mlsanityData to 13 Oct 2026

Supervised Learning on Relational Databases with Graph Neural Networks

arXiv 2002.02046 ↗First posted 6 Feb 2020cs.LG cs.AI cs.DBcited by 48

Not on the map. Why?

Abstract (arXiv)

The majority of data scientists and machine learning practitioners use relational data in their work [State of ML and Data Science 2017, Kaggle, Inc.]. But training machine learning models on data stored in relational databases requires significant data extraction and feature engineering efforts. These efforts are not only costly, but they also destroy potentially important relational structure in the data. We introduce a method that uses Graph Neural Networks to overcome these challenges. Our proposed method outperforms state-of-the-art automatic feature engineering methods on two out of three datasets.

Key facts. Cited by 48 papers in the map (data through 13 Oct 2026). First posted on arXiv 6 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 7; 2024: 8; 2025: 15; 2026: 13.

48 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  2. 2024RelBench: A Benchmark for Deep Learning on Relational Databasescited by 91
  3. 2023Relational Deep Learning: Graph Representation Learning on Relational Databasescited by 55
  4. 2025RelGNN: Composite Message Passing for Relational Deep Learningcited by 45
  5. 2025Griffin: Towards a Graph-Centric Relational Database Foundation Modelcited by 43
  6. 2021ARM-Net: Adaptive Relation Modeling Network for Structured Datacited by 24
  7. 2023GFS: Graph-based Feature Synthesis for Prediction over Relational Databasescited by 16
  8. 2024Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directionscited by 13
  9. 2026Relational In-Context Learning via Synthetic Pre-training with Structural Priorcited by 12
  10. 20244DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on Relational DBscited by 11
  11. 2024Why LLMs Are Bad at Synthetic Table Generation (and what to do about it)cited by 10
  12. 2024Transformers Meet Relational Databasescited by 9
36 more
  1. 2026No Need to Train Your RDB Foundation Modelcited by 9
  2. 2022Generating Realistic Synthetic Relational Data through Graph Variational Autoencoderscited by 8
  3. 2023Graph Neural Network contextual embedding for Deep Learning on Tabular Datacited by 8
  4. 2025OpenGU: A Comprehensive Benchmark for Graph Unlearningcited by 8
  5. 2025RDB2G-Bench: A Comprehensive Benchmark for Automatic Graph Modeling of Relational Databasescited by 8
  6. 2025REDELEX: A Framework for Relational Deep Learning Explorationcited by 8
  7. 2024Rank and Align: Towards Effective Source-free Graph Domain Adaptationcited by 7
  8. 2025AutoG: Towards automatic graph construction from tabular datacited by 7
  9. 2023Towards Foundation Models for Relational Databases [Vision Paper]cited by 6
  10. 2025From Features to Structure: Task-Aware Graph Construction for Relational and Tabular Learning with GNNscited by 6
  11. 2025Task-Agnostic Contrastive Pretraining for Relational Deep Learningcited by 4
  12. 2025A Pre-training Framework for Relational Data with Information-theoretic Principlescited by 4
  13. 2023RDBench: ML Benchmark for Relational Databasescited by 3
  14. 2026RDBLearn: Simple In-Context Prediction Over Relational Databasescited by 3
  15. 2022Flaky Performances when Pretraining on Relational Databasescited by 2
  16. 2023Embeddings for Tabular Data: A Surveycited by 2
  17. 2024Differentially Private Synthetic Data Generation for Relational Databasescited by 2
  18. 2023AdaMedGraph: Adaboosting Graph Neural Networks for Personalized Medicinecited by 1
  19. 2025RCCFormer: A Robust Crowd Counting Network Based on Transformercited by 1
  20. 2025Database Views as Explanations for Relational Deep Learningcited by 1
  21. 2025Relational Database Distillation: From Structured Tables to Condensed Graph Datacited by 1
  22. 2026RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databasescited by 1
  23. 2026A Fair Benchmarking of Deep Relational Database Learning Modelscited by 1
  24. 2022Graph Representation Learning via Aggregation Enhancementcited by 0
  25. 2022Time Series of Non-Additive Metrics: Identification and Interpretation of Contributing Factors of Variance by Linear Decompositioncited by 0
  26. 2025Rel-HNN: Split Parallel Hypergraph Neural Network for Learning on Relational Databasescited by 0
  27. 2025Synthesize, Retrieve, and Propagate: A Unified Predictive Modeling Framework for Relational Databasescited by 0
  28. 2025Graph-Based Feature Augmentation for Predictive Tasks on Relational Datasetscited by 0
  29. 2026From Schema to Signal: Retrieval-Augmented Modeling for Relational Data Analyticscited by 0
  30. 2026Gaussian Relational Graph Transformercited by 0
  31. 2026What Makes a Desired Graph for Relational Deep Learning?cited by 0
  32. 2026Universal Encoders for Modular Relational Deep Learningcited by 0
  33. 2026InvWeaver: Deductive Feedback for Invariant Synthesis in Interacting-Loop Programscited by 0
  34. 2026Incremental Evaluation and Training in Relational Deep Learningcited by 0
  35. 2026MetaRTL: Meta-path Attention Enhanced Relational Table Learningcited by 0
  36. 2026RelICL: Training-free Relational Learning with Tabular Foundation Modelscited by 0