Imbalance Learning

Imbalance learning tackles the challenge of building accurate machine learning models when datasets contain significantly unequal representation of different classes. Current research focuses on developing robust algorithms and model architectures, such as those incorporating adversarial training, spiking neural networks, and ensemble methods, to mitigate the bias towards majority classes and improve performance on under-represented minority classes. This field is crucial for applications where class imbalance is prevalent, such as medical diagnosis and natural language processing, enabling fairer and more reliable predictions in real-world scenarios. Addressing this imbalance is essential for improving the generalizability and fairness of machine learning models.

Papers

October 14, 2024

RICASSO: Reinforced Imbalance Learning with Class-Aware Self-Supervised Outliers Exposure
Xuan Zhang, Sin Chee Chin, Tingxuan Gao, Wenming Yang
Long Tailed Recognition Outlier Exposure Mixed Data Imbalance Learning Data Mixing

March 13, 2024

Iterative Online Image Synthesis via Diffusion Model for Imbalanced Classification
Shuhan Li, Yi Lin, Hao Chen, Kwang-Ting Cheng
Diffusion Model Image Synthesis Medical Image Classification Imbalanced Data Imbalanced Classification Imbalance Learning

February 7, 2024

Towards Improved Imbalance Robustness in Continual Multi-Label Learning with Dual Output Spiking Architecture (DOSA)
Sourav Mishra, Shirin Dora, Suresh Sundaram
Multi Label Federat\textbf{T}ed Cl\textbf{A}ss Continual Lea\textbf{R}nin\textbf{G Imbalance Learning

January 21, 2024

Majority or Minority: Data Imbalance Learning Method for Named Entity Recognition
Sota Nemoto, Shunsuke Kitada, Hitoshi Iyatomi
Natural Language Processing Machine Learning Model Entity Recognition Named Entity Recognition Machine Reading Comprehension Majority Rule Imbalance Learning Minority Inclusion

May 6, 2023

Rethinking Class Imbalance in Machine Learning
Ou Wu
Machine Learning Class Imbalance Data Imbalance Imbalance Learning Output Imbalance

April 25, 2023

Combining Adversaries with Anti-adversaries in Training
Xiaoling Zhou, Nan Yang, Ou Wu
Training Data Adversarial Training Adversarial Perturbation Multi Step Adversarial Attack Monotone Adversary Standard Adversarial Training Imbalance Learning Adversarial Direction

March 4, 2023

Investigating Group Distributionally Robust Optimization for Deep Imbalanced Learning: A Case Study of Binary Tabular Data Classification
Ismail. B. Mustapha, Shafaatunnur Hasan, Hatem S Y Nabbus, Mohamed Mostafa Ali Montaser, Sunday Olusanya Olatunji, Siti Maryam Shamsuddin
Case Study Robust Optimization Distributionally Robust Optimization Data Imbalance Tabular Data Classification Imbalance Learning Deep Imbalanced

December 28, 2022

Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data
Harsh Rangwani, Sumukh K Aithal, Mayank Mishra, R. Venkatesh Babu
Sharpness Aware Minimization Saddle Point Generalization Capability Class Loss Margin Based Class Imbalanced Data Imbalance Learning

November 15, 2022

Persian Emotion Detection using ParsBERT and Imbalanced Data Handling Approaches
Amirhossein Abaskohi, Nazanin Sabri, Behnam Bahrak
Emotion Recognition Opinion Mining Emotion Datasets Imbalance Learning Persian Speech

November 9, 2022

Discrimination and Class Imbalance Aware Online Naive Bayes
Maryam Badar, Marco Fisichella, Vasileios Iosifidis, Wolfgang Nejdl
Class Imbalance Group DIscrimination Instance Weighting Imbalance Learning

September 1, 2022

Effective Class-Imbalance learning based on SMOTE and Convolutional Neural Networks
Javad Hassannataj Joloudari, Abdolreza Marefat, Mohammad Ali Nematollahi, Solomon Sunday Oyelere, Sadiq Hussain
Convolutional Neural Network Imbalanced Data Persian Dataset Feature Normalization Synthetic Minority Oversampling Technique Imbalance Learning

June 25, 2022

Envelope imbalanced ensemble model with deep sample learning and local-global structure consistency
Fan Li, Xiaoheng Zhang, Yongming Li, Pin Wang
Ensemble Model Ensemble Method Ensemble Algorithm Envelope Tracking Imbalance Learning Speech Envelope Global Consistency

January 14, 2022

Imputing Missing Observations with Time Sliced Synthetic Minority Oversampling Technique
Andrew Baumgartner, Sevda Molani, Qi Wei, Jennifer Hadlock
Time Series Classification Imputation Method Time Series Imputation Partial Observation Irregular Time Series Synthetic Minority Oversampling Technique Imbalance Learning

Imbalance Learning

Papers

RICASSO: Reinforced Imbalance Learning with Class-Aware Self-Supervised Outliers Exposure

Iterative Online Image Synthesis via Diffusion Model for Imbalanced Classification

Towards Improved Imbalance Robustness in Continual Multi-Label Learning with Dual Output Spiking Architecture (DOSA)

Majority or Minority: Data Imbalance Learning Method for Named Entity Recognition

Rethinking Class Imbalance in Machine Learning

Combining Adversaries with Anti-adversaries in Training

Investigating Group Distributionally Robust Optimization for Deep Imbalanced Learning: A Case Study of Binary Tabular Data Classification

Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data

Persian Emotion Detection using ParsBERT and Imbalanced Data Handling Approaches

Discrimination and Class Imbalance Aware Online Naive Bayes

Effective Class-Imbalance learning based on SMOTE and Convolutional Neural Networks

Envelope imbalanced ensemble model with deep sample learning and local-global structure consistency

Imputing Missing Observations with Time Sliced Synthetic Minority Oversampling Technique