MetaRTL is a two-stage framework for relational table learning that first generates lightweight pre-trained table embeddings and then applies non‑parametric message passing to extract meta‑path features. These features are aggregated using an attention module called MetaAttn, shifting computation from deep GNN stacks to efficient meta‑path aggregation. Experiments on 10 real‑world datasets across 24 tasks show that MetaRTL achieves strong performance while reducing computational cost.
By Ken Zhong, Weichen Li, Zheng Wang
RDL-Bench is a new benchmark for task-aware question answering over relational databases, introduced in arXiv:2610.21382v1. It categorizes user questions into reasoning-oriented queries, which depend on the current database state, and prediction-oriented queries, which rely on future outcomes under temporal constraints. Each benchmark instance includes a natural-language question, task metadata, schema details, temporal context, executable evidence or target-construction logic, and denotation-level ground truth, supporting evaluation in both native solver and task-aware modular system settings.
By Yao Cheng, Siqiang Luo
arXiv:2608. 13023v1 Announce Type: new Abstract: Relational Deep Learning (RDL) models multi-tabular databases as temporal heterogeneous graphs to enable end-to-end representation learning.
By Jakub Pele\v{s}ka, Gustav \v{S}\'ir
arXiv:2606. 28916v1 Announce Type: cross Abstract: We introduce GRAB, a constructor-encoder-bridge pipeline for table question answering.
By Simone Varriale, Tamara Cucumides, Floris Geerts, Paolo Papotti
arXiv:2610.03625v1 Announce Type: cross
Abstract: Relational databases are among the most widely deployed forms of structured knowledge, and natural language access to them requires grounding languag...
By Darian Lee, Shannon Rumsey, Jack St. Clair, Xinyi Tang, Aditya Bansal, Yuanming Shi
arXiv:2606. 08491v1 Announce Type: new Abstract: Relational deep learning (RDL) converts relational databases (RDBs) into heterogeneous graphs, but graphs derived directly from database schemas are often not well suited for how graph neural networks (GNNs) perform relational reasoning.
By Yao Cheng, Siqiang Luo
arXiv:2606. 03040v1 Announce Type: new Abstract: Relational databases underpin modern enterprise, scientific, and healthcare systems, yet predictive machine learning on such data remains challenging due to their multi-table, heterogeneous, and temporal structure.
By Phillip Jiang
arXiv:2610.20534v1 Announce Type: new
Abstract: Relational deep learning has emerged as a powerful paradigm for learning end-to-end predictive models over relational databases by representing them as...
By Viet The Nguyen, Vijay Prakash Dwivedi, Gunther Gust
arXiv:2607. 03659v1 Announce Type: cross Abstract: Relational databases (RDBs) are the primary data infrastructure in many enterprises, yet recent deep learning methods designed for RDBs have been evaluated under inconsistent experimental protocols, making fair comparison difficult.
By Kazi F. Akhter, Bharath Ajendla, Manar D. Samad
GENSCRIPT is an inference‑only pipeline that generates synthetic data without training a generative model. It creates a deterministic statistical profile of the source data, uses a language model to infer field semantics and cross‑column constraints, and then compiles these into an executable sampler that works for single‑table, temporal, and relational data. The method builds generators in minutes, samples large datasets quickly, and achieves fidelity comparable to leading methods while preserving key data relationships such as 1‑to‑1 mappings and primary‑foreign key constraints.
By Zilong Zhao, Abdul Raheem, Jiayu Li, Sohei Arisaka, Darius Lim Hong Yi, Milad Abdollahzadeh, Uzair Javaid, Biplab Sikdar
The paper introduces FlockMTL, an extension for database management systems that deeply integrates large language models and retrieval‑augmented generation into DuckDB. It provides model‑driven scalar and aggregate functions, cost‑based optimizations like batching and caching, and new SQL DDL abstractions (PROMPT and MODEL) to treat LLMs as first‑class schema objects. These features aim to simplify the development of knowledge‑intensive analytical applications by reducing the effort required to orchestrate heterogeneous data systems and manage LLM context.
By Anas Dorbani, Sunny Yasser, Jimmy Lin, Amine Mhedhbi
arXiv:2608. 16319v1 Announce Type: new Abstract: This first release of Prior Labs in relational learning shows our continued commitment to open science.
By Adrian Hayler, Klemens Fl\"oge, Alan Arazi, Rishabh Ranjan, Jure Leskovec, Felix Birkel, Brendan Roof, Anurag Garg, Kristina Collins, Lydia Sidhoum, Jonas K\"ubler, Siyuan Guo, Oscar Key, Jan Hendrik Metzen, Rylee Grace, David Salinas, Arthur Cahu, Simon Bing, Benjamin J\"ager, Tuana \c{C}elik, Mihir Manium, Vitor Monteiro, Jake Robertson, Jerry Chen, Eliott Kalfon, Tom\'as Pereda, Lilly Wehrhahn, Dominik Safaric, Tobias Schroeder, Georg Grab, Diana Kriuchkova, Clara Cornu, Philipp Singer, Nick Erickson, Vahid Balazadeh, Marie Salmon, Simone Alessi, K\"ur\c{s}at Kaya, Philipp Jund, L\'eo Grinsztajn, Yann LeCun, Bernhard Sch\"olkopf, Madelon Hulsebos, Lennart Purucker, Sauraj Gambhir, Frank Hutter, Noah Hollmann