返回
Structure-aware deep clustering network based on contrastive learning
DOI:10.1016/j.neunet.2023.08.020.png)
摘要
En 中文
Recently, deep clustering has been extensively employed for various data mining tasks, and it can be divided into auto-encoder (AE)-based and graph neural networks (GNN)-based methods. However, existing AE-based methods fall short in effectively extracting structural information, while GNN suffer from smoothing and heterophily. Although methods that combine AE and GNN achieve impressive performance, there remains an inadequate balance between preserving the raw structure and exploring the underlying structure. Accordingly, we propose a novel network named Structure-Aware Deep Clustering network (SADC). Firstly, we compute the cumulative influence of non-adjacent nodes at multiple depths and, thus, enhance the adjacency matrix. Secondly, an enhanced graph auto-encoder is designed. Thirdly, the latent space of AE is endowed with the ability to perceive the raw structure during the learning process. Besides, we design self-supervised mechanisms to achieve co-optimization of node representation learning and topology learning. A new loss function is designed to preserve the inherent structure while also allowing for exploration of latent data structure. Extensive experiments on six benchmark datasets validate that our method outperforms state-of-the-art methods.(c) 2023 Elsevier Ltd. All rights reserved.
Keyword:
Deep clustering
Contrastive learning
Auto-encoder
Graph auto-encoder
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
Synergetic information bottleneck for joint multi-view and ensemble clustering
INFORMATION FUSION
IF15.5
A Survey of Clustering With Deep Learning: From the Perspective of Network Architecture
IEEE ACCESS
IF3.6
A cluster analysis of health behaviours and their relationship to mental health difficulties, life satisfaction and functioning in adolescents
PREVENTIVE MEDICINE
IF3.2

