前言
子空间聚类,用来identify constituent modes of variation in data with locally linear structure.
本文用于missing feature的聚类,propose a unified non-parametric generative framework for temporal subspace clustering to segment data drawn from a sequentially ordered union of subspaces that deals with the missing features in a principled way.
就是要利用时序信息
非参的话,还能自动确定子空间数目(即cluster数目)
intro
哦,本文专治missing feature的聚类,以及将free parameters给固定住,这样就不用交叉验证来确定参数了,而且减轻计算复杂度和参数灵敏度。
时域聚类的,不想看了。