Text

Genetic Programming for Manifold Learning: Preserving Local Topology

Manifold learning (MaL) methods are an invaluable tool in today’s world of increasingly huge datasets. MaL algorithms can discover a much lower-dimensional representation (embedding) of a high-dimensional dataset through nonlinear transformations that preserve the most important structure of the original data. State-of-the-art MaL methods directly optimize an embedding without mapping between the original space and the discovered embedded space. This makes interpretability—a key requirement in exploratory data analysis—nearly impossible. Recently, genetic programming has emerged as a very promising approach to MaL by evolving functional mappings from the original space to an embedding. However, genetic programming-based MaL has struggled to match the performance of other approaches. In this work, we propose a new approach to using genetic programming for MaL, which preserves local topology. This is expected to significantly improve performance on tasks where local neighborhood structure (topology) is paramount. We compare our proposed approach with various baseline MaL methods and find that it often outperforms other methods, including a clear improvement over previous genetic programming approaches. These results are particularly promising, given the potential interpretability and reusability of the evolved mappings.

Ketersediaan

Informasi Detail

Judul Seri

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION; Vol.26 No.4 August 2022

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 661-675

Bahasa

English

ISBN/ISSN

-

Klasifikasi

NONE

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

FEATURE SELECTION
FEATURE CONSTRUCTION
EVOLUTIONARY LEARNING
GENETIC PROGRAMMING (GP)
MANIFOLD LEARNING (MAL)

Info Detail Spesifik

DOI: 10.1109/TEVC.2021.3106672

Pernyataan Tanggungjawab

Andrew Lensen, Bing Xue, Mengjie Zhang

Versi lain/terkait

Lampiran Berkas

Komentar