Incremental ELMVIS for unsupervised learning

TL;DR

This paper introduces an incremental version of ELMVIS+ that enhances unsupervised learning by efficiently handling large datasets and improving local optima, applicable to general dataset processing beyond visualization.

Contribution

The paper presents a novel incremental ELMVIS+ method that reduces memory usage and extends applicability to unsupervised data dependency learning in high-dimensional spaces.

Findings

Capable of learning dependencies from unorganized data

Reconstructs shuffled datasets effectively

Maintains high speed with larger sample pools

Abstract

An incremental version of the ELMVIS+ method is proposed in this paper. It iteratively selects a few best fitting data samples from a large pool, and adds them to the model. The method keeps high speed of ELMVIS+ while allowing for much larger possible sample pools due to lower memory requirements. The extension is useful for reaching a better local optimum with greedy optimization of ELMVIS, and the data structure can be specified in semi-supervised optimization. The major new application of incremental ELMVIS is not to visualization, but to a general dataset processing. The method is capable of learning dependencies from non-organized unsupervised data -- either reconstructing a shuffled dataset, or learning dependencies in complex high-dimensional space. The results are interesting and promising, although there is space for improvements.