mlsanityData to 14 Oct 2026

Tabular Incremental Inference

arXiv 2601.15751 ↗First posted 22 Jan 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Tabular data is a fundamental form of data structure. The evolution of table analysis tools reflects humanity's continuous progress in data acquisition, management, and processing. The dynamic changes in table columns arise from technological advancements, changing needs, data integration, etc. However, the standard process of training AI models on tables with fixed columns and then performing inference is not suitable for handling dynamically changed tables. Therefore, new methods are needed for efficiently handling such tables in an unsupervised manner. In this paper, we introduce a new task, Tabular Incremental Inference (TabII), which aims to enable trained models to incorporate new columns during the inference stage, enhancing the practicality of AI models in scenarios where tables are dynamically changed. Furthermore, we demonstrate that this new task can be framed as an optimization problem based on the information bottleneck theory, which emphasizes that the key to an ideal tabular incremental inference approach lies in minimizing mutual information between tabular data and representation while maximizing between representation and task labels. Under this guidance, we design a TabII method with Large Language Model placeholders and Pretrained TabAdapter to provide external knowledge and Incremental Sample Condensation blocks to condense the task-relevant information given by incremental column attributes. Experimental results across eight public datasets show that TabII effectively utilizes incremental attributes, achieving state-of-the-art performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 44 references that are in the map. First posted on arXiv 22 Jan 2026.

Builds on

22 of 44 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  7. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  8. 2015Deep Learning and the Information Bottleneck Principlecited by 802
  9. 2021Revisiting Deep Learning Models for Tabular Datacited by 740
  10. 2019TabNet: Attentive Interpretable Tabular Learningcited by 648
  11. 2021Tabular Data: Deep Learning is Not All You Needcited by 535
  12. 2017Opening the Black Box of Deep Neural Networks via Informationcited by 503
10 more
  1. 2021SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Trainingcited by 319
  2. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 159
  3. 2021SCARF: Self-Supervised Contrastive Learning using Random Feature Corruptioncited by 156
  4. 2022LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Taskscited by 148
  5. 2022TransTab: Learning Transferable Tabular Transformers Across Tablescited by 132
  6. 2021SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learningcited by 104
  7. 2023How Does Information Bottleneck Help Deep Learning?cited by 93
  8. 2024Making Pre-trained Language Models Great on Tabular Predictioncited by 57
  9. 2023STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tablescited by 49
  10. 2023MediTab: Scaling Medical Tabular Data Predictors via Data Consolidation, Enrichment, and Refinementcited by 24

Built on by

Not cited yet.