# Rel-HNN: Split Parallel Hypergraph Neural Network for Learning on Relational Databases

arXiv: https://arxiv.org/abs/2507.12562 · HTML: https://mlsanity.com/paper/2507.12562/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 44 references that are in the map.
- First posted on arXiv 16 Jul 2025.

## Builds on (most cited first, 22 of 22)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Gated Graph Sequence Neural Networks](https://mlsanity.com/paper/1511.05493/) (2015)
- [Hypergraph Neural Networks](https://mlsanity.com/paper/1809.09401/) (2018)
- [Diffusion-Convolutional Neural Networks](https://mlsanity.com/paper/1511.02136/) (2015)
- [You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks](https://mlsanity.com/paper/2106.13264/) (2021)
- [RelBench: A Benchmark for Deep Learning on Relational Databases](https://mlsanity.com/paper/2407.20060/) (2024)
- [Supervised Learning on Relational Databases with Graph Neural Networks](https://mlsanity.com/paper/2002.02046/) (2020)
- [HYTREL: Hypergraph-enhanced Tabular Data Representation Learning](https://mlsanity.com/paper/2307.08623/) (2023)
- [Relational Graph Transformer](https://mlsanity.com/paper/2505.10960/) (2025)
- [Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directions](https://mlsanity.com/paper/2401.02143/) (2024)
- [MEGAN: A Generative Adversarial Network for Multi-View Network Embedding](https://mlsanity.com/paper/1909.01084/) (2019)
- [Group interactions modulate critical mass dynamics in social convention](https://mlsanity.com/paper/2103.10411/) (2021)
- [SPARE: A Single-Pass Neural Model for Relational Databases](https://mlsanity.com/paper/2310.13581/) (2023)
- [CardBench: A Benchmark for Learned Cardinality Estimation in Relational Databases](https://mlsanity.com/paper/2408.16170/) (2024)
- [Learning Models over Relational Data: A Brief Tutorial](https://mlsanity.com/paper/1911.06577/) (2019)
- [DPHGNN: A Dual Perspective Hypergraph Neural Networks](https://mlsanity.com/paper/2405.16616/) (2024)
- [Machine Learning over Static and Dynamic Relational Data](https://mlsanity.com/paper/2107.13923/) (2021)

## Abstract (arXiv)

Relational databases (RDBs) are ubiquitous in enterprise and real-world applications. Flattening the database poses challenges for deep learning models that rely on fixed-size input representations to capture relational semantics from the structured nature of relational data. Graph neural networks (GNNs) have been proposed to address this, but they often oversimplify relational structures by modeling all the tuples as monolithic nodes and ignoring intra-tuple associations. In this work, we propose a novel hypergraph-based framework, that we call rel-HNN, which models each unique attribute-value pair as a node and each tuple as a hyperedge, enabling the capture of fine-grained intra-tuple relationships. Our approach learns explicit multi-level representations across attribute-value, tuple, and table levels. To address the scalability challenges posed by large RDBs, we further introduce a split-parallel training algorithm that leverages multi-GPU execution for efficient hypergraph learning. Extensive experiments on real-world and benchmark datasets demonstrate that rel-HNN significantly outperforms existing methods in both classification and regression tasks. Moreover, our split-parallel training achieves substantial speedups -- up to 3.18x for learning on relational data and up to 2.94x for hypergraph learning -- compared to conventional single-GPU execution.