Related papers: TransTab: Learning Transferable Tabular Transforme…

Tabular foundation models such as TabPFN have revolutionized predictive machine learning for tabular data. At the same time, the driving factors of this revolution are hard to understand. Existing open-source tabular foundation models are…

Table structure recognition (TSR) holds widespread practical importance by parsing tabular images into structured representations, yet encounters significant challenges when processing complex layouts involving merged or empty cells.…

Machine learning (ML) accelerates the exploration of material properties and their links to the structure of the underlying molecules. In previous work [J. Shi, M. J. Quevillon, P. H. A. Valen\c{c}a, and J. K. Whitmer, \textit{ACS Appl.…

Machine learning for tabular data remains constrained by poor schema generalization, a challenge rooted in the lack of semantic understanding of structured variables. This challenge is particularly acute in domains like clinical medicine,…

We introduce AutoGluon-Tabular, an open-source AutoML framework that requires only a single line of Python to train highly accurate machine learning models on an unprocessed tabular dataset such as a CSV file. Unlike existing AutoML…

Data preparation, also called data wrangling, is considered one of the most expensive and time-consuming steps when performing analytics or building machine learning models. Preparing data typically involves collecting and merging data from…

The objective of this work is to improve the accuracy of building demand forecasting. This is a more challenging task than grid level forecasting. For the said purpose, we develop a new technique called recurrent transform learning (RTL).…

Deep learning methods have advanced quickly in brain imaging analysis over the past few years, but they are usually restricted by the limited labeled data. Pre-trained model on unlabeled data has presented promising improvement in feature…

For tabular datasets, the change in the relationship between the label and covariates ($Y|X$-shifts) is common due to missing variables (a.k.a. confounders). Since it is impossible to generalize to a completely new and unknown domain, we…

Deep learning fostered a leap ahead in automated skin lesion analysis in the last two years. Those models are expensive to train and difficult to parameterize. Objective: We investigate methodological issues for designing and evaluating…

Transfer learning (TL), the next frontier in machine learning (ML), has gained much popularity in recent years, due to the various challenges faced in ML, like the requirement of vast amounts of training data, expensive and time-consuming…

Transformer-based models have shown promising performance on tabular data compared to their classical counterparts such as neural networks and Gradient Boosted Decision Trees (GBDTs) in scenarios with limited training data. They utilize…

Pre-training has shown success in different areas of machine learning, such as Computer Vision, Natural Language Processing (NLP), and medical imaging. However, it has not been fully explored for clinical data analysis. An immense amount of…

Tabular foundation models, such as TabPFNv2 and TabICL, have recently dethroned gradient-boosted trees at the top of predictive benchmarks, demonstrating the value of in-context learning for tabular data. We introduce TabICLv2, a new…

Tabular data underpins decisions across science, industry, and public services. Despite rapid progress, advances in deep learning have not fully carried over to the tabular domain, where gradient-boosted decision trees (GBDTs) remain a…

Many statistical learning models hold an assumption that the training data and the future unlabeled data are drawn from the same distribution. However, this assumption is difficult to fulfill in real-world scenarios and creates barriers in…

Tabular data remain a dominant form of real-world information but pose persistent challenges for deep learning due to heterogeneous feature types, lack of natural structure, and limited label-preserving augmentations. As a result, ensemble…

Diffusion models have been the predominant generative model for tabular data generation. However, they face the conundrum of modeling under a separate versus a unified data representation. The former encounters the challenge of jointly…

Tables are pervasive in diverse documents, making table recognition (TR) a fundamental task in document analysis. Existing modular TR pipelines separately model table structure and content, leading to suboptimal integration and complex…

Accurate forecasting of recovery rates (RR) is central to credit risk management and regulatory capital determination. In many loan portfolios, however, RR modeling is constrained by data scarcity arising from infrequent default events.…