# RelGNN: Composite Message Passing for Relational Deep Learning

arXiv: https://arxiv.org/abs/2502.06784 · HTML: https://mlsanity.com/paper/2502.06784/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 10 Feb 2025.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [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)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Representation Learning on Graphs with Jumping Knowledge Networks](https://mlsanity.com/paper/1806.03536/) (2018)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Neural Graph Collaborative Filtering](https://mlsanity.com/paper/1905.08108/) (2019)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification](https://mlsanity.com/paper/2009.03509/) (2020)
- [Principal Neighbourhood Aggregation for Graph Nets](https://mlsanity.com/paper/2004.05718/) (2020)
- [MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding](https://mlsanity.com/paper/2002.01680/) (2020)
- [Time2Vec: Learning a Vector Representation of Time](https://mlsanity.com/paper/1907.05321/) (2019)
- [Identity-aware Graph Neural Networks](https://mlsanity.com/paper/2101.10320/) (2021)
- [Do We Really Need Complicated Model Architectures For Temporal Networks?](https://mlsanity.com/paper/2302.11636/) (2023)
- [A Survey of Heterogeneous Information Network Analysis](https://mlsanity.com/paper/1511.04854/) (2015)
- [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)
- [Supervised Learning on Relational Databases with Graph Neural Networks](https://mlsanity.com/paper/2002.02046/) (2020)
- [HiGPT: Heterogeneous Graph Language Model](https://mlsanity.com/paper/2402.16024/) (2024)
- [On the Stability of Expressive Positional Encodings for Graphs](https://mlsanity.com/paper/2310.02579/) (2023)
- [PyTorch Frame: A Modular Framework for Multi-Modal Tabular Learning](https://mlsanity.com/paper/2404.00776/) (2024)
- [Learning Efficient Positional Encodings with Graph Neural Networks](https://mlsanity.com/paper/2502.01122/) (2025)
- [ContextGNN: Beyond Two-Tower Recommendation Systems](https://mlsanity.com/paper/2411.19513/) (2024)
- [Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks](https://mlsanity.com/paper/1807.03490/) (2018)
- [Tackling prediction tasks in relational databases with LLMs](https://mlsanity.com/paper/2411.11829/) (2024)
- [Meta-Path Guided Embedding for Similarity Search in Large-Scale Heterogeneous Information Networks](https://mlsanity.com/paper/1610.09769/) (2016)

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

- [Griffin: Towards a Graph-Centric Relational Database Foundation Model](https://mlsanity.com/paper/2505.05568/) (2025)
- [Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data](https://mlsanity.com/paper/2510.06377/) (2025)
- [Relational Graph Transformer](https://mlsanity.com/paper/2505.10960/) (2025)
- [Relational Deep Learning: Challenges, Foundations and Next-Generation Architectures](https://mlsanity.com/paper/2506.16654/) (2025)
- [RelBench v2: A Large-Scale Benchmark and Repository for Relational Data](https://mlsanity.com/paper/2602.12606/) (2026)
- [KumoRFM-2: Scaling Foundation Models for Relational Learning](https://mlsanity.com/paper/2604.12596/) (2026)
- [TabPFN-3: Technical Report](https://mlsanity.com/paper/2605.13986/) (2026)
- [Relational In-Context Learning via Synthetic Pre-training with Structural Prior](https://mlsanity.com/paper/2603.03805/) (2026)
- [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)
- [Predictive Query Language: A Domain-Specific Language for Predictive Modeling on Relational Databases](https://mlsanity.com/paper/2602.09572/) (2026)
- [Towards Anomaly Detection on Relational Data](https://mlsanity.com/paper/2606.18621/) (2026)
- [Task-Agnostic Contrastive Pretraining for Relational Deep Learning](https://mlsanity.com/paper/2506.22530/) (2025)
- [Integrating Temporal and Structural Context in Graph Transformers for Relational Deep Learning](https://mlsanity.com/paper/2511.04557/) (2025)
- [OpenRFM: Dissecting Relational In-Context Learning](https://mlsanity.com/paper/2606.04320/) (2026)
- [ReFuGe: Feature Generation for Prediction Tasks on Relational Databases with LLM Agents](https://mlsanity.com/paper/2601.17735/) (2026)
- [Advancing Open and Reproducible Relational Learning: RelArena-α, TabPFN-Rel and RPI](https://mlsanity.com/paper/2608.16319/) (2026)
- [Relatron: Automating Relational Machine Learning over Relational Databases](https://mlsanity.com/paper/2602.22552/) (2026)
- [RelAgent: LLM Agents as Data Scientists for Relational Learning](https://mlsanity.com/paper/2605.07840/) (2026)
- [Database Views as Explanations for Relational Deep Learning](https://mlsanity.com/paper/2509.09482/) (2025)
- [Relational Database Distillation: From Structured Tables to Condensed Graph Data](https://mlsanity.com/paper/2510.06980/) (2025)
- [Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases](https://mlsanity.com/paper/2603.07916/) (2026)
- [RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases](https://mlsanity.com/paper/2605.23241/) (2026)
- [Incorporating Deep Learning Design in Database Queries](https://mlsanity.com/paper/2605.24207/) (2026)
- [A Fair Benchmarking of Deep Relational Database Learning Models](https://mlsanity.com/paper/2607.03659/) (2026)
- [Surprisingly Simple and Effective Multi-Domain Graph Foundation Model through Graph-to-Table Alignment](https://mlsanity.com/paper/2607.11374/) (2026)
- [Declarative by Design, Assistable Only by Convention: Benchmarking Multi-Agent Frameworks for AI-Assistability](https://mlsanity.com/paper/2602.11198/) (2026)
- [Gaussian Relational Graph Transformer](https://mlsanity.com/paper/2605.15575/) (2026)
- [Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning](https://mlsanity.com/paper/2605.21475/) (2026)
- [RelGT-AC: A Relational Graph Transformer for Autocomplete Tasks in Relational Databases](https://mlsanity.com/paper/2606.03040/) (2026)

## Abstract (arXiv)

Predictive tasks on relational databases are critical in real-world applications spanning e-commerce, healthcare, and social media. To address these tasks effectively, Relational Deep Learning (RDL) encodes relational data as graphs, enabling Graph Neural Networks (GNNs) to exploit relational structures for improved predictions. However, existing RDL methods often overlook the intrinsic structural properties of the graphs built from relational databases, leading to modeling inefficiencies, particularly in handling many-to-many relationships. Here we introduce RelGNN, a novel GNN framework specifically designed to leverage the unique structural characteristics of the graphs built from relational databases. At the core of our approach is the introduction of atomic routes, which are simple paths that enable direct single-hop interactions between the source and destination nodes. Building upon these atomic routes, RelGNN designs new composite message passing and graph attention mechanisms that reduce redundancy, highlight key signals, and enhance predictive accuracy. RelGNN is evaluated on 30 diverse real-world tasks from Relbench (Fey et al., 2024), and achieves state-of-the-art performance on the vast majority of tasks, with improvements of up to 25%. Code is available at https://github.com/snap-stanford/RelGNN.