Semi-supervised learning (SSL) aims to improve performance by exploiting unlabeled data
when labels are scarce. Conventional SSL studies typically assume close environments …

For classification and regression on tabular data, the dominance of gradient-boosted
decision trees (GBDTs) has recently been challenged by often much slower deep learning …

Data missingness is a practical challenge of sustained interest to the scientific community. In
this paper, we present Shades-of-Null, an evaluation suite for responsible missing value …

This paper presents a novel approach to optimizing semantic joinability in heterogeneous
data, leveraging embedding techniques and deep learning in the context of big data …

Accurate forecasting of PV power generation is crucial for energy providers to effectively
participate in day-ahead (D-1) and two-day-ahead (D-2) markets, including FCR-D, day …

The widespread enthusiasm for deep learning has recently expanded into the domain of
tabular data. Recognizing that the advancement in deep tabular methods is often inspired by …