# Supervised Learning on Relational Databases with Graph Neural Networks

arXiv: https://arxiv.org/abs/2002.02046 · HTML: https://mlsanity.com/paper/2002.02046/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2020.

## Built on by (most cited first, 30 of 48)

- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [RelBench: A Benchmark for Deep Learning on Relational Databases](https://mlsanity.com/paper/2407.20060/) (2024)
- [Relational Deep Learning: Graph Representation Learning on Relational Databases](https://mlsanity.com/paper/2312.04615/) (2023)
- [RelGNN: Composite Message Passing for Relational Deep Learning](https://mlsanity.com/paper/2502.06784/) (2025)
- [Griffin: Towards a Graph-Centric Relational Database Foundation Model](https://mlsanity.com/paper/2505.05568/) (2025)
- [ARM-Net: Adaptive Relation Modeling Network for Structured Data](https://mlsanity.com/paper/2107.01830/) (2021)
- [GFS: Graph-based Feature Synthesis for Prediction over Relational Databases](https://mlsanity.com/paper/2312.02037/) (2023)
- [Relational In-Context Learning via Synthetic Pre-training with Structural Prior](https://mlsanity.com/paper/2603.03805/) (2026)
- [Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directions](https://mlsanity.com/paper/2401.02143/) (2024)
- [4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on Relational DBs](https://mlsanity.com/paper/2404.18209/) (2024)
- [Why LLMs Are Bad at Synthetic Table Generation (and what to do about it)](https://mlsanity.com/paper/2406.14541/) (2024)
- [No Need to Train Your RDB Foundation Model](https://mlsanity.com/paper/2602.13697/) (2026)
- [Transformers Meet Relational Databases](https://mlsanity.com/paper/2412.05218/) (2024)
- [Generating Realistic Synthetic Relational Data through Graph Variational Autoencoders](https://mlsanity.com/paper/2211.16889/) (2022)
- [Graph Neural Network contextual embedding for Deep Learning on Tabular Data](https://mlsanity.com/paper/2303.06455/) (2023)
- [OpenGU: A Comprehensive Benchmark for Graph Unlearning](https://mlsanity.com/paper/2501.02728/) (2025)
- [RDB2G-Bench: A Comprehensive Benchmark for Automatic Graph Modeling of Relational Databases](https://mlsanity.com/paper/2506.01360/) (2025)
- [REDELEX: A Framework for Relational Deep Learning Exploration](https://mlsanity.com/paper/2506.22199/) (2025)
- [Towards Foundation Models for Relational Databases [Vision Paper]](https://mlsanity.com/paper/2305.15321/) (2023)
- [Rank and Align: Towards Effective Source-free Graph Domain Adaptation](https://mlsanity.com/paper/2408.12185/) (2024)
- [AutoG: Towards automatic graph construction from tabular data](https://mlsanity.com/paper/2501.15282/) (2025)
- [From Features to Structure: Task-Aware Graph Construction for Relational and Tabular Learning with GNNs](https://mlsanity.com/paper/2506.02243/) (2025)
- [RDBLearn: Simple In-Context Prediction Over Relational Databases](https://mlsanity.com/paper/2602.18495/) (2026)
- [Task-Agnostic Contrastive Pretraining for Relational Deep Learning](https://mlsanity.com/paper/2506.22530/) (2025)
- [A Pre-training Framework for Relational Data with Information-theoretic Principles](https://mlsanity.com/paper/2507.09837/) (2025)
- [RDBench: ML Benchmark for Relational Databases](https://mlsanity.com/paper/2310.16837/) (2023)
- [Flaky Performances when Pretraining on Relational Databases](https://mlsanity.com/paper/2211.05213/) (2022)
- [Embeddings for Tabular Data: A Survey](https://mlsanity.com/paper/2302.11777/) (2023)
- [Differentially Private Synthetic Data Generation for Relational Databases](https://mlsanity.com/paper/2405.18670/) (2024)
- [AdaMedGraph: Adaboosting Graph Neural Networks for Personalized Medicine](https://mlsanity.com/paper/2311.14304/) (2023)

## Abstract (arXiv)

The majority of data scientists and machine learning practitioners use relational data in their work [State of ML and Data Science 2017, Kaggle, Inc.]. But training machine learning models on data stored in relational databases requires significant data extraction and feature engineering efforts. These efforts are not only costly, but they also destroy potentially important relational structure in the data. We introduce a method that uses Graph Neural Networks to overcome these challenges. Our proposed method outperforms state-of-the-art automatic feature engineering methods on two out of three datasets.