Skip to content

JoinGR: Learning to Traverse Join Graphs for Table Retrieval

Oct 2026 · 0 citations · 22 references
Computer Science

TL;DR

Cross-domain experiments show that the learned scorer transfers across benchmarks, indicating that the method captures reusable joingraph traversal behavior.

Abstract

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.

View source

Similar papers

Conference Open access Oct 2026

DBRAG: Multi-Table Retrieval-Augmented Generation for Complex Database Queries

Recent advancements in large language models have introduced new capabilities for reasoning over structured data, particularly through program-aided tools that can analyze tables. However, many existing methods address single-table scenarios or assume that the relevant tables are already provided. In practice, users of...

Prince Larbi Ampofo, Ryoji Kubo, D. Difallah · 0 citations
Preprint Aug 2026

PEARL: Front-Loading Relational Chains for Multi-Hop Table Retrieval

PEARL augments the retrieval corpus offline by generating multi-hop queries over pre-identified join paths and reorganizing relevant columns into vertically partitioned corpus units, enabling effective multi-table retrieval without query-time LLM inference.

S. Ho, Hyeongu Kang, Seongku Kang et al. · 0 citations
Conference

TABERTA: A Language Model for Dataset Discovery

TABERTA is presented, a unified retrieval framework for dataset discovery that adapts a bi-encoder language model to relational data by fine-tuning it on serialized representations of tables by fine-tuning the language encoder to diverse structural patterns using optimized strategies that serialize schema and table con...

Enas Khwaileh, L. Traeger, Albert Gatt et al. · 0 citations
#artificial intelligence Preprint Sep 2026

TabJoinBench: A Benchmark for Joinable Table Discovery

This work evaluates representative join discovery methods spanning set-based, feature-based, and learned approaches, together with general-purpose language-model embedding baselines, and publicly release the processed datasets, ground-truth annotations, and generation pipeline to facilitate reproducible evaluation and...

S. De, Jin Wang, Vivek Gupta · 0 citations
Jul 2026

GAS: A Lightweight Framework for Filtered Search over Wide-Table Vectors

Graph with Adaptive Shortcuts (GAS), a framework that leverages historical query logs to build lightweight auxiliary structures, enhancing search efficiency over a single base graph with minimal overhead, and consistently outperforms existing general indexes in wide-table scenarios.

Zi-Yuan He, Yu-Xiang Wang, Yu Sun et al. · 0 citations
Preprint Oct 2026

Prune First, Decide Fast: Scalable Semantic Query Processing with JEVDB

JEVDB is presented, a scalable semantic database system that uses fast, typed decision models for semantic filters, joins, classification, and ranking, while selectively escalating uncertain cases to generative LLMs.

Zheng-Le Wang, Han-Xu Yan, Fuheng Zhao et al. · 3 citations · ⚡1

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.