paper-with-me

Papers

Tabular Incremental Inference

2026-01-22 · Xinda Chen, Zhen Xing, Hanyu Zhang, Weimin Tan, Bo Yan 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.

📄 PDF Abstract BibTeX arXiv:2601.15751

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

No Imputation of Missing Values In Tabular Data Classification Using Incremental Learning

2025-04-20 · Manar D. Samad, Kazi Fuad B. Akhter, Shourav B. Rabbani, Ibna Kowsar

Tabular data sets with varying missing values are prepared for machine learning using an arbitrary imputation strategy. Synthetic values generated by imputation models often concern data stakeholders about computational …

ImputationIncremental LearningMissing Values

Overcoming Catastrophic Forgetting in Tabular Data Classification: A Pseudorehearsal-based approach

2024-07-12 · Pablo García-Santaclara, Bruno Fernández-Castro, Rebeca P. Díaz-Redondo

Continual learning (CL) poses the important challenge of adapting to evolving data distributions without forgetting previously acquired knowledge while consolidating new knowledge. In this paper, we introduce a new metho…

Continual LearningLifelong learning

Incremental Transformer Neural Processes

2026-02-21 · Philip Mortimer, Cristiana Diaconu, Tommy Rochussen, Bruno Mlodozeniec 외 arxiv

Neural Processes (NPs), and specifically Transformer Neural Processes (TNPs), have demonstrated remarkable performance across tasks ranging from spatiotemporal forecasting to tabular data modelling. However, many of thes…

SPRINT: Semi-supervised Prototypical Representation for Few-Shot Class-Incremental Tabular Learning

2026-03-04 · Umid Suleymanov, Murat Kantarcioglu, Kevin S Chan, Michael De Lucia 외 arxiv

Real-world systems must continuously adapt to novel concepts from limited data without forgetting previously acquired knowledge. While Few-Shot Class-Incremental Learning (FSCIL) is established in computer vision, its ap…

Few-Shot Class-Incremental Learning

TabMixer: advancing tabular data analysis with an enhanced MLP-mixer approach

2025-02-21 · Pattern Analysis and Applications 2025 2 · Ali Eslamian, Qiang Cheng

Tabular data, prevalent in relational databases and spreadsheets, is fundamental across fields like healthcare, engineering, and finance. Despite significant advances in tabular data learning, critical challenges remain:…

Computational EfficiencyDeep LearningIncremental LearningMissing Values+2