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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Abedinia, Aydin, Tabakhi, Shima, Seydi, Vahid
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916746259070976
author Abedinia, Aydin
Tabakhi, Shima
Seydi, Vahid
author_facet Abedinia, Aydin
Tabakhi, Shima
Seydi, Vahid
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_14345
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Classification with Semi-Supervised Deep Learning Using Distance-Based Sample Weights
Abedinia, Aydin
Tabakhi, Shima
Seydi, Vahid
Machine Learning
Artificial Intelligence
68T05, 62H30
I.2.6; I.5.1; I.5.4
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.
title Enhancing Classification with Semi-Supervised Deep Learning Using Distance-Based Sample Weights
topic Machine Learning
Artificial Intelligence
68T05, 62H30
I.2.6; I.5.1; I.5.4
url https://arxiv.org/abs/2505.14345