Control-based Graph Embeddings with Data Augmentation for Contrastive Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ahmad, Obaid Ullah, Said, Anwar, Shabbir, Mudassir, Abbas, Waseem, Koutsoukos, Xenofon
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917643148066816
author Ahmad, Obaid Ullah
Said, Anwar
Shabbir, Mudassir
Abbas, Waseem
Koutsoukos, Xenofon
author_facet Ahmad, Obaid Ullah
Said, Anwar
Shabbir, Mudassir
Abbas, Waseem
Koutsoukos, Xenofon
contents In this paper, we study the problem of unsupervised graph representation learning by harnessing the control properties of dynamical networks defined on graphs. Our approach introduces a novel framework for contrastive learning, a widely prevalent technique for unsupervised representation learning. A crucial step in contrastive learning is the creation of 'augmented' graphs from the input graphs. Though different from the original graphs, these augmented graphs retain the original graph's structural characteristics. Here, we propose a unique method for generating these augmented graphs by leveraging the control properties of networks. The core concept revolves around perturbing the original graph to create a new one while preserving the controllability properties specific to networks and graphs. Compared to the existing methods, we demonstrate that this innovative approach enhances the effectiveness of contrastive learning frameworks, leading to superior results regarding the accuracy of the classification tasks. The key innovation lies in our ability to decode the network structure using these control properties, opening new avenues for unsupervised graph representation learning.
format Preprint
id arxiv_https___arxiv_org_abs_2403_04923
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Control-based Graph Embeddings with Data Augmentation for Contrastive Learning
Ahmad, Obaid Ullah
Said, Anwar
Shabbir, Mudassir
Abbas, Waseem
Koutsoukos, Xenofon
Machine Learning
Multiagent Systems
Systems and Control
In this paper, we study the problem of unsupervised graph representation learning by harnessing the control properties of dynamical networks defined on graphs. Our approach introduces a novel framework for contrastive learning, a widely prevalent technique for unsupervised representation learning. A crucial step in contrastive learning is the creation of 'augmented' graphs from the input graphs. Though different from the original graphs, these augmented graphs retain the original graph's structural characteristics. Here, we propose a unique method for generating these augmented graphs by leveraging the control properties of networks. The core concept revolves around perturbing the original graph to create a new one while preserving the controllability properties specific to networks and graphs. Compared to the existing methods, we demonstrate that this innovative approach enhances the effectiveness of contrastive learning frameworks, leading to superior results regarding the accuracy of the classification tasks. The key innovation lies in our ability to decode the network structure using these control properties, opening new avenues for unsupervised graph representation learning.
title Control-based Graph Embeddings with Data Augmentation for Contrastive Learning
topic Machine Learning
Multiagent Systems
Systems and Control
url https://arxiv.org/abs/2403.04923