Fast Multiview Semi-Supervised Classification With Optimal Bipartite Graph

Abstract

As data collection becomes increasingly facile and descriptions of data grow more diverse, exploring heterogeneous multiview data is becoming essential. Extracting valuable insights from vast multiview datasets is profoundly meaningful which can leverage the diversity of multiple features to improve classification accuracy. As is well-known, semi-supervised learning (SSL) utilizes limited set of labeled samples to train models when addressing label scarcity. However, although the existing multiview semi-supervised algorithms can accomplish classification task, they often struggle with high complexity problem and lack interpretability, more transparent, and low-complexity approaches are worth studying. Besides, the interplay between graph structure and multiview consistency makes a deeper understanding of underlying data patterns but challenges persist in optimizing graph and ensuring scalability. In this article, we propose a fast multiview semi-supervised algorithm based on anchor graph (BGFMS), which improves the classification performance. It could significantly reduce the computational complexity by converting the label prediction of the original data into the forecast for few anchor points and avoids the additional processing procedure. Extensive experimental results on synthetic dataset and different real datasets validate the effectiveness and efficiency of our algorithm.