithms for data clustering, regression and feature extraction with applications in pathology, ophthalmology and metabolomics Ivica Kopriva IP-2022-10-6403 Znanstveni
Depositing User:	Ivica Kopriva
Date Deposited:	04 Apr 2025 13:42
URI:	http://fulir.irb.hr/id/eprint/9682
DOI:	10.1109/ICASSP49660.2025.10888170

Actions (login required)

View Item