analiza aiqbench
RelGT-AC advances relational deep learning by integrating a column masking strategy and a TF-IDF text encoder to effectively handle heterogeneous database structures for autocomplete tasks. The model demonstrates robust performance across regression and classification benchmarks, specifically outperforming GraphSAGE on text-heavy eligibility scenarios by recovering lexical signals often lost in standard categorical encoders. This work offers a practical solution for intelligent form-filling in enterprise systems where data spans multiple tables with mixed temporal and structural characteristics.
RelGT-AC: A Relational Graph Transformer for Autocomplete Tasks in Relational Databases
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.
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.
12 pages, 6 figures. Code and model checkpoints available at this https URL
Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2606.03040 [cs.AI]
(or arXiv:2606.03040v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.03040 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 295 cuvinte
Subiecte conexe
QUARTET: Quad-branch cross-Attention and Random-walk Traces for Enhancing Transformers on Relational Graphs
arXiv · 24 sept. 2026
When they can perform a task, AIs are much cheaper than humans
LessWrong · 27 sept. 2026
Gaussian Relational Graph Transformer
arXiv · 30 sept. 2026
Temporal Heterogeneous Graph Pretraining for Relational Deep Learning
arXiv · 30 sept. 2026