Manifold Adaptive Multiple Kernel K-Means for Clustering
This work addresses clustering accuracy for data analysis applications, but it is incremental as it builds upon existing multiple kernel k-means methods.
The paper tackled the problem of insufficient consideration of local manifold structure in multiple kernel k-means clustering by adopting manifold adaptive kernels, resulting in improved performance over state-of-the-art baselines on various datasets.
Multiple kernel methods based on k-means aims to integrate a group of kernels to improve the performance of kernel k-means clustering. However, we observe that most existing multiple kernel k-means methods exploit the nonlinear relationship within kernels, whereas the local manifold structure among multiple kernel space is not sufficiently considered. In this paper, we adopt the manifold adaptive kernel, instead of the original kernel, to integrate the local manifold structure of kernels. Thus, the induced multiple manifold adaptive kernels not only reflect the nonlinear relationship but also the local manifold structure. We then perform multiple kernel clustering within the multiple kernel k-means clustering framework. It has been verified that the proposed method outperforms several state-of-the-art baseline methods on a variety of data sets.