Retrieving the right tables is a prerequisite for Text-to-SQL over realistic databases.
Dense table retrievers rank schema elements independently, but this ignores a key source of evidence: some required tables are not mentioned in the question and become identifiable only through their join relationships to already relevant tables.
We introduce JOINGR
JOINGR is a join-aware table retrieval method that treats the database join graph as the retrieval space.
Columns are represented as graph nodes, while intra-table and foreign-key relationships are represented as typed edges.
Given a question, JOINGR selects semantically similar anchor tables, traverses join edges with a query-conditioned scorer, and aggregates the resulting edge deposits into table scores.
The scorer is a lightweight MLP on top of frozen query, node, and edge embeddings, trained with a pairwise margin loss over gold tables.
Experiments
On BIRD and Spider datasets, JOINGR is competitive with the strongest retrieval baselines.
On BEAVER, a challenging enterprise benchmark with multi-hop table requirements, JOINGR substantially improves recall over dense retrieval and re-ranking baselines.
Cross-domain Experiments
Cross-domain experiments show that the learned scorer transfers across benchmarks, indicating that the method captures reusable joingraph traversal behavior.