Related papers: AnaMeta: A Table Understanding Dataset of Field Me…
Data imputation and data generation have important applications for many domains, like healthcare and finance, where incomplete or missing data can hinder accurate analysis and decision-making. Diffusion models have emerged as powerful…
We introduce Meta-Album, an image classification meta-dataset designed to facilitate few-shot learning, transfer learning, meta-learning, among other tasks. It includes 40 open datasets, each having at least 20 classes with 40 examples per…
Autonomous driving is among the largest domains in which deep learning has been fundamental for progress within the last years. The rise of datasets went hand in hand with this development. All the more striking is the fact that researchers…
Many data we collect today are in tabular form, with rows as records and columns as attributes associated with each record. Understanding the structural relationship in tabular data can greatly facilitate the data science process.…
Tabular data is prevalent across diverse domains in machine learning. With the rapid progress of deep tabular prediction methods, especially pretrained (foundation) models, there is a growing need to evaluate these methods systematically…
As machine learning models are increasingly deployed in high-stakes domains, the need for interpretability has grown to meet strict regulatory and accountability constraints. Despite this interest, systematic evaluations of inherently…
Transformer-based tabular foundation models (TFMs) dominate small to medium tabular predictive benchmark tasks, yet their inference mechanisms remain largely unexplored. We present the first large-scale mechanistic study of layerwise…
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…
Scientists increasingly recognize the importance of providing rich, standards-adherent metadata to describe their experimental results. Despite the availability of sophisticated tools to assist in the process of data annotation,…
We consider the task of meta-analysis in high-dimensional settings in which the data sources are similar but non-identical. To borrow strength across such heterogeneous datasets, we introduce a global parameter that emphasizes…
Tabular data prediction (TDP) is one of the most popular industrial applications, and various methods have been designed to improve the prediction performance. However, existing works mainly focus on feature interactions and ignore sample…
Recent work on database application development platforms has sought to include a declarative formulation of a conceptual data model in the application code, using annotations or attributes. Some recent work has used metadata to include the…
In this paper, we explore the question of whether large language models can support cost-efficient information extraction from tables. We introduce schema-driven information extraction, a new task that transforms tabular data into…
Tabular data are omnipresent in various sectors of industries. Neural networks for tabular data such as TabNet have been proposed to make predictions while leveraging the attention mechanism for interpretability. However, the inferred…
Recent research in tabular data synthesis has focused on single tables, whereas real-world applications often involve complex data with tens or hundreds of interconnected tables. Previous approaches to synthesizing multi-relational…
The importance of databases of reliable and accurate data in chemistry has substantially increased in the past two decades. Their main usage is to parametrize electronic structure theory methods, and to assess their capabilities and…
As one of the most fundamental models, meta learning aims to effectively address few-shot learning challenges. However, it still faces significant issues related to the training data, such as training inefficiencies due to numerous…
Interaction data is widely used in multiple domains such as cognitive science, visualization, human computer interaction, and cybersecurity, among others. Applications range from cognitive analyses over user/behavior modeling, adaptation,…
Most of the previous methods for table recognition rely on training datasets containing many richly annotated table images. Detailed table image annotation, e.g., cell or text bounding box annotation, however, is costly and often…
Over the past few years, table interpretation tasks have made significant progress due to their importance and the introduction of new technologies and benchmarks in the field. This work experiments with a hybrid approach for detecting…