Comparative Analysis of Reconstruction and Permutation Pretext Tasks for Cross-Domain Transfer on TabNet Benchmarks

Abstract Semi-supervised learning is the branch of machine learning concerned with using labelled as well as unlabelled data to perform certain learning tasks. Conceptually situated between supervised and unsupervised learning, it permits harnessing the large amounts of unlabelled data available in many use cases in combination with typically smaller sets of labelled data. In recent years, research in this area has followed the general trends observed in machine learning, with much attention directed at neural network-based models and generative learning. The literature on the topic has also e

Research goal: Which self-supervised pretext tasks (reconstruction vs. permutation) yield better performance in cross-domain transfer scenarios, as evaluated by accuracy metrics on tabular datasets from the TabNet benchmark suite?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 7.9/10.