研究人员推出了一种新颖的深度聚类框架FMMVCC，专为单变量时间序列数据设计。该框架利用了以其高效、线性复杂度的状态空间序列建模而闻名的Mamba架构，以捕捉长程时间依赖性。FMMVCC还融入了多视图自监督学习技术，包括时间掩码和增强，以发现标注有限数据中的结构。在15个基准数据集上的评估表明，FMMVCC在众多指标评估中超越了现有的最先进方法，取得了卓越的性能，并且平均排名最高。 AI
影响 引入了一种更有效的时间序列分析方法，有望改进异常检测和模式识别等应用。
排序理由 该集群包含一篇详细介绍新模型及其实验评估的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.07258v1 Announce Type: cross Abstract: In many realistic scenarios, large volumes of time series data are generated with limited or expensive annotations. This limitation makes supervised learning methods difficult to apply and leads to the use of unsupervised approach…
In many realistic scenarios, large volumes of time series data are generated with limited or expensive annotations. This limitation makes supervised learning methods difficult to apply and leads to the use of unsupervised approaches capable of discovering meaningful structures di…
In many realistic scenarios, large volumes of time series data are generated with limited or expensive annotations. This limitation makes supervised learning methods difficult to apply and leads to the use of unsupervised approaches capable of discovering meaningful structures di…