Deep Clustering Analysis via Dual Variational Autoencoder With Spherical Latent Embeddings

Article Computer Science, Information Systems

DLRF-Net: A Progressive Deep Latent Low-Rank Fusion Network for Hierarchical Subspace Discovery

Zhao Zhang et al.

Summary: The article proposes a novel strategy to investigate deep low-rank representation learning of images by introducing DLRF-Net model to refine principal features layer by layer, aiming to achieve more accurate features and subspaces.

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep embedding clustering based on contractive autoencoder

Bassoma Diallo et al.

Summary: This study explores the use of deep learning techniques for representation learning in document clustering. By utilizing contractive autoencoders and appending the Frobenius norm as a penalty term, a new deep embedding clustering framework (DECCA) is proposed, with its superiority confirmed on six real-world datasets.

NEUROCOMPUTING (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Simple, Scalable, and Stable Variational Deep Clustering

Lele Cao et al.

Summary: Deep clustering (DC) is the leading technique for unsupervised clustering, but it often faces challenges such as high operational costs, low scalability, and unstable results. This paper evaluates various DC variants in an industrial context and focuses on variational deep clustering (VDC) methods. By introducing algorithmic improvements, a novel clustering algorithm S3VDC is proposed, which outperforms the state-of-the-art on benchmark tasks and industrial datasets without ground truth labels. Additionally, the usability and interpretability of S3VDC are analytically evaluated.

MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2020, PT I (2021)

添加到收藏夹

Article Automation & Control Systems