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{207302,
        author = {Dipti Diliprao Mehare and Dr. P. M. Jawandhiya},
        title = {Graph-Based Personalized Learning: A Review of Graph Neural Networks (GNN) and Graph Convolutional Networks (GCN) in Advanced Educational Recommendation Frameworks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {3},
        pages = {236-243},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=207302},
        abstract = {Digital learning environments generate complex, non-Euclidean data structures containing deep relational connections between learners, instructional materials, concepts, and pedagogical rules. Traditional recommendation architectures—such as matrix factorization, collaborative filtering, and linear deep learning models—treat data isolatedly, failing to capture complex prerequisite structural dependencies and high-order user-item interactions. This review explores the deployment of Graph Neural Networks (GNNs) and Graph Convolutional Networks (GCNs) within advanced educational recommendation systems. We evaluate graph-based user profiling, semantic knowledge graphs, message-passing mechanics, and neighborhood aggregation methods specifically tailored for academic progress tracking. The paper categorizes the architectural shifts in graph-driven pedagogy and outlines how structural relational embeddings solve classic recommendation bottlenecks while respecting pedagogical constraints.},
        keywords = {Graph Neural Networks (GNN), Graph Convolutional Networks (GCN), Educational Recommendation Systems, Knowledge Graphs, Personalized Learning, Relational Embeddings.},
        month = {August},
        }