Deep Clustering via Distribution Learning
This work addresses a theoretical gap in deep clustering for researchers, though it appears incremental as it builds on existing distribution learning methods.
The paper tackles the lack of theoretical analysis linking clustering and distribution learning in deep clustering by providing a theoretical framework and introducing Monte-Carlo Marginalization for Clustering, which integrates into DCDL to achieve promising results compared to state-of-the-art methods on popular datasets.
Distribution learning finds probability density functions from a set of data samples, whereas clustering aims to group similar data points to form clusters. Although there are deep clustering methods that employ distribution learning methods, past work still lacks theoretical analysis regarding the relationship between clustering and distribution learning. Thus, in this work, we provide a theoretical analysis to guide the optimization of clustering via distribution learning. To achieve better results, we embed deep clustering guided by a theoretical analysis. Furthermore, the distribution learning method cannot always be directly applied to data. To overcome this issue, we introduce a clustering-oriented distribution learning method called Monte-Carlo Marginalization for Clustering. We integrate Monte-Carlo Marginalization for Clustering into Deep Clustering, resulting in Deep Clustering via Distribution Learning (DCDL). Eventually, the proposed DCDL achieves promising results compared to state-of-the-art methods on popular datasets. Considering a clustering task, the new distribution learning method outperforms previous methods as well.