Tabular Representation Learning

Overview

Tabular representation learning studies how to encode rows, columns, and whole tables so models can use mixed numerical and categorical data, missing values, and schema structure. Common approaches include feature-aware transformers, masked or contrastive self-supervised learning, autoencoders, and embeddings that combine table structure with language-model or graph representations. These embeddings support tasks such as classification, retrieval, clustering, anomaly detection, synthetic data generation, and transfer across datasets or schemas. Results remain sensitive to the task and dataset: no single encoder consistently leads, and when pretraining helps over training from scratch or tree-based models is still uncertain.

Latest papers

CardsList

59 papers7 papers in the last four weeks, down 30% on the four weeks before. 0.1% of all new papers.

  1. LightTAR: Light and Fast Target-Aware Representations for Multimodal Tabular Learning

    Nov 12, 2026Eilam Shapira, Alan Arazi, Shoham Grunblat +1Tabular Representation LearningDimensionality Reduction

  2. Beyond Row-Level Prediction: Evaluating and Learning Composition for Reusable Table Representations

    Nov 10, 2026Ali Younes, Saeed Ghoorchian, Maximilian Schambach +2Tabular Representation LearningCompositional Representation Learning

  3. TabAbax: A Tabular Foundation Model Technical Report

    Oct 31, 2026Zhixiong Cheng, Xiaoyun Gao, Shiyuan Han +2Tabular Foundation ModelsTabular ICL

  4. ElTab: Elastically Looped Tabular Transformers

    Oct 30, 2026Mieszko Komisarczyk, Saurabh Mathur, Maurice Kraus +2Efficient Transformer InferenceTabular Prediction

  5. Fed-IGTD: A federated learning-based framework for tabular-to-image encoding

    Oct 28, 2026David Chushig-Muzo, Eva Milara, Francisco J. Lara Abelenda +2Federated LearningDifferentially Private Federated Learning

  6. HypTI: Hyperbolic Geometry-Aware Multimodal Feature Fusion Framework for Dementia Detection Based on Tabular-Image Data

    Oct 20, 2026Jianfei Xu, Huizhi Liang, Judith Harrison +3Multimodal FusionMultimodal Classification

  7. CARTA: Self-Supervised Reusable Transaction Embeddings via Heterogeneous Tokenization and Cross-Attention

    Oct 17, 2026Shreyas K. Chandrahas, Jose Munoz, Satish Babu BellapuRepresentation LearningTabular Representation Learning

  8. When Does Depth Help? Understanding Layerwise Inference in Tabular Foundation Models

    Oct 14, 2026Wenwen Gong, Haotian Gu, Zhen Yang +6Tabular Foundation ModelsTransformer Inference

  9. MERIT: Multimodal Evidence Reasoning over Image Tables

    Oct 13, 2026Haoyang Jiang, Zhuotong Fan, Mingyang Yi +3Table QAAutomated Fact-Checking

  10. TILE: Bridging LLMs and Table Foundation Models for Tabular Learning with Strings

    Oct 12, 2026Félix Lefebvre, David Holzmüller, Gioia Blayer +3Tabular MLTabular Representation Learning

  11. EchoTab: Learning Measurement-Grounded Representations for Echocardiographic Diagnosis through Tabular Reconstruction

    Oct 9, 2026Michelle Espranita Liman, Ioana Ionac, Alexander Müller +3Medical Image Representation LearningRepresentation Learning

  12. Thinking in Depth: Retrospective Inference for Tabular Foundation Models

    Oct 7, 2026Hao-Run Cai, Si-Yang Liu, Zi-Jian Cheng +8Tabular Foundation ModelsTabular ICL

  13. Adapting prior-data fitted networks for tabular anomaly detection

    Oct 5, 2026Maximilian Bershtman, Niv CohenTabular Anomaly DetectionUnsupervised Anomaly Detection

  14. SwitchPFN: Shared Switching Dynamics for Frozen In-Context Time Series Classification

    Sep 24, 2026Zhenyi Zhu, Jacqueline Pang, Peilin Shen +7Tabular Foundation ModelsTime Series Classification

  15. Discovery-Driven Integration of Disjoint Tables via Text

    Sep 22, 2026Md Ataur Rahman, Dimitris Sacharidis, Oscar Romero +1Cross-Modal RetrievalTabular Representation Learning

  16. InRTL: Effective Intra-Inter Interaction Learning for Relational Tables

    Sep 11, 2026Weichen Li, Ken Zhong, Zheng Wang +2Tabular Representation LearningRelational Deep Learning

  17. H2Table: Hierarchical Hypergraph-Enhanced Large Language Models for Complex Table Reasoning

    Sep 1, 2026Jia Ling, Yangfan Wang, Chen Tang +4Table QAHierarchical Representation Learning

  18. VG-TIE: An interpretable tabular-to-image encoding method based on visibility graphs

    Aug 29, 2026David Chushig-Muzo, Luis M. López-Ramos, Ángeles Rodríguez de Cara +3Tabular Representation Learning

  19. TabuLM: Morphology-Aware Tabular Pre-training for Low-Resource Languages

    Aug 27, 2026Ireddi Rakshitha, Devavarapu Yashwanth, Ntakirutimana PierreLanguage Model PretrainingLanguage Modeling

  20. Discovering Relationships in Data Lakes Using Large Language Models: An Industrial Case

    Aug 27, 2026Ahlame Diouan, Eric Ferey, Sabine Loudcher +1Schema LinkingTabular Representation Learning

  21. When Does Self-Supervised Pretraining Help Tabular Models? A Study of Label Scarcity and Missing Data

    Aug 25, 2026Sahand MazroueiSelf-Supervised Pre-TrainingTabular ML

  22. Conditional-Independence-Regularized Distributional Autoencoders for Mixed-Type Data

    Aug 20, 2026Siyuan Tang, Gongjun Xu, Ji ZhuAutoencodersConditional Distribution Estimation

  23. TabNSM: Neural Sparse Mixer for Tabular Regression

    Aug 18, 2026Ali Eslamian, Qiang ChengTabular RegressionTabular Representation Learning

  24. RecipeNet: A Hierarchical Transformer for Recipe Data

    Aug 14, 2026Pin-Yen Huang, Sachin Chhabra, Prasanth Sai Gouripeddi +2Representation LearningHierarchical Representation Learning

  25. Unlocking the Power of Medical Tabular Data via Semantic-Aware Multimodal Pre-training

    Aug 11, 2026Yingsheng Liu, Haiming Li, Jingmin Zhu +6Cross-Modal Representation LearningMultimodal Pretraining

  26. Self-Supervised Representations for Binary Program Clustering: From Empirical Study to Retrieval-Augmented Learning

    Aug 3, 2026Martin Mocko, Daniela ChudáRepresentation LearningSelf-Supervised Learning

  27. Human Preference aligned Tabular Similarity

    Jul 27, 2026Frederik Hoppe, Astrid Franz, Marianne Michaelis +2Human Preference EvaluationTabular Representation Learning

  28. TEmBed-T: A Multi-Dimensional Benchmark for Table-Level Embeddings

    Jul 27, 2026Ayeen Poostforoushan, Liane Vogel, Carsten BinnigTabular Representation LearningInformation Retrieval