Online Unsupervised Multi-View Feature Selection with Adaptive Neighbors

Unsupervised feature selection has emerged as a significant and challenging issue in multi-view learning due to the need to process a large amount of unlabeled and high-dimensional multi-view data. Although numerous methods have been developed to this point, the majority of them are offline and have substantial computational and memory costs. Unlike previous work, we propose an Online Unsupervised Multi-View Feature Selection with Adaptive Neighbors (OUMVFSAN) method by exploring view-specific feature selection matrices and weights to handle the multi-view streaming data. Specifically, the proposed OUMVFSAN method naturally performs information fusion of different views guided through a consensus clustering indicator matrix to make feature selection matrices select more valuable features. Moreover, through processing multi-view streaming data by a buffering technique, OUMVFSAN reduces the computational and storage cost without sacrificing performance. We demonstrate the effectiveness and efficiency of the proposed OUMVFSAN with extensive experiments on eight multi-view datasets. It is worth noting that OUMVFSAN performs better than many state-of-the-art online and offline unsupervised multi-view feature selection methods.