RelGT-AC: A Relational Graph Transformer for Autocomplete Tasks in Relational Databases

Researchers have developed RelGT-AC, a relational graph transformer designed to predict missing column values in relational databases, functioning as an intelligent form-filling assistant. The model introduces a column masking strategy, a unified task head for multiple prediction types, and a TF-IDF text encoder, outperforming baseline models on regression tasks and achieving up to +10 AUROC points on text-heavy eligibility tasks across three RelBench v2 datasets.

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. 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.