Graph Representation Learning for Evaluation of Synthetic Relational DataJurkovič, Martin (Avtor) Šubelj, Lovro (Mentor) synthetic datarelational databasesdata generationgraph representation learninggraph neural networksempirical comparisondata quality evaluationutilityEvaluating the utility of synthetic relational databases is challenging, as existing approaches rely on manual feature engineering or single-table flattening, which obscure relational structure and reduce scalability. This thesis introduces RDL-utility, a general framework that represents relational databases as heterogeneous graphs and trains graph neural networks (GNNs) directly on the graphs. Using a standardized AutoComplete task, RDL-utility measures how well models trained on synthetic data perform on real held-out data. Experiments on five real-world databases, including an ablation study across six GNN architectures, show that diffusion-based generative methods achieve the highest utility, although no single method consistently outperforms all others. RDL-utility provides a reproducible, structure-sensitive evaluation, establishing a foundation for future research and applications.20252025-09-22 14:45:02Magistrsko delo/naloga173771sl