Authors
Wenxuan Tu, Sihang Zhou, