Abstract
For the provision of accurate link prediction, this study's neural network-based method for API recommendation uses structure encoding to capture topological context. SEGNN4SLP, a Graph Neural Network (GNN) framework that integrates node attributes and graph structure to enhance GNNs' link prediction skills, makes a substantial contribution. Utilizing an actual dataset with 21,900 APIs, 6,435 Mashups, and 13, 340 interactions, ProgrammableWeb.com was the source of the evaluation. Eighty percent of the data were test sets and twenty percent were training sets after single API-invocation Mashups were eliminated. The results demonstrate high link prediction accuracy, which is attributed to the incorporation of structural encoding in embedding learning and improved collaborative signal extraction from users and APIs, which improves API recommendation performance overall.