Text meets topology: A dynamic graph learning method with Dy-GNNs and LLMs for tracking text attributed community evolution in complex networks

Sruthi K.S., A. Sreekumar and Kannan Balakrishnan

Chaos, Solitons & Fractals, 2026, vol. 208, issue P1

Abstract: This work proposes a novel fusion framework that reformulates community evolution prediction as a temporal edge classification problem in dynamic text-attributed graphs. Our approach integrates state-of-the-art Large Language Model (LLM)-based textual embeddings with structural and temporal information, directly embedding semantic signals into the message-passing mechanisms of multiple architecturally enhanced dynamic graph neural networks (Dy-GNNs). LLMs can represent the rich text associated with node or edge attributes to generate the textual embeddings of the data. The combined textual and structural embedding of dynamic networks is then used to train deep models to predict edge classes, which is subsequently modified into community prediction. The fusion approach offers a more efficient model that can understand the evolution patterns of dynamic networks in real-world applications.

Keywords: Complex networks; Dynamic text attributed networks (Dy-TAGs); Dynamic graph neural networks (Dy-GNNs); Large language models (LLMs); Textual embeddings; Community evolution; Edge classification problem (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960077926002626
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:chsofr:v:208:y:2026:i:p1:s0960077926002626

DOI: 10.1016/j.chaos.2026.118121

Access Statistics for this article

Chaos, Solitons & Fractals is currently edited by Stefano Boccaletti and Stelios Bekiros

More articles in Chaos, Solitons & Fractals from Elsevier
Bibliographic data for series maintained by Thayer, Thomas R. ().