RelGNN passes messages along schema-derived atomic routes through junction tables and improves over heterogeneous GNN baselines on most RelBench tasks, with the largest gain on one trial-database regression task.
Supervised learning on relational databases with graph neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RelGNN: Composite Message Passing for Relational Deep Learning
RelGNN passes messages along schema-derived atomic routes through junction tables and improves over heterogeneous GNN baselines on most RelBench tasks, with the largest gain on one trial-database regression task.