Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{204641,
        author = {Meena Patil},
        title = {Optimization based external graph learning for large scale dynamic and sparse network},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {3800-3807},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204641},
        abstract = {Graph learning is a challenge for large dynamic sparse networks due to low levels of connectivity and changing network structure. To represent more accurately, this study created an Optimization-based External Graph Learning (OEGL) framework, which integrates the original network topology with external graph data to improve the effectiveness of representation learning. The OEGL framework comprises three keys: (1) optimization of the graph, (2) temporal encoding of the graph, and (3) adaptive message aggregation in order to enhance the performance of learning. The OEGL framework demonstrated 94% accuracy on node classification and 0.95 AUC for link prediction, exhibiting superior performance relative to existing methods of learning from graphs. Additionally, the OEGL framework illustrated its scalability for networks having between 1 and 5 million nodes, making it a powerful tool for conducting analysis of large-scale dynamic networks.},
        keywords = {Optimization-Based Graph Learning, Dynamic and Sparse Networks, External Graph Integration, Node Classification and Link Prediction},
        month = {June},
        }