mlsanityData to 14 Oct 2026

Griffin: Towards a Graph-Centric Relational Database Foundation Model

arXiv 2505.05568 ↗First posted 8 May 2025cs.LG cs.AI cs.DBcited by 47

Not on the map. Why?

Abstract (arXiv)

We introduce Griffin, the first foundation model attemptation designed specifically for Relational Databases (RDBs). Unlike previous smaller models focused on single RDB tasks, Griffin unifies the data encoder and task decoder to handle diverse tasks. Additionally, we enhance the architecture by incorporating a cross-attention module and a novel aggregator. Griffin utilizes pretraining on both single-table and RDB datasets, employing advanced encoders for categorical, numerical, and metadata features, along with innovative components such as cross-attention modules and enhanced message-passing neural networks (MPNNs) to capture the complexities of relational data. Evaluated on large-scale, heterogeneous, and temporal graphs extracted from RDBs across various domains (spanning over 150 million nodes), Griffin demonstrates superior or comparable performance to individually trained models, excels in low-data scenarios, and shows strong transferability with similarity and diversity in pretraining across new datasets and tasks, highlighting its potential as a universally applicable foundation model for RDBs. Code available at https://github.com/yanxwb/Griffin.

Key facts. Cited by 47 papers in the map (data through 14 Oct 2026). Builds on 45 of its 65 references that are in the map. First posted on arXiv 8 May 2025.

Builds on

45 of 65 references.

References · 45

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  4. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  5. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  6. 2021Florence: A New Foundation Model for Computer Visioncited by 804
  7. 2021Revisiting Deep Learning Models for Tabular Datacited by 740
  8. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  9. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 674
  10. 2019TabNet: Attentive Interpretable Tabular Learningcited by 648
  11. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 482
  12. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 434
33 more
  1. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 428
  2. 2020TabTransformer: Tabular Data Modeling Using Contextual Embeddingscited by 409
  3. 2021SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Trainingcited by 319
  4. 2022TabLLM: Few-shot Classification of Tabular Data with Large Language Modelscited by 277
  5. 2024Nomic Embed: Training a Reproducible Long Context Text Embeddercited by 265
  6. 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 243
  7. 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 235
  8. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 232
  9. 2023GraphGPT: Graph Instruction Tuning for Large Language Modelscited by 226
  10. 2022On Embeddings for Numerical Features in Tabular Deep Learningcited by 186
  11. 2020Handling Missing Data with Graph Representation Learningcited by 133
  12. 2023Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learningcited by 133
  13. 2022TransTab: Learning Transferable Tabular Transformers Across Tablescited by 132
  14. 2024TableBench: A Comprehensive and Complex Benchmark for Table Question Answeringcited by 128
  15. 2023GraphText: Graph Reasoning in Text Spacecited by 111
  16. 2024RelBench: A Benchmark for Deep Learning on Relational Databasescited by 96
  17. 2023XTab: Cross-table Pretraining for Tabular Transformerscited by 81
  18. 2024CARTE: Pretraining and Transfer for Tabular Learningcited by 76
  19. 2024TableGPT2: A Large Multimodal Model with Tabular Data Integrationcited by 72
  20. 2024Making Pre-trained Language Models Great on Tabular Predictioncited by 57
  21. 2023Relational Deep Learning: Graph Representation Learning on Relational Databasescited by 56
  22. 2020Supervised Learning on Relational Databases with Graph Neural Networkscited by 48
  23. 2025RelGNN: Composite Message Passing for Relational Deep Learningcited by 48
  24. 2021TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular Datacited by 36
  25. 2024PyTorch Frame: A Modular Framework for Multi-Modal Tabular Learningcited by 32
  26. 2024Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Latercited by 30
  27. 2023UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Sciencecited by 29
  28. 2021TabGNN: Multiplex Graph Neural Network for Tabular Data Predictioncited by 26
  29. 2024ContextGNN: Beyond Two-Tower Recommendation Systemscited by 19
  30. 2024TQA-Bench: Evaluating LLMs for Multi-Table Question Answeringcited by 17
  31. 2023GFS: Graph-based Feature Synthesis for Prediction over Relational Databasescited by 16
  32. 20244DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on Relational DBscited by 11
  33. 2024The impact of data set similarity and diversity on transfer learning success in time series forecastingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 40.

