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

TL;DR

Rel-HNN introduces a hypergraph neural network framework that models relational databases at a fine-grained level, capturing intra-tuple relationships and enabling scalable multi-GPU training for improved learning performance.

Contribution

The paper presents a novel hypergraph-based model for relational data and a split-parallel training algorithm, enhancing scalability and capturing detailed relational structures.

Findings

Rel-HNN outperforms existing methods in classification and regression tasks.

Split-parallel training achieves up to 3.18x speedup on large datasets.

The approach effectively models intra-tuple relationships in RDBs.

Abstract

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.