Journal
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
Volume 34, Issue 9, Pages 6303-6312Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2021.3135460
Keywords
Clustering; data augmentation; dual variational autoencoder; mixture models; variational autoencoder (VAE); variational inference; von Mises-Fisher mixture model
Ask authors/readers for more resources
This article proposes a clustering method based on variational autoencoder with spherical latent embeddings. The method improves clustering accuracy by using the von Mises-Fisher mixture model prior and a dual VAE structure, and enhances model robustness through an augmented loss function.
In recent years, clustering methods based on deep generative models have received great attention in various unsupervised applications, due to their capabilities for learning promising latent embeddings from original data. This article proposes a novel clustering method based on variational autoencoder (VAE) with spherical latent embeddings. The merits of our clustering method can be summarized as follows. First, instead of considering the Gaussian mixture model (GMM) as the prior over latent space as in a variety of existing VAE-based deep clustering methods, the von Mises-Fisher mixture model prior is deployed in our method, leading to spherical latent embeddings that can explicitly control the balance between the capacity of decoder and the utilization of latent embedding in a principled way. Second, a dual VAE structure is leveraged to impose the reconstruction constraint for the latent embedding and its corresponding noise counterpart, which embeds the input data into a hyperspherical latent space for clustering. Third, an augmented loss function is proposed to enhance the robustness of our model, which results in a self-supervised manner through the mutual guidance between the original data and the augmented ones. The effectiveness of the proposed deep generative clustering method is validated through comparisons with state-of-the-art deep clustering methods on benchmark datasets. The source code of the proposed model is available at https://github.com/fwt-team/DSVAE.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available