Topological Graph Neural Networks: A Novel Approach for Geometric Deep Learning
Applied AI Letters · 2026-06 · 7 (2)
DOI: 10.1002/ail2.70021 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied AI Letters, online erschienen am 11.03.2026. Verfasst von Amarjeet und 7 weiteren Autor:innen. Die Arbeit nennt 11 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This paper introduces a novel approach to graph neural networks (GNNs) that incorporates topological data analysis (TDA) to enhance the representational power of traditional GNN architectures. We propose Topological Graph Neural Networks (TopGNNs), which leverage persistent homology and simplicial complexes to capture multi‐scale structural information that conventional GNNs often overlook. Our experimental results on benchmark datasets demonstrate that TopGNNs achieve competitive performance compared to state‐of‐the‐art methods, particularly for tasks requiring sensitivity to global graph structure. We provide a comprehensive empirical analysis of TopGNNs across various domains including molecular property prediction, social network analysis, and citation networks. The proposed framework bridges the gap between algebraic topology and deep learning on graphs, offering a promising direction for future research in geometric deep learning.
Zitieren
APA
Amarjeet, Sinha, A., Hussain, K., Bhat, W. A., Maurya, S., Ahmed, M. N., Hussain, M. R., & Khalid, S. (2026). Topological Graph Neural Networks: A Novel Approach for Geometric Deep Learning. Applied AI Letters, 7(2). https://doi.org/10.1002/ail2.70021
Vancouver
Amarjeet, Sinha A, Hussain K, Bhat WA, Maurya S, Ahmed MN, et al. Topological Graph Neural Networks: A Novel Approach for Geometric Deep Learning. Applied AI Letters. 2026;7(2). doi:10.1002/ail2.70021
BibTeX
@article{Amarjeet2026,
author = {Amarjeet and Sinha, Anurag and Hussain, Khalid and Bhat, Wasim Ahmad and Maurya, Sudhanshu and Ahmed, Mohammad Nadeem and Hussain, Mohammad Rashid and Khalid, S.},
title = {Topological Graph Neural Networks: A Novel Approach for Geometric Deep Learning},
journal = {Applied AI Letters},
year = {2026},
volume = {7},
number = {2},
doi = {10.1002/ail2.70021}
}
EUVIMED