Imbalanced Clustering

Imbalanced clustering addresses the challenge of clustering datasets where the sizes of different clusters vary significantly, a common issue in real-world data. Current research focuses on developing algorithms that mitigate the bias towards larger clusters exhibited by traditional methods, employing techniques like coresets for approximation, self-refined organizing maps for efficient streaming data handling, and optimal transport frameworks for deep imbalanced clustering. These advancements aim to improve the accuracy and efficiency of clustering algorithms on imbalanced data, impacting various fields by enabling more robust analysis of datasets with naturally uneven class distributions.