A unified framework for discrete spectral clustering

摘要: Spectral clustering has been playing a vital role in various research areas. Most traditional spectral algorithms comprise two independent stages (i.e., first learning continuous labels and then rounding the learned into discrete ones), which may lead to severe information loss performance degradation. In this work, we study how achieve as well reliably generalize unseen data. We propose unified scheme jointly learns robust out-ofsample prediction functions. Specifically, explicitly enforce transformation on intermediate labels, leads tractable optimization problem with solution. Moreover, further compensate unreliability of integrate an adaptive module l2,p learn function for Extensive experiments conducted data sets have demonstrated superiority our proposal compared existing approaches.