General Transform: A Unified Framework for Adaptive Transform to Enhance Representations

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Budiutama, Gekko, Daimon, Shunsuke, Nishi, Hirofumi, Matsushita, Yu-ichiro
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913826367078400
author Budiutama, Gekko
Daimon, Shunsuke
Nishi, Hirofumi
Matsushita, Yu-ichiro
author_facet Budiutama, Gekko
Daimon, Shunsuke
Nishi, Hirofumi
Matsushita, Yu-ichiro
contents Discrete transforms, such as the discrete Fourier transform, are widely used in machine learning to improve model performance by extracting meaningful features. However, with numerous transforms available, selecting an appropriate one often depends on understanding the dataset's properties, making the approach less effective when such knowledge is unavailable. In this work, we propose General Transform (GT), an adaptive transform-based representation designed for machine learning applications. Unlike conventional transforms, GT learns data-driven mapping tailored to the dataset and task of interest. Here, we demonstrate that models incorporating GT outperform conventional transform-based approaches across computer vision and natural language processing tasks, highlighting its effectiveness in diverse learning scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2505_04969
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle General Transform: A Unified Framework for Adaptive Transform to Enhance Representations
Budiutama, Gekko
Daimon, Shunsuke
Nishi, Hirofumi
Matsushita, Yu-ichiro
Machine Learning
Computation and Language
Computer Vision and Pattern Recognition
Discrete transforms, such as the discrete Fourier transform, are widely used in machine learning to improve model performance by extracting meaningful features. However, with numerous transforms available, selecting an appropriate one often depends on understanding the dataset's properties, making the approach less effective when such knowledge is unavailable. In this work, we propose General Transform (GT), an adaptive transform-based representation designed for machine learning applications. Unlike conventional transforms, GT learns data-driven mapping tailored to the dataset and task of interest. Here, we demonstrate that models incorporating GT outperform conventional transform-based approaches across computer vision and natural language processing tasks, highlighting its effectiveness in diverse learning scenarios.
title General Transform: A Unified Framework for Adaptive Transform to Enhance Representations
topic Machine Learning
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.04969