Metraipolis › archive › dc_edc0be702255
JoinGR: Learning to Traverse Join Graphs for Table Retrieval — arXiv:2610.01064
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.01064
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:12:39.969Z
- SHA-256 of the archived text
0c3213d091b8efc95c0add223399cc290e3bdc6e5a7ac872e67ece22415fa2e5- Stable URL of this page
https://metraipolis.com/documento/dc_edc0be702255
How to cite
JoinGR: Learning to Traverse Join Graphs for Table Retrieval — arXiv:2610.01064 — arXiv (en), https://arxiv.org/abs/2610.01064 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_edc0be702255 (Metraipolis archive dc_edc0be702255, sha256 0c3213d091b8efc95c0add223399cc290e3bdc6e5a7ac872e67ece22415fa2e5)
BibTeX
@misc{dcedc0be702255,
title = {JoinGR: Learning to Traverse Join Graphs for Table Retrieval — arXiv:2610.01064},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.01064},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_edc0be702255; sha256 0c3213d091b8efc95c0add223399cc290e3bdc6e5a7ac872e67ece22415fa2e5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01064. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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, 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. 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 show that the learned scorer transfers across benchmarks, indicating that the method captures reusable joingraph traversal behavior. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Databases (cs.DB); Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2610.01064 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T10:21:28.152Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).