Budgeted Interactive Property Graph Repair with Graph Neural Networks
Published in Proceedings of the ACM on Management of Data (PACMMOD), SIGMOD 2027, 2027
Introduces a Graph Neural Network–based framework for interactive property graph repair that combines representation learning, optimization, and human expertise under budget constraints. The framework learns to estimate repair difficulty and allocates a limited budget between automatic inference and targeted human input.
To appear at ACM SIGMOD 2027. A preprint and code will be linked here once available.
DOI: 10.1145/3837100
Recommended citation: A. Pachera, A. Bonifati, A. Mauri. Budgeted Interactive Property Graph Repair with Graph Neural Networks. Proceedings of the ACM on Management of Data (PACMMOD), SIGMOD 2027. DOI: 10.1145/3837100
Download Paper