mlsanityData to 14 Oct 2026

TabGNN: Multiplex Graph Neural Network for Tabular Data Prediction

arXiv 2108.09127 ↗First posted 20 Aug 2021cs.LGcited by 26

Not on the map. Why?

Abstract (arXiv)

Tabular data prediction (TDP) is one of the most popular industrial applications, and various methods have been designed to improve the prediction performance. However, existing works mainly focus on feature interactions and ignore sample relations, e.g., users with the same education level might have a similar ability to repay the debt. In this work, by explicitly and systematically modeling sample relations, we propose a novel framework TabGNN based on recently popular graph neural networks (GNN). Specifically, we firstly construct a multiplex graph to model the multifaceted sample relations, and then design a multiplex graph neural network to learn enhanced representation for each sample. To integrate TabGNN with the tabular solution in our company, we concatenate the learned embeddings and the original ones, which are then fed to prediction models inside the solution. Experiments on eleven TDP datasets from various domains, including classification and regression ones, show that TabGNN can consistently improve the performance compared to the tabular solution AutoFE in 4Paradigm.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Builds on 18 of its 36 references that are in the map. First posted on arXiv 20 Aug 2021.

Builds on

18 of 36 references.

References · 18

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
  7. 2016Wide & Deep Learning for Recommender Systemscited by 747
  8. 2017DeepFM: A Factorization-Machine based Neural Network for CTR Predictioncited by 676
  9. 2017Deep Interest Network for Click-Through Rate Predictioncited by 544
  10. 2019Behavior Sequence Transformer for E-commerce Recommendation in Alibabacited by 130
  11. 2019Representation Learning for Attributed Multiplex Heterogeneous Networkcited by 91
  12. 2020AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Predictioncited by 52
6 more
  1. 2020Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structurescited by 45
  2. 2018Product-based Neural Networks for User Response Prediction over Multi-field Categorical Datacited by 44
  3. 2019AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applicationscited by 40
  4. 2020Abstract Diagrammatic Reasoning with Multiplex Graph Networkscited by 37
  5. 2018Multi-dimensional Graph Convolutional Networkscited by 15
  6. 2020MTBRN: Multiplex Target-Behavior Relation Enhanced Network for Click-Through Rate Predictioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 6; 2024: 7; 2025: 8; 2026: 2.

26 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  2. 2022TransTab: Learning Transferable Tabular Transformers Across Tablescited by 132
  3. 2025Griffin: Towards a Graph-Centric Relational Database Foundation Modelcited by 47
  4. 2024SwitchTab: Switched Autoencoders Are Effective Tabular Learnerscited by 38
  5. 2025Representation Learning for Tabular Data: A Comprehensive Surveycited by 36
  6. 2022Hopular: Modern Hopfield Networks for Tabular Datacited by 18
  7. 2024A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Datacited by 15
  8. 2026Relational In-Context Learning via Synthetic Pre-training with Structural Priorcited by 14
  9. 2024Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directionscited by 13
  10. 2023Graph Neural Network contextual embedding for Deep Learning on Tabular Datacited by 8
  11. 2025AutoG: Towards automatic graph construction from tabular datacited by 7
  12. 2022Learning Enhanced Representations for Tabular Data via Neighborhood Propagationcited by 6
14 more
  1. 2023MuG: A Multimodal Classification Benchmark on Game Data with Tabular, Textual, and Visual Fieldscited by 6
  2. 2025From Features to Structure: Task-Aware Graph Construction for Relational and Tabular Learning with GNNscited by 6
  3. 2023Interpretable Graph Neural Networks for Tabular Datacited by 5
  4. 2023TabGSL: Graph Structure Learning for Tabular Data Predictioncited by 3
  5. 2024Novel Representation Learning Technique using Graphs for Performance Analyticscited by 2
  6. 2025TabGLM: Tabular Graph Language Model for Learning Transferable Representations Through Multi-Modal Consistency Minimizationcited by 2
  7. 2023Between-Sample Relationship in Learning Tabular Data Using Graph and Attention Networkscited by 1
  8. 2023AdaMedGraph: Adaboosting Graph Neural Networks for Personalized Medicinecited by 1
  9. 2024Interpretable Graph Neural Networks for Heterogeneous Tabular Datacited by 1
  10. 2024Geodesic Flow Kernels for Semi-Supervised Learning on Mixed-Variable Tabular Datasetcited by 1
  11. 2025IVGAE: Handling Incomplete Heterogeneous Data with a Variational Graph Autoencodercited by 1
  12. 2025Can Graphs Improve Tabular Foundation Models?cited by 0
  13. 2025A Roadmap for Applying Graph Neural Networks to Numerical Data: Insights from Cementitious Materialscited by 0
  14. 2026TAROT: Task-Adaptive Refinement of LLM-prior Graphs for Few-shot Tabular Learningcited by 0