# Relatron: Automating Relational Machine Learning over Relational Databases

arXiv: https://arxiv.org/abs/2602.22552 · HTML: https://mlsanity.com/paper/2602.22552/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 76 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 30 of 50)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [TUDataset: A collection of benchmark datasets for learning with graphs](https://mlsanity.com/paper/2007.08663/) (2020)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs](https://mlsanity.com/paper/1802.10026/) (2018)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Principal Neighbourhood Aggregation for Graph Nets](https://mlsanity.com/paper/2004.05718/) (2020)
- [An Investigation into Neural Net Optimization via Hessian Eigenvalue Density](https://mlsanity.com/paper/1901.10159/) (2019)
- [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021)
- [Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs](https://mlsanity.com/paper/2307.03393/) (2023)
- [Task2Vec: Task Embedding for Meta-Learning](https://mlsanity.com/paper/1902.03545/) (2019)
- [Design Space for Graph Neural Networks](https://mlsanity.com/paper/2011.08843/) (2020)
- [Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges](https://mlsanity.com/paper/2107.05847/) (2021)
- [RelBench: A Benchmark for Deep Learning on Relational Databases](https://mlsanity.com/paper/2407.20060/) (2024)
- [Position: Graph Foundation Models are Already Here](https://mlsanity.com/paper/2402.02216/) (2024)
- [Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification](https://mlsanity.com/paper/2406.08993/) (2024)
- [Auto-GNN: Neural Architecture Search of Graph Neural Networks](https://mlsanity.com/paper/1909.03184/) (2019)
- [Neural Common Neighbor with Completion for Link Prediction](https://mlsanity.com/paper/2302.00890/) (2023)
- [Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond](https://mlsanity.com/paper/2209.06177/) (2022)
- [Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks](https://mlsanity.com/paper/2502.14546/) (2025)
- [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)
- [GraphNAS: Graph Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1904.09981/) (2019)
- [Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?](https://mlsanity.com/paper/2306.01323/) (2023)

## Built on by (most cited first, 2 of 2)

- [OpenRFM: Dissecting Relational In-Context Learning](https://mlsanity.com/paper/2606.04320/) (2026)
- [AutoGrable: What Is a Good Graph for a Table?](https://mlsanity.com/paper/2608.11431/) (2026)

## Abstract (arXiv)

Predictive modeling over relational databases (RDBs) powers applications, yet remains challenging due to capturing both cross-table dependencies and complex feature interactions. Relational Deep Learning (RDL) methods automate feature engineering via message passing, while classical approaches like Deep Feature Synthesis (DFS) rely on predefined non-parametric aggregators. Despite performance gains, the comparative advantages of RDL over DFS and the design principles for selecting effective architectures remain poorly understood. We present a comprehensive study that unifies RDL and DFS in a shared design space and conducts architecture-centric searches across diverse RDB tasks. Our analysis yields three key findings: (1) RDL does not consistently outperform DFS, with performance being highly task-dependent; (2) no single architecture dominates across tasks, underscoring the need for task-aware model selection; and (3) validation accuracy is an unreliable guide for architecture choice. This search yields a model performance bank that links architecture configurations to their performance; leveraging this bank, we analyze the drivers of the RDL-DFS performance gap and introduce two task signals -- RDB task homophily and an affinity embedding that captures size, path, feature, and temporal structure -- whose correlation with the gap enables principled routing. Guided by these signals, we propose Relatron, a task embedding-based meta-selector that chooses between RDL and DFS and prunes the within-family search. Lightweight loss-landscape metrics further guard against brittle checkpoints by preferring flatter optima. In experiments, Relatron resolves the "more tuning, worse performance" effect and, in joint hyperparameter-architecture optimization, achieves up to 18.5% improvement over strong baselines with 10x lower cost than Fisher information-based alternatives.