Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases 事件

Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases arXiv:2603.07916v2 Announce Type: replace Abstract: In recent advances, to enable a fully data-driven learning paradigm on relational databases (RDB), relational deep learning (RDL) is proposed to structure the RDB as a heterogeneous entity graph and adopt the graph neural network (GNN) as the predictive model. However, existing RDL methods neglect the imbalance problem of relational data in RDBs and risk under-repres