Filtration-Based Representation Learning for Temporal Graphs

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chowdhury, Samrik, Pritam, Siddharth, Roy, Rohit, Sajeev, Madhav Cherupilil
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911298354151424
author Chowdhury, Samrik
Pritam, Siddharth
Roy, Rohit
Sajeev, Madhav Cherupilil
author_facet Chowdhury, Samrik
Pritam, Siddharth
Roy, Rohit
Sajeev, Madhav Cherupilil
contents In this work, we introduce a filtration on temporal graphs based on $δ$-temporal motifs (recurrent subgraphs), yielding a multi-scale representation of temporal structure. Our temporal filtration allows tools developed for filtered static graphs, including persistent homology and recent graph filtration kernels, to be applied directly to temporal graph analysis. We demonstrate the effectiveness of this approach on temporal graph classification tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2502_10076
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Filtration-Based Representation Learning for Temporal Graphs
Chowdhury, Samrik
Pritam, Siddharth
Roy, Rohit
Sajeev, Madhav Cherupilil
Machine Learning
Computational Geometry
Algebraic Topology
In this work, we introduce a filtration on temporal graphs based on $δ$-temporal motifs (recurrent subgraphs), yielding a multi-scale representation of temporal structure. Our temporal filtration allows tools developed for filtered static graphs, including persistent homology and recent graph filtration kernels, to be applied directly to temporal graph analysis. We demonstrate the effectiveness of this approach on temporal graph classification tasks.
title Filtration-Based Representation Learning for Temporal Graphs
topic Machine Learning
Computational Geometry
Algebraic Topology
url https://arxiv.org/abs/2502.10076