Adaptive Attribute and Structure Subspace Clustering Network

TL;DR

This paper introduces AASSC-Net, a novel deep clustering model that adaptively fuses attribute and structure information via an attention mechanism, significantly improving clustering performance.

Contribution

The paper proposes a new deep clustering network that simultaneously models attribute and structure information with an adaptive fusion approach, enhancing clustering accuracy.

Findings

Outperforms state-of-the-art clustering methods on benchmark datasets.

Demonstrates the effectiveness of adaptive graph fusion in clustering.

Provides comprehensive ablation studies validating module contributions.

Abstract

Deep self-expressiveness-based subspace clustering methods have demonstrated effectiveness. However, existing works only consider the attribute information to conduct the self-expressiveness, which may limit the clustering performance. In this paper, we propose a novel adaptive attribute and structure subspace clustering network (AASSC-Net) to simultaneously consider the attribute and structure information in an adaptive graph fusion manner. Specifically, we first exploit an auto-encoder to represent input data samples with latent features for the construction of an attribute matrix. We also construct a mixed signed and symmetric structure matrix to capture the local geometric structure underlying data samples. Then, we perform self-expressiveness on the constructed attribute and structure matrices to learn their affinity graphs separately. Finally, we design a novel attention-based fusion module to adaptively leverage these two affinity graphs to construct a more discriminative affinity graph. Extensive experimental results on commonly used benchmark datasets demonstrate that our AASSC-Net significantly outperforms state-of-the-art methods. In addition, we conduct comprehensive ablation studies to discuss the effectiveness of the designed modules. The code will be publicly available at https://github.com/ZhihaoPENG-CityU.