Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior

TL;DR

This paper introduces DS2CF-Net, a deep neural network that combines hierarchical coupled factorization with enriched priors and dual-graph learning to improve representation learning and clustering accuracy.

Contribution

It proposes a novel deep coupled factorization architecture with enriched priors and manifold structure preservation for hierarchical representation learning.

Findings

Achieves state-of-the-art clustering performance on real datasets.

Effectively captures deep hierarchical features and local manifold structures.

Enhances discriminative ability through label and structure constraints.

Abstract

Nonnegative matrix factorization is usually powerful for learning the "shallow" parts-based representation, but it clearly fails to discover deep hierarchical information within both the basis and representation spaces. In this paper, we technically propose a new enriched prior based Dual-constrained Deep Semi-Supervised Coupled Factorization Network, called DS2CF-Net, for learning the hierarchical coupled representations. To ex-tract hidden deep features, DS2CF-Net is modeled as a deep-structure and geometrical structure-constrained neural network. Specifically, DS2CF-Net designs a deep coupled factorization architecture using multi-layers of linear transformations, which coupled updates the bases and new representations in each layer. To improve the discriminating ability of learned deep representations and deep coefficients, our network clearly considers enriching the supervised prior by the joint deep coefficients-regularized label prediction, and incorporates enriched prior information as additional label and structure constraints. The label constraint can enable the samples of the same label to have the same coordinate in the new feature space, while the structure constraint forces the coefficient matrices in each layer to be block-diagonal so that the enhanced prior using the self-expressive label propagation are more accurate. Our network also integrates the adaptive dual-graph learning to retain the local manifold structures of both the data manifold and feature manifold by minimizing the reconstruction errors in each layer. Extensive experiments on several real databases demonstrate that our DS2CF-Net can obtain state-of-the-art performance for representation learning and clustering.