Salvato in:
Dettagli Bibliografici
Autori principali: Yousefimehr, Behnam, Ghatee, Mehdi, Fazli, Javad, Ghaffari, Shervin, Rafei, Zahra, Seifi, Mohammad Amin, Tavakoli, Sajed, Nikahd, Abolfazl, Gandomani, Mahdi Razi, Orouji, Alireza, Kashani, Ramtin Mahmoudi, Heshmati, Sarina, Mousavi, Negin Sadat
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2505.13518
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908999180353536
author Yousefimehr, Behnam
Ghatee, Mehdi
Fazli, Javad
Ghaffari, Shervin
Rafei, Zahra
Seifi, Mohammad Amin
Tavakoli, Sajed
Nikahd, Abolfazl
Gandomani, Mahdi Razi
Orouji, Alireza
Kashani, Ramtin Mahmoudi
Heshmati, Sarina
Mousavi, Negin Sadat
author_facet Yousefimehr, Behnam
Ghatee, Mehdi
Fazli, Javad
Ghaffari, Shervin
Rafei, Zahra
Seifi, Mohammad Amin
Tavakoli, Sajed
Nikahd, Abolfazl
Gandomani, Mahdi Razi
Orouji, Alireza
Kashani, Ramtin Mahmoudi
Heshmati, Sarina
Mousavi, Negin Sadat
contents Imbalanced datasets, where one class significantly outnumbers others, remain a persistent challenge in machine learning, often biasing predictions toward the majority class and degrading classifier performance. This paper provides a comprehensive, systematic review of data balancing methods, extending beyond foundational oversampling techniques such as the Synthetic Minority Oversampling Technique (SMOTE) and its variants (e.g., Borderline SMOTE, K-Means SMOTE, and Safe-Level SMOTE) to encompass advanced adaptive methods (MWMOTE, AMDO), deep generative models (generative adversarial networks, variational autoencoders, and diffusion models), undersampling techniques (NearMiss, Tomek Links), combination/hybrid methods (SMOTE-ENN, SMOTE-Tomek, and SMOTE+OCSVM), ensemble strategies (SMOTEBoost, RUSBoost, Balanced Random Forest, and One-Sided Selection), and specialized approaches for multi-label and clustered data. Beyond descriptive categorization, this review critically examines each method's underlying assumptions, operational mechanisms, and suitability for diverse data characteristics, including high dimensionality, mixed feature types, class overlap, and noise. Key findings demonstrate that no single method universally outperforms others; optimal selection depends critically on dataset characteristics, classifier choice, and evaluation metrics. The paper concludes by identifying emerging research directions, including self-supervised learning for imbalance, diffusion-based generative oversampling, distribution-preserving resampling, knowledge distillation for imbalanced deployment, and the adaptation of foundation models to skewed distributions, offering practical guidelines for practitioners and a roadmap for future methodological development.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13518
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Data Balancing Strategies: A Systematic Survey of Resampling and Augmentation Methods
Yousefimehr, Behnam
Ghatee, Mehdi
Fazli, Javad
Ghaffari, Shervin
Rafei, Zahra
Seifi, Mohammad Amin
Tavakoli, Sajed
Nikahd, Abolfazl
Gandomani, Mahdi Razi
Orouji, Alireza
Kashani, Ramtin Mahmoudi
Heshmati, Sarina
Mousavi, Negin Sadat
Machine Learning
Artificial Intelligence
Imbalanced datasets, where one class significantly outnumbers others, remain a persistent challenge in machine learning, often biasing predictions toward the majority class and degrading classifier performance. This paper provides a comprehensive, systematic review of data balancing methods, extending beyond foundational oversampling techniques such as the Synthetic Minority Oversampling Technique (SMOTE) and its variants (e.g., Borderline SMOTE, K-Means SMOTE, and Safe-Level SMOTE) to encompass advanced adaptive methods (MWMOTE, AMDO), deep generative models (generative adversarial networks, variational autoencoders, and diffusion models), undersampling techniques (NearMiss, Tomek Links), combination/hybrid methods (SMOTE-ENN, SMOTE-Tomek, and SMOTE+OCSVM), ensemble strategies (SMOTEBoost, RUSBoost, Balanced Random Forest, and One-Sided Selection), and specialized approaches for multi-label and clustered data. Beyond descriptive categorization, this review critically examines each method's underlying assumptions, operational mechanisms, and suitability for diverse data characteristics, including high dimensionality, mixed feature types, class overlap, and noise. Key findings demonstrate that no single method universally outperforms others; optimal selection depends critically on dataset characteristics, classifier choice, and evaluation metrics. The paper concludes by identifying emerging research directions, including self-supervised learning for imbalance, diffusion-based generative oversampling, distribution-preserving resampling, knowledge distillation for imbalanced deployment, and the adaptation of foundation models to skewed distributions, offering practical guidelines for practitioners and a roadmap for future methodological development.
title Data Balancing Strategies: A Systematic Survey of Resampling and Augmentation Methods
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.13518