The Flow has not summarised this story yet — read it at arXiv Machine Learning.
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.
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.
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.
arXiv:2606. 28916v1 Announce Type: cross Abstract: We introduce GRAB, a constructor-encoder-bridge pipeline for table question answering.
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...
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.