Processing Heterogeneous Graphs within Heterogeneous Data Type Embeddings to Enhance Recommender Systems

Embeddings represent a viable solution to address the challenge of data and information generation in heterogeneous graphs. This research presents our approach for generating and processing heterogeneous embeddings (AGHE), which are built from various data types such as text, images, and subgraphs embedded in nodes. AGHE comprises several stages, from graph creation to the generation of embedding compositions based on node features and metapaths. In the conducted experiments, simple and embedding compositions were used as input data for the Node Classification task in Recommender Systems, investigating effectiveness metrics. The outcomes achieved in our experiments are encouraging, demonstrating superior results compared to the baseline used.