Self-paced learning for anchor-based multi-view clustering: A progressive approach

In the field of multi-view clustering (MVC), the surge in data has led to a significant increase in both the number of samples and the complexity of feature spaces, posing considerable challenges to the domain. Traditional anchor-based clustering methods effectively reduce the time and space complexity of algorithms by selecting representative samples to reconstruct similarity matrices. However, these methods are susceptible to the influence of low-quality anchors. To address this issue, we propose a novel self-paced learning for anchor- based MVC method, termed MSPA. This approach begins by constructing an anchor alternative pool, a novel strategy for selecting anchors that captures both intra-view and inter-view structural information. Subsequently, the concept of self-paced learning (SPL) is employed to progressively integrate anchors of varying quality into the model learning process, thereby constructing an anchor graph. Finally, the K-Means algorithm is applied to the resulting feature matrix to infer the final clustering results. Comprehensive comparative analyses conducted on eight benchmark datasets demonstrate that our proposed method outperforms existing state-of-the-art MVC algorithms in terms of efficiency.