提出新算法打破聚类模型训练中的性能瓶颈
Breaking the Reclustering Barrier in Centroid-based Deep Clustering
- 通过避免早期聚类过早固化，实现持续动态调整
- 在多个基准测试中稳定提升聚类效果，支持从零开始训练
- 结构简单但效果强，适合希望改进聚类性能的研究者
本文研究了基于中心点的深度聚类（DC）算法中一个关键现象：性能在初期快速提升后迅速饱和。实践中常采用周期性重聚类来应对，但我们证明该方法无法真正突破性能平台。我们称之为“重聚类障碍”，并实证分析其发生时机、内在机制，提出新算法BRB以突破该障碍。BRB避免对初始聚类过早固化，允许持续适应重新初始化的聚类目标，同时保持概念简洁。将BRB应用于主流的基于中心点的DC算法，结果表明：(1) 在广泛聚类基准上性能持续提升；(2) 支持从零开始训练；(3) 结合对比损失后，性能可媲美当前最先进算法。代码与预训练模型已开源。
原文摘要 · Abstract (English)
This work investigates an important phenomenon in centroid-based deep clustering (DC) algorithms: Performance quickly saturates after a period of rapid early gains. Practitioners commonly address early saturation with periodic reclustering, which we demonstrate to be insufficient to address performance plateaus. We call this phenomenon the "reclustering barrier" and empirically show when the reclustering barrier occurs, what its underlying mechanisms are, and how it is possible to Break the Reclustering Barrier with our algorithm BRB. BRB avoids early over-commitment to initial clusterings and enables continuous adaptation to reinitialized clustering targets while remaining conceptually simple. Applying our algorithm to widely-used centroid-based DC algorithms, we show that (1) BRB consistently improves performance across a wide range of clustering benchmarks, (2) BRB enables training from scratch, and (3) BRB performs competitively against state-of-the-art DC algorithms when combined with a contrastive loss. We release our code and pre-trained models at https://github.com/Probabilistic-and-Interactive-ML/breaking-the-reclustering-barrier .
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。