mlsanityData to 14 Oct 2026

REDELEX: A Framework for Relational Deep Learning Exploration

arXiv 2506.22199 ↗First posted 27 Jun 2025cs.LG cs.DBcited by 8

Not on the map. Why?

Abstract (arXiv)

Relational databases (RDBs) are widely regarded as the gold standard for storing structured information. Consequently, predictive tasks leveraging this data format hold significant application promise. Recently, Relational Deep Learning (RDL) has emerged as a novel paradigm wherein RDBs are conceptualized as graph structures, enabling the application of various graph neural architectures to effectively address these tasks. However, given its novelty, there is a lack of analysis into the relationships between the performance of various RDL models and the characteristics of the underlying RDBs. In this study, we present REDELEX-a comprehensive exploration framework for evaluating RDL models of varying complexity on the most diverse collection of over 70 RDBs, which we make available to the community. Benchmarked alongside key representatives of classic methods, we confirm the generally superior performance of RDL while providing insights into the main factors shaping performance, including model complexity, database sizes and their structural properties.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 21 of its 45 references that are in the map. First posted on arXiv 27 Jun 2025.

Builds on

21 of 45 references.

References · 21

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  7. 2021How Attentive are Graph Attention Networks?cited by 835
  8. 2021Revisiting Deep Learning Models for Tabular Datacited by 740
  9. 2019TabNet: Attentive Interpretable Tabular Learningcited by 648
  10. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 530
  11. 2021Deep Neural Networks and Tabular Data: A Surveycited by 491
  12. 2020TabTransformer: Tabular Data Modeling Using Contextual Embeddingscited by 409
9 more
  1. 2021SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Trainingcited by 319
  2. 2021UniT: Multimodal Multitask Learning with a Unified Transformercited by 195
  3. 2022Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questionscited by 116
  4. 2024RelBench: A Benchmark for Deep Learning on Relational Databasescited by 96
  5. 2020Supervised Learning on Relational Databases with Graph Neural Networkscited by 48
  6. 2025RelGNN: Composite Message Passing for Relational Deep Learningcited by 48
  7. 2020Turning 30: New Ideas in Inductive Logic Programmingcited by 42
  8. 2023Trompt: Towards a Better Deep Neural Network for Tabular Datacited by 36
  9. 2023GFS: Graph-based Feature Synthesis for Prediction over Relational Databasescited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 7.

8 papers.

  1. 2026RelBench v2: A Large-Scale Benchmark and Repository for Relational Datacited by 20
  2. 2025Integrating Temporal and Structural Context in Graph Transformers for Relational Deep Learningcited by 4
  3. 2026Advancing Open and Reproducible Relational Learning: RelArena-α, TabPFN-Rel and RPIcited by 3
  4. 2026Declarative by Design, Assistable Only by Convention: Benchmarking Multi-Agent Frameworks for AI-Assistabilitycited by 0
  5. 2026Universal Encoders for Modular Relational Deep Learningcited by 0
  6. 2026Incremental Evaluation and Training in Relational Deep Learningcited by 0
  7. 2026Relational Task Generation Language: A Declarative Specification Framework for Relational Deep Learningcited by 0
  8. 2026RelICL: Training-free Relational Learning with Tabular Foundation Modelscited by 0