Related papers: TabSTAR: A Tabular Foundation Model for Tabular Da…

Tabular foundational models are pre-trained models designed for a wide range of tabular data tasks. They have shown strong performance across domains, yet their internal representations and learned concepts remain poorly understood. This…

Representation learning stands as one of the critical machine learning techniques across various domains. Through the acquisition of high-quality features, pre-trained embeddings significantly reduce input space redundancy, benefiting…

Language models (LMs) are increasingly being deployed to perform autonomous data analyses. However, their data awareness -- the ability to recognize, reason over, and appropriately handle data artifacts such as missing values, outliers, and…

Dealing with tabular data is challenging due to partial information, noise, and heterogeneous structure. Existing techniques often struggle to simultaneously address key aspects of tabular data such as textual information, a variable number…

Traditional methods for tabular classification usually rely on supervised learning from scratch, which requires extensive training data to determine model parameters. However, a novel approach called Prior-Data Fitted Networks (TabPFN) has…

The existing literature on deep learning for tabular data proposes a wide range of novel architectures and reports competitive results on various datasets. However, the proposed models are usually not properly compared to each other and…

Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks. In the field of video action recognition, mainstream approaches often introduce additional modules to capture…

Tabular data -- structured, heterogeneous, spreadsheet-style data with rows and columns -- is widely used in practice across many domains. However, while recent foundation models have reduced the need for developing task-specific datasets…

Representation learning is a fundamental aspect of modern artificial intelligence, driving substantial improvements across diverse applications. While selfsupervised contrastive learning has led to significant advancements in fields like…

Tabular representation learning has recently gained a lot of attention. However, existing approaches only learn a representation from a single table, and thus ignore the potential to learn from the full structure of relational databases,…

In engineering design, navigating complex decision-making landscapes demands a thorough exploration of the design, performance, and constraint spaces, often impeded by resource-intensive simulations. Data-driven methods can mitigate this…

Self-supervised representation learning methods have achieved significant success in computer vision and natural language processing, where data samples exhibit explicit spatial or semantic dependencies. However, applying these methods to…

Existing work on tabular representation learning jointly models tables and associated text using self-supervised objective functions derived from pretrained language models such as BERT. While this joint pretraining improves tasks involving…

Graph few-shot learning has garnered significant attention for its ability to rapidly adapt to downstream tasks with limited labeled data, sparking considerable interest among researchers. Recent advancements in graph few-shot learning…

Since a vast number of tables can be easily collected from web pages, spreadsheets, PDFs, and various other document types, a flurry of table pre-training frameworks have been proposed following the success of text and images, and they have…

Tabular Foundation Models (TFMs) have recently shown strong in-context learning capabilities on structured data, achieving zero-shot performance comparable to traditional machine learning methods. We find that zero-shot TFMs already achieve…

Tabular data prediction has been employed in medical applications such as patient health risk prediction. However, existing methods usually revolve around the algorithm design while overlooking the significance of data engineering. Medical…

Accurate prediction of mechanical properties of steel during hot rolling processes, such as Thin Slab Direct Rolling (TSDR), remains challenging due to complex interactions among chemical compositions, processing parameters, and resultant…

Tabular in-context learning (ICL) has recently achieved state-of-the-art (SOTA) performance on several tabular prediction tasks. Previously restricted to classification problems on small tables, recent advances such as TabPFN and TabICL…

Generative modeling for tabular data has recently gained significant attention in the Deep Learning domain. Its objective is to estimate the underlying distribution of the data. However, estimating the underlying distribution of tabular…