FastCentNN: Accelerating Centroid Neural Network with Entropy Proxy
Provides a practical drop-in replacement for CentNN with a configurable speed-stability trade-off, benefiting users of unsupervised competitive learning algorithms.
FastCentNN accelerates Centroid Neural Network by introducing an early splitting strategy based on centroid movement per epoch, reducing runtime by up to 16% on synthetic 2D datasets and about 5% on high-dimensional datasets while maintaining comparable clustering quality.
Centroid neural network (CentNN) is an unsupervised competitive learning algorithm in which centroid splitting is triggered only after strict local stabilization, often leading to prolonged low-movement training phases before model expansion. This report proposes FastCentNN, an accelerated variant that addresses this inefficiency by introducing an early splitting strategy based on the total centroid movement per epoch, which serves as a training entropy proxy. As a result, FastCentNN reduces unnecessary reassignment epochs while preserving the original winner-loser learning dynamics. FastCentNN supports both absolute and stage-relative movement thresholds, allowing the splitting criterion to remain either fixed or adaptive throughout training. Experiments on some benchmark datasets show that FastCentNN consistently achieves clustering quality comparable to CentNN while reducing runtime by up to 16% on synthetic 2D datasets and about 5% on high-dimensional datasets. FastCentNN therefore provides a practical and efficient drop-in replacement for CentNN, retaining its online adaptive learning behavior while offering a simple and interpretable speed-stability trade-off through configurable splitting thresholds.