T3former: Temporal Graph Classification with Topological Machine Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Uddin, Md. Joshem, Changani, Soham, Coskunuzer, Baris
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914169715949568
author Uddin, Md. Joshem
Changani, Soham
Coskunuzer, Baris
author_facet Uddin, Md. Joshem
Changani, Soham
Coskunuzer, Baris
contents Temporal graph classification plays a critical role in applications such as cybersecurity, brain connectivity analysis, social dynamics, and traffic monitoring. Despite its significance, this problem remains underexplored compared to temporal link prediction or node forecasting. Existing methods often rely on snapshot-based or recurrent architectures that either lose fine-grained temporal information or struggle with long-range dependencies. Moreover, local message-passing approaches suffer from oversmoothing and oversquashing, limiting their ability to capture complex temporal structures. We introduce T3former, a novel Topological Temporal Transformer that leverages sliding-window topological and spectral descriptors as first-class tokens, integrated via a specialized Descriptor-Attention mechanism. This design preserves temporal fidelity, enhances robustness, and enables principled cross-modal fusion without rigid discretization. T3former achieves state-of-the-art performance across multiple benchmarks, including dynamic social networks, brain functional connectivity datasets, and traffic networks. It also offers theoretical guarantees of stability under temporal and structural perturbations. Our results highlight the power of combining topological and spectral insights for advancing the frontier of temporal graph learning.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13789
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle T3former: Temporal Graph Classification with Topological Machine Learning
Uddin, Md. Joshem
Changani, Soham
Coskunuzer, Baris
Machine Learning
Social and Information Networks
Algebraic Topology
55N31, 68T07, 05C85
G.2.2; I.2.6
Temporal graph classification plays a critical role in applications such as cybersecurity, brain connectivity analysis, social dynamics, and traffic monitoring. Despite its significance, this problem remains underexplored compared to temporal link prediction or node forecasting. Existing methods often rely on snapshot-based or recurrent architectures that either lose fine-grained temporal information or struggle with long-range dependencies. Moreover, local message-passing approaches suffer from oversmoothing and oversquashing, limiting their ability to capture complex temporal structures. We introduce T3former, a novel Topological Temporal Transformer that leverages sliding-window topological and spectral descriptors as first-class tokens, integrated via a specialized Descriptor-Attention mechanism. This design preserves temporal fidelity, enhances robustness, and enables principled cross-modal fusion without rigid discretization. T3former achieves state-of-the-art performance across multiple benchmarks, including dynamic social networks, brain functional connectivity datasets, and traffic networks. It also offers theoretical guarantees of stability under temporal and structural perturbations. Our results highlight the power of combining topological and spectral insights for advancing the frontier of temporal graph learning.
title T3former: Temporal Graph Classification with Topological Machine Learning
topic Machine Learning
Social and Information Networks
Algebraic Topology
55N31, 68T07, 05C85
G.2.2; I.2.6
url https://arxiv.org/abs/2510.13789