用熵代理加速聚类中心分裂，提升无监督学习效率。
FastCentNN: Accelerating Centroid Neural Network with Entropy Proxy
- 以每轮中心移动总量作为熵代理，提前触发聚类中心分裂。
- 在保持原有学习机制下，合成2D数据上提速16%，高维数据上提速5%。
- 支持固定或自适应阈值，适合需要快速收敛的在线学习场景。
Centroid神经网络（CentNN）是一种无监督竞争学习算法，其聚类中心仅在局部稳定后才分裂，常导致长时间低移动训练阶段。本文提出FastCentNN，通过引入基于每轮中心移动总量的早期分裂策略（作为训练熵代理），有效减少不必要的重新分配周期，同时保留原始的胜者-败者学习动态。FastCentNN支持绝对和阶段相对移动阈值，使分裂准则可固定或自适应。在多个基准数据集上的实验表明，FastCentNN在聚类质量与原版CentNN相当的前提下，合成2D数据上运行时间减少最多16%，高维数据上约5%。该方法为CentNN提供了无需修改架构的高效替代方案，兼具在线自适应能力与可配置的速度-稳定性权衡。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。