Deep Clustering and Representation Learning that Preserves Geometric Structures

Lirong Wu, Zicheng Liu, Zelin Zang, Jun Xia, Siyuan Li, Stan Z. Li

Keywords: Deep Clustering, Manifold Representation Learning

Abstract: In this paper, we propose a novel framework for Deep Clustering and multimanifold Representation Learning (DCRL) that preserves the geometric structure of data. In the proposed DCRL framework, manifold clustering is done in the latent space guided by a clustering loss. To overcome the problem that clusteringoriented losses may deteriorate the geometric structure of embeddings in the latent space, an isometric loss is proposed for preserving intra-manifold structure locally and a ranking loss for inter-manifold structure globally. Experimental results on various datasets show that the DCRL framework leads to performances comparable to current state-of-the-art deep clustering algorithms, yet exhibits superior performance for manifold representation. Our results also demonstrate the importance and effectiveness of the proposed losses in preserving geometric structure in terms of visualization and performance metrics. The code is provided in the Supplementary Material.

One-sentence Summary: The proposed framework uses two principles, intra-manifold metric-preserving and inter-manifold metric rank-preserving to solve multi-manifold clustering problem effectively.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=jyYmZWrIhX