Enhancing Classification with Semi-Supervised Deep Learning Using Distance-Based Sample Weights

TL;DR

This paper introduces a semi-supervised deep learning framework that uses distance-based sample weights to improve classification accuracy and robustness, especially in noisy or imbalanced datasets, by prioritizing informative samples.

Contribution

It proposes a novel distance-based weighting mechanism integrated with semi-supervised learning to enhance model performance and generalization in challenging data scenarios.

Findings

Significant improvements in accuracy, precision, and recall on twelve benchmark datasets.

Outperforms existing semi-supervised methods across multiple metrics.

Effective in noisy and imbalanced data conditions.

Abstract

Recent advancements in semi-supervised deep learning have introduced effective strategies for leveraging both labeled and unlabeled data to improve classification performance. This work proposes a semi-supervised framework that utilizes a distance-based weighting mechanism to prioritize critical training samples based on their proximity to test data. By focusing on the most informative examples, the method enhances model generalization and robustness, particularly in challenging scenarios with noisy or imbalanced datasets. Building on techniques such as uncertainty consistency and graph-based representations, the approach addresses key challenges of limited labeled data while maintaining scalability. Experiments on twelve benchmark datasets demonstrate significant improvements across key metrics, including accuracy, precision, and recall, consistently outperforming existing methods. This framework provides a robust and practical solution for semi-supervised learning, with potential applications in domains such as healthcare and security where data limitations pose significant challenges.