Learning Conditionally Independent Transformations using Normal Subgroups in Group Theory

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Nishitsunoi, Kayato, Ohmura, Yoshiyuki, Komatsu, Takayuki, Kuniyoshi, Yasuo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917978747961344
author Nishitsunoi, Kayato
Ohmura, Yoshiyuki
Komatsu, Takayuki
Kuniyoshi, Yasuo
author_facet Nishitsunoi, Kayato
Ohmura, Yoshiyuki
Komatsu, Takayuki
Kuniyoshi, Yasuo
contents Humans develop certain cognitive abilities to recognize objects and their transformations without explicit supervision, highlighting the importance of unsupervised representation learning. A fundamental challenge in unsupervised representation learning is to separate different transformations in learned feature representations. Although algebraic approaches have been explored, a comprehensive theoretical framework remains underdeveloped. Existing methods decompose transformations based on algebraic independence, but these methods primarily focus on commutative transformations and do not extend to cases where transformations are conditionally independent but noncommutative. To extend current representation learning frameworks, we draw inspiration from Galois theory, where the decomposition of groups through normal subgroups provides an approach for the analysis of structured transformations. Normal subgroups naturally extend commutativity under certain conditions and offer a foundation for the categorization of transformations, even when they do not commute. In this paper, we propose a novel approach that leverages normal subgroups to enable the separation of conditionally independent transformations, even in the absence of commutativity. Through experiments on geometric transformations in images, we show that our method successfully categorizes conditionally independent transformations, such as rotation and translation, in an unsupervised manner, suggesting a close link between group decomposition via normal subgroups and transformation categorization in representation learning.
format Preprint
id arxiv_https___arxiv_org_abs_2504_04490
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Conditionally Independent Transformations using Normal Subgroups in Group Theory
Nishitsunoi, Kayato
Ohmura, Yoshiyuki
Komatsu, Takayuki
Kuniyoshi, Yasuo
Computer Vision and Pattern Recognition
Humans develop certain cognitive abilities to recognize objects and their transformations without explicit supervision, highlighting the importance of unsupervised representation learning. A fundamental challenge in unsupervised representation learning is to separate different transformations in learned feature representations. Although algebraic approaches have been explored, a comprehensive theoretical framework remains underdeveloped. Existing methods decompose transformations based on algebraic independence, but these methods primarily focus on commutative transformations and do not extend to cases where transformations are conditionally independent but noncommutative. To extend current representation learning frameworks, we draw inspiration from Galois theory, where the decomposition of groups through normal subgroups provides an approach for the analysis of structured transformations. Normal subgroups naturally extend commutativity under certain conditions and offer a foundation for the categorization of transformations, even when they do not commute. In this paper, we propose a novel approach that leverages normal subgroups to enable the separation of conditionally independent transformations, even in the absence of commutativity. Through experiments on geometric transformations in images, we show that our method successfully categorizes conditionally independent transformations, such as rotation and translation, in an unsupervised manner, suggesting a close link between group decomposition via normal subgroups and transformation categorization in representation learning.
title Learning Conditionally Independent Transformations using Normal Subgroups in Group Theory
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.04490