Relaxing join orders to a differentiable soft adjacency matrix and optimizing with gradients plus a GNN cost model yields plans that match or beat discrete search while scaling better on graph datasets.
On the role of sparsity and DAG constraints for learning linear dags
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Gradient-Based Join Ordering
Relaxing join orders to a differentiable soft adjacency matrix and optimizing with gradients plus a GNN cost model yields plans that match or beat discrete search while scaling better on graph datasets.