mlsanityData to 7 Oct 2026

RelBench: A Benchmark for Deep Learning on Relational Databases

arXiv 2407.20060 ↗First posted 29 Jul 2024cs.LG cs.AI cs.DBcited by 90

Not on the map. Why?

Abstract (arXiv)

We present RelBench, a public benchmark for solving predictive tasks over relational databases with graph neural networks. RelBench provides databases and tasks spanning diverse domains and scales, and is intended to be a foundational infrastructure for future research. We use RelBench to conduct the first comprehensive study of Relational Deep Learning (RDL) (Fey et al., 2024), which combines graph neural network predictive models with (deep) tabular models that extract initial entity-level representations from raw tables. End-to-end learned RDL models fully exploit the predictive signal encoded in primary-foreign key links, marking a significant shift away from the dominant paradigm of manual feature engineering combined with tabular models. To thoroughly evaluate RDL against this prior gold-standard, we conduct an in-depth user study where an experienced data scientist manually engineers features for each task. In this study, RDL learns better models whilst reducing human work needed by more than an order of magnitude. This demonstrates the power of deep learning for solving predictive tasks over relational databases, opening up many new research opportunities enabled by RelBench.

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). Builds on 17 of its 34 references that are in the map. First posted on arXiv 29 Jul 2024.

Builds on

17 of 34 references.

References · 17

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  6. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  7. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  8. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  9. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  10. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  11. 2019Neural Graph Collaborative Filteringcited by 660
  12. 2021Identity-aware Graph Neural Networkscited by 197
5 more
  1. 2023Temporal Graph Benchmark for Machine Learning on Temporal Graphscited by 137
  2. 2023Relational Deep Learning: Graph Representation Learning on Relational Databasescited by 55
  3. 2020Supervised Learning on Relational Databases with Graph Neural Networkscited by 48
  4. 2024PyTorch Frame: A Modular Framework for Multi-Modal Tabular Learningcited by 32
  5. 2017An Empirical Analysis of Feature Engineering for Predictive Modelingcited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 28; 2026: 57.

90 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  2. 2025Position: Graph Learning Will Lose Relevance Due To Poor Benchmarkscited by 52
  3. 2025PyG 2.0: Scalable Learning on Real World Graphscited by 49
  4. 2025RelGNN: Composite Message Passing for Relational Deep Learningcited by 45
  5. 2025Griffin: Towards a Graph-Centric Relational Database Foundation Modelcited by 41
  6. 2025Relational Transformer: Toward Zero-Shot Foundation Models for Relational Datacited by 32
  7. 2025Relational Graph Transformercited by 30
  8. 2025Turning Tabular Foundation Models into Graph Foundation Modelscited by 30
  9. 2025Relational Deep Learning: Challenges, Foundations and Next-Generation Architecturescited by 22
  10. 2025Learning Efficient Positional Encodings with Graph Neural Networkscited by 21
  11. 2024ContextGNN: Beyond Two-Tower Recommendation Systemscited by 19
  12. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Surveycited by 18
38 more
  1. 2026RelBench v2: A Large-Scale Benchmark and Repository for Relational Datacited by 17
  2. 2026PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Modelscited by 15
  3. 2026KumoRFM-2: Scaling Foundation Models for Relational Learningcited by 15
  4. 2024Tackling prediction tasks in relational databases with LLMscited by 14
  5. 2026Relational In-Context Learning via Synthetic Pre-training with Structural Priorcited by 11
  6. 2024Transformers Meet Relational Databasescited by 9
  7. 2025Joint Relational Database Generation via Graph-Conditional Diffusion Modelscited by 8
  8. 2025RDB2G-Bench: A Comprehensive Benchmark for Automatic Graph Modeling of Relational Databasescited by 8
  9. 2025REDELEX: A Framework for Relational Deep Learning Explorationcited by 8
  10. 2026No Need to Train Your RDB Foundation Modelcited by 8
  11. 2024A Self-Explainable Heterogeneous GNN for Relational Deep Learningcited by 7
  12. 2025Nonparametric Teaching for Graph Property Learnerscited by 5
  13. 2025Position: Foundation Models for Tabular Data within Systemic Contexts Need Groundingcited by 5
  14. 2025Retrieval-Augmented Generation of Ontologies from Relational Databasescited by 4
  15. 2025Task-Agnostic Contrastive Pretraining for Relational Deep Learningcited by 4
  16. 2025A Pre-training Framework for Relational Data with Information-theoretic Principlescited by 4
  17. 2025Integrating Temporal and Structural Context in Graph Transformers for Relational Deep Learningcited by 4
  18. 2026OpenRFM: Dissecting Relational In-Context Learningcited by 4
  19. 2026Towards Anomaly Detection on Relational Datacited by 4
  20. 2025RelDiff: Relational Data Generative Modeling with Graph-Based Diffusion Modelscited by 3
  21. 2026RDBLearn: Simple In-Context Prediction Over Relational Databasescited by 3
  22. 2026The Post-GCN Decade Revisited: Curvature-Stratified Evaluation of Relational Learningcited by 3
  23. 2026Grables: Tabular Learning Beyond Independent Rowscited by 2
  24. 2026Finding Connections: Membership Inference Attacks for the Multi-Table Synthetic Data Settingcited by 2
  25. 2026LakeMLB: Data Lake Machine Learning Benchmarkcited by 2
  26. 2026Relatron: Automating Relational Machine Learning over Relational Databasescited by 2
  27. 2026Task Scarcity and Label Leakage in Relational Transfer Learningcited by 2
  28. 2026Sheet As Token: A Graph-Enhanced Representation for Multi-Sheet Spreadsheet Understandingcited by 2
  29. 2026RelAgent: LLM Agents as Data Scientists for Relational Learningcited by 2
  30. 2026MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Imagecited by 2
  31. 2026Advancing Open and Reproducible Relational Learning: RelArena-α, TabPFN-Rel and RPIcited by 2
  32. 2025RCCFormer: A Robust Crowd Counting Network Based on Transformercited by 1
  33. 2025Database Views as Explanations for Relational Deep Learningcited by 1
  34. 2025Relational Database Distillation: From Structured Tables to Condensed Graph Datacited by 1
  35. 2025Agentic NL2SQL to Reduce Computational Costscited by 1
  36. 2025RELATE: A Schema-Agnostic Perceiver Encoder for Multimodal Relational Graphscited by 1
  37. 2026Rethinking GNNs and Missing Features: Challenges, Evaluation and a Robust Solutioncited by 1
  38. 2026Uncertainty-Aware Delivery Delay Duration Prediction via Multi-Task Deep Learningcited by 1

50 most cited of 90 All 90 (JSON)