47 papers.

Sort:

By area:

  1. 2025Relational Transformer: Toward Zero-Shot Foundation Models for Relational Datacited by 39
  2. 2025Relational Graph Transformercited by 34
  3. 2026RelBench v2: A Large-Scale Benchmark and Repository for Relational Datacited by 20
  4. 2026PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Modelscited by 19
  5. 2026KumoRFM-2: Scaling Foundation Models for Relational Learningcited by 19
  6. 2026TabPFN-3: Technical Reportcited by 17
  7. 2026Relational In-Context Learning via Synthetic Pre-training with Structural Priorcited by 14
  8. 2026No Need to Train Your RDB Foundation Modelcited by 10
  9. 2025Position: Foundation Models for Tabular Data within Systemic Contexts Need Groundingcited by 6
  10. 2026RDBLearn: Simple In-Context Prediction Over Relational Databasescited by 5
  11. 2026Towards Anomaly Detection on Relational Datacited by 5
  12. 2025A Pre-training Framework for Relational Data with Information-theoretic Principlescited by 4
35 more
  1. 2026OpenRFM: Dissecting Relational In-Context Learningcited by 4
  2. 2026NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases Trainingcited by 2
  3. 2026Relatron: Automating Relational Machine Learning over Relational Databasescited by 2
  4. 2026Task Scarcity and Label Leakage in Relational Transfer Learningcited by 2
  5. 2026RelAgent: LLM Agents as Data Scientists for Relational Learningcited by 2
  6. 2025Database Views as Explanations for Relational Deep Learningcited by 1
  7. 2025RELATE: A Schema-Agnostic Perceiver Encoder for Multimodal Relational Graphscited by 1
  8. 2026TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusioncited by 1
  9. 2026Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databasescited by 1
  10. 2026RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databasescited by 1
  11. 2026Incorporating Deep Learning Design in Database Queriescited by 1
  12. 2026Statistically Indistinguishable, Operationally Distinct: A Formal Barrier for Tabular Foundation Modelscited by 1
  13. 2026A Fair Benchmarking of Deep Relational Database Learning Modelscited by 1
  14. 2025Struc-EMB: The Potential of Structure-Aware Encoding in Language Embeddingscited by 0
  15. 2026Gaussian Relational Graph Transformercited by 0
  16. 2026Towards Foundation Models for Relational Databases with Language Models and Graph Neural Networkscited by 0
  17. 2026Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learningcited by 0
  18. 2026RelGT-AC: A Relational Graph Transformer for Autocomplete Tasks in Relational Databasescited by 0
  19. 2026Neuro-Relational Programs: Unifying Queries and Neural Computation over Structured Datacited by 0
  20. 2026Relational Structural Causal Modelscited by 0
  21. 2026Universal Encoders for Modular Relational Deep Learningcited by 0
  22. 2026FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Taskscited by 0
  23. 2026InvWeaver: Deductive Feedback for Invariant Synthesis in Interacting-Loop Programscited by 0
  24. 2026PluRel-to-RDB-PFN: Schema-Guided Synthetic Relational Pretrainingcited by 0
  25. 2026Incremental Evaluation and Training in Relational Deep Learningcited by 0
  26. 2026Context Window Failures in Relational Foundation Modelscited by 0
  27. 2026Relational Task Generation Language: A Declarative Specification Framework for Relational Deep Learningcited by 0
  28. 2026Temporal Heterogeneous Graph Pretraining for Relational Deep Learningcited by 0
  29. 2026Support-Set Target Leakage in Relational Foundation Models during In-Context Learning: Impact, Detection, and Mitigationcited by 0
  30. 2026Support-Set Target Leakage in Relational Foundation Models during In-Context Learning: Model Dependence and Evaluation Reliabilitycited by 0
  31. 2026RelICL: Training-free Relational Learning with Tabular Foundation Modelscited by 0
  32. 2026When Does Synthetic Relational Data Teach Models to Use Relations? Tracing Predictive Structure from Pretraining Data to Model Behaviorcited by 0
  33. 2026Relational Learning as World Modelingcited by 0
  34. 2026RT-J: Large-Scale Pretraining of Relational Transformers for Context-Efficient Predictionscited by 0
  35. 2026Revisiting Simple Baselines for Relational Deep Learningcited by 0