mlsanityData to 14 Oct 2026

T2G-Former: Organizing Tabular Features into Relation Graphs Promotes Heterogeneous Feature Interaction

arXiv 2211.16887 ↗First posted 30 Nov 2022cs.LGcited by 41

Not on the map. Why?

Abstract (arXiv)

Recent development of deep neural networks (DNNs) for tabular learning has largely benefited from the capability of DNNs for automatic feature interaction. However, the heterogeneity nature of tabular features makes such features relatively independent, and developing effective methods to promote tabular feature interaction still remains an open problem. In this paper, we propose a novel Graph Estimator, which automatically estimates the relations among tabular features and builds graphs by assigning edges between related features. Such relation graphs organize independent tabular features into a kind of graph data such that interaction of nodes (tabular features) can be conducted in an orderly fashion. Based on our proposed Graph Estimator, we present a bespoke Transformer network tailored for tabular learning, called T2G-Former, which processes tabular data by performing tabular feature interaction guided by the relation graphs. A specific Cross-level Readout collects salient features predicted by the layers in T2G-Former across different levels, and attains global semantics for final prediction. Comprehensive experiments show that our T2G-Former achieves superior performance among DNNs and is competitive with non-deep Gradient Boosted Decision Tree models.

Key facts. Cited by 41 papers in the map (data through 14 Oct 2026). Builds on 31 of its 56 references that are in the map. First posted on arXiv 30 Nov 2022.

Builds on

31 of 56 references.

References · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  5. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  6. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  7. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  8. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 932
  9. 2016Complex Embeddings for Simple Link Predictioncited by 902
  10. 2021Revisiting Deep Learning Models for Tabular Datacited by 740
  11. 2017DeepFM: A Factorization-Machine based Neural Network for CTR Predictioncited by 676
  12. 2019TabNet: Attentive Interpretable Tabular Learningcited by 648
19 more
  1. 2017Self-Normalizing Neural Networkscited by 598
  2. 2021Deep Neural Networks and Tabular Data: A Surveycited by 491
  3. 2020TabTransformer: Tabular Data Modeling Using Contextual Embeddingscited by 409
  4. 2017Deep & Cross Network for Ad Click Predictionscited by 393
  5. 2016From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classificationcited by 341
  6. 2020DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systemscited by 327
  7. 2018AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networkscited by 320
  8. 2019Neural Oblivious Decision Ensembles for Deep Learning on Tabular Datacited by 203
  9. 2022On Embeddings for Numerical Features in Tabular Deep Learningcited by 186
  10. 2015Holographic Embeddings of Knowledge Graphscited by 181
  11. 2021Representing Numbers in NLP: a Survey and a Visioncited by 83
  12. 2018Deep Neural Decision Treescited by 72
  13. 2017Open-World Knowledge Graph Completioncited by 64
  14. 2020The Tree Ensemble Layer: Differentiability meets Conditional Computationcited by 57
  15. 2021DANets: Deep Abstract Networks for Tabular Data Classification and Regressioncited by 50
  16. 2018Quasi-hyperbolic momentum and Adam for deep learningcited by 48
  17. 2022Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Taskscited by 42
  18. 2018Multi-Layered Gradient Boosting Decision Treescited by 16
  19. 2018Benchmarking and Optimization of Gradient Boosting Decision Tree Algorithmscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 18; 2025: 10; 2026: 8.

41 papers.

Sort:

By area:

  1. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 159
  2. 2024TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensemblingcited by 113
  3. 2024Making Pre-trained Language Models Great on Tabular Predictioncited by 57
  4. 2024TALENT: A Tabular Analytics and Learning Toolboxcited by 52
  5. 2023ExcelFormer: A neural network surpassing GBDTs on tabular datacited by 34
  6. 2024HyperFast: Instant Classification for Tabular Datacited by 22
  7. 2023Towards Cross-Table Masked Pretraining for Web Data Miningcited by 21
  8. 2024BiSHop: Bi-Directional Cellular Learning for Tabular Data with Generalized Sparse Modern Hopfield Modelcited by 21
  9. 2024A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Datacited by 15
  10. 2024Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directionscited by 13
  11. 2024Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular Domainscited by 12
  12. 2024Attention versus Contrastive Learning of Tabular Data -- A Data-centric Benchmarkingcited by 9
29 more
  1. 2024Arithmetic Feature Interaction Is Necessary for Deep Tabular Learningcited by 8
  2. 2024Causality for Tabular Data Synthesis: A High-Order Structure Causal Benchmark Frameworkcited by 8
  3. 2023NCART: Neural Classification and Regression Tree for Tabular Datacited by 7
  4. 2024TabSeq: A Framework for Deep Learning on Tabular Data via Sequential Orderingcited by 5
  5. 2024Small Models are LLM Knowledge Triggers on Medical Tabular Predictioncited by 4
  6. 2025Transfer Learning of Tabular Data by Finetuning Large Language Modelscited by 4
  7. 2025Modern Neural Networks for Small Tabular Datasets: The New Default for Field-Scale Digital Soil Mapping?cited by 4
  8. 2023TabGSL: Graph Structure Learning for Tabular Data Predictioncited by 3
  9. 2024Cross-Table Pretraining towards a Universal Function Space for Heterogeneous Tabular Datacited by 2
  10. 2025MultiTab: A Comprehensive Benchmark Suite for Multi-Dimensional Evaluation in Tabular Domainscited by 2
  11. 2023Text2Tree: Aligning Text Representation to the Label Tree Hierarchy for Imbalanced Medical Classificationcited by 1
  12. 2025Cross-Modality Masked Learning for Survival Prediction in ICI Treated NSCLC Patientscited by 1
  13. 2025Towards Interpretable Deep Neural Networks for Tabular Datacited by 1
  14. 2025Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learningcited by 1
  15. 2026DynaTab: Dynamic Feature Ordering as Neural Rewiring for High-Dimensional Tabular Datacited by 1
  16. 2024Challenging Gradient Boosted Decision Trees with Tabular Transformers for Fraud Detection at Booking.comcited by 0
  17. 2024Tokenize features, enhancing tables: the FT-TABPFN model for tabular classificationcited by 0
  18. 2024APAR: Modeling Irregular Target Functions in Tabular Regression via Arithmetic-Aware Pre-Training and Adaptive-Regularized Fine-Tuningcited by 0
  19. 2025The Role of Feature Interactions in Graph-based Tabular Deep Learningcited by 0
  20. 2025Interpretable Graph-Language Modeling for Detecting Youth Illicit Drug Usecited by 0
  21. 2025Uncertainty-Aware Multimodal Fusion for Oral Lesion Classificationcited by 0
  22. 2025XNNTab -- Interpretable Neural Networks for Tabular Data using Sparse Autoencoderscited by 0
  23. 2026Response-Aware Multimodal Learning for Post-Treatment Visual Acuity Forecastingcited by 0
  24. 2026TAROT: Task-Adaptive Refinement of LLM-prior Graphs for Few-shot Tabular Learningcited by 0
  25. 2026When, Where, and How: Adaptive Binning for Tabular Self-Supervised Learningcited by 0
  26. 2026TabLoRA: Parameter-Efficient Low-Rank Ensemble Learning for Large-Scale Tabular Datacited by 0
  27. 2026TabNSM: Neural Sparse Mixer for Tabular Regressioncited by 0
  28. 2026Xiaomi-TabLDM: A Tabular Foundation Model Technical Reportcited by 0
  29. 2026Explainable Neuro-Fuzzy Prediction for Trustworthy Decision-Making in Maritimecited by 0