RelGT-AC: A Relational Graph Transformer for Autocomplete Tasks in Relational Databases
Quick Answer
This paper shows that RelGT-AC, a Relational Graph Transformer, enhances autocomplete tasks in relational databases by introducing a column masking strategy, a unified task head, and a TF-IDF encoder.
Quick Take
RelGT-AC, a Relational Graph Transformer, enhances autocomplete tasks in relational databases by introducing a column masking strategy, a unified task head, and a TF-IDF encoder. It outperforms GraphSAGE on all regression tasks and achieves up to +10 AUROC points on text-heavy tasks across three RelBench v2 datasets.
Key Points
- Introduces column masking to avoid trivial solutions during subgraph encoding.
- Supports binary classification, multiclass classification, and regression in one model.
- TF-IDF encoder recovers strong lexical signals from free-text columns.
- Outperforms GraphSAGE on all regression autocomplete tasks.
- Achieves up to +10 AUROC points on text-heavy eligibility tasks.
Paper Resources
Article Content
From source RSS / original summaryarXiv: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. Relational Deep Learning (RDL) addresses this by representing databases as heterogeneous graphs and applying graph neural networks (GNNs) directly.
RelBench v2 recently introduced autocomplete tasks -- a practically motivated task type where the goal is to predict an existing column value from relational context, analogous to an intelligent form-filling assistant.
We propose RelGT-AC (Relational Graph Transformer for Autocomplete), extending the RelGT architecture with three targeted contributions: (1) a column masking strategy that prevents trivial solutions by masking the target column during subgraph encoding; (2) a unified task head supporting binary classification, multiclass classification, and regression autocomplete tasks within a single model; and (3) a TF-IDF text encoder that automatically detects and encodes free-text columns, recovering strong lexical signal that categorical encoders discard.
Across 7 tasks spanning 3 RelBench v2 datasets (rel-trial, rel-f1, rel-stack), RelGT-AC outperforms the GraphSAGE baseline on all 3 regression autocomplete tasks and achieves up to +10 AUROC points on text-heavy eligibility tasks via the TF-IDF encoder.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Automatic Ordinary Differential Equations Discovery For Biological Systems Using Powered Agentic System
The MEDA system utilizes large language models and symbolic regression to autonomously discover ordinary differential equations for biological systems, achieving strong structural recovery and biologically plausible models. It outperforms existing methods by integrating domain knowledge and mechanistic constraints, demonstrating effective retrieval and extrapolation capabilities.