Deep Attention-guided Graph Clustering with Dual Self-supervision
Peng, Zhihao, Liu, Hui, Jia, Yuheng, Hou, Junhui
–arXiv.org Artificial Intelligence
Existing deep embedding clustering works only consider the deepest layer to learn a feature embedding and thus fail to well utilize the available discriminative information from cluster assignments, resulting performance limitation. To this end, we propose a novel method, namely deep attention-guided graph clustering with dual self-supervision (DAGC). Specifically, DAGC first utilizes a heterogeneity-wise fusion module to adaptively integrate the features of an auto-encoder and a graph convolutional network in each layer and then uses a scale-wise fusion module to dynamically concatenate the multi-scale features in different layers. Such modules are capable of learning a discriminative feature embedding via an attention-based mechanism. In addition, we design a distribution-wise fusion module that leverages cluster assignments to acquire clustering results directly. To better explore the discriminative information from the cluster assignments, we develop a dual self-supervision solution consisting of a soft self-supervision strategy with a triplet Kullback-Leibler divergence loss and a hard self-supervision strategy with a pseudo supervision loss. Extensive experiments validate that our method consistently outperforms state-of-the-art methods on six benchmark datasets. Especially, our method improves the ARI by more than 18.14% over the best baseline.
arXiv.org Artificial Intelligence
Nov-10-2021
- Country:
- Oceania > Australia
- North America
- United States
- Washington > King County
- Seattle (0.04)
- New York > New York County
- New York City (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Florida > Broward County
- Fort Lauderdale (0.04)
- California > Alameda County
- Oakland (0.04)
- Washington > King County
- Canada > British Columbia
- United States
- Europe
- Asia
- Middle East > Jordan (0.04)
- Macao (0.04)
- Taiwan > Taiwan Province
- Taipei (0.04)
- South Korea > Seoul
- Seoul (0.04)
- China
- Jiangsu Province > Nanjing (0.04)
- Hong Kong > Kowloon (0.04)
- Genre:
- Research Report > Promising Solution (0.68)
- Industry:
- Government (0.31)
- Technology: