Unsupervised Representation Learning by Quasiconformal Extension

Hirokazu Shimauchi

2023

Abstract

In this paper, we introduce a novel unsupervised representation learning method based on quasiconformal extension. It is essential to develop feature representations that significantly improve predictive performance, regardless of whether the approach is implicit or explicit. Quasiconformal extension extends a mapping to a higher dimension with a certain regularity. The method introduced in this study constructs a piecewise linear mapping of real line by leveraging the correspondence between the distribution of individual features and a uniform distribution. Subsequently, a higher-order feature representation is generated through quasiconformal extension, aiming to achieve effective representations. In experiments conducted across ten distinct datasets, our approach enhanced the performance of neural networks, extremely randomized trees, and support vector machines, when the features contained a sufficient level of information necessary for classification.

Paper Citation

in Harvard Style

Shimauchi H. (2023). Unsupervised Representation Learning by Quasiconformal Extension. In Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: NCTA; ISBN 978-989-758-674-3, SciTePress, pages 440-449. DOI: 10.5220/0012254500003595

in Bibtex Style

@conference{ncta23,
author={Hirokazu Shimauchi},
title={Unsupervised Representation Learning by Quasiconformal Extension},
booktitle={Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: NCTA},
year={2023},
pages={440-449},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012254500003595},
isbn={978-989-758-674-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: NCTA
TI - Unsupervised Representation Learning by Quasiconformal Extension
SN - 978-989-758-674-3
AU - Shimauchi H.
PY - 2023
SP - 440
EP - 449
DO - 10.5220/0012254500003595
PB - SciTePress