Generalized Clustering and Multi-Manifold Learning with Geometric Structure Preservation
This work addresses a specific issue in manifold clustering for generalized data, offering incremental improvements in preserving local and global geometric structures.
The paper tackles the problem of manifold-based clustering corrupting latent space structure by proposing a GCML framework with geometric structure preservation, achieving superior performance in qualitative and quantitative metrics compared to counterparts.
Though manifold-based clustering has become a popular research topic, we observe that one important factor has been omitted by these works, namely that the defined clustering loss may corrupt the local and global structure of the latent space. In this paper, we propose a novel Generalized Clustering and Multi-manifold Learning (GCML) framework with geometric structure preservation for generalized data, i.e., not limited to 2-D image data and has a wide range of applications in speech, text, and biology domains. In the proposed framework, manifold clustering is done in the latent space guided by a clustering loss. To overcome the problem that the clustering-oriented loss may deteriorate the geometric structure of the latent space, an isometric loss is proposed for preserving intra-manifold structure locally and a ranking loss for inter-manifold structure globally. Extensive experimental results have shown that GCML exhibits superior performance to counterparts in terms of qualitative visualizations and quantitative metrics, which demonstrates the effectiveness of preserving geometric structure.