Comparison of Reconstruction-Based and Permutation-Based SSL Methods on Tabular 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: How do reconstruction-based and permutation-based SSL methods compare in terms of model convergence speed and final representation quality (measured by downstream task accuracy) on standardized tabular benchmarks such as those in the RBT framework?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.2/10.