Disjoint Cluster

Disjoint cluster analysis focuses on partitioning data points into mutually exclusive groups, maximizing similarity within clusters and dissimilarity between them. Current research emphasizes developing efficient algorithms for large-scale datasets, particularly bipartite graphs and high-dimensional spaces, often employing techniques like autoencoders, spectral methods, and novel optimization strategies such as the Big Bang-Big Crunch algorithm. These advancements aim to improve clustering quality, scalability, and robustness to noise, with applications spanning diverse fields including social network analysis, recommendation systems, and bioinformatics. A key challenge remains balancing computational efficiency with the accurate identification of the optimal number of clusters.