# Domain Constraint Approximation based Semi Supervision

## TL;DR

This paper introduces a fuzzy domain-constraint framework to improve semi-supervised learning by reducing reliance on initial model quality and traditional constraints, demonstrating effectiveness through simulations.

## Contribution

It proposes a novel fuzzy domain-constraint approach that enhances semi-supervised learning without traditional constraint learning requirements.

## Key findings

- Effective in improving semi-supervised learning performance
- Reduces dependency on initial labeled data quality
- Demonstrates superior results in simulations

## Abstract

Deep learning for supervised learning has achieved astonishing performance in various machine learning applications. However, annotated data is expensive and rare. In practice, only a small portion of data samples are annotated. Pseudo-ensembling-based approaches have achieved state-of-the-art results in computer vision related tasks. However, it still relies on the quality of an initial model built by labeled data. Less labeled data may degrade model performance a lot. Domain constraint is another way regularize the posterior but has some limitation. In this paper, we proposed a fuzzy domain-constraint-based framework which loses the requirement of traditional constraint learning and enhances the model quality for semi supervision. Simulations results show the effectiveness of our design.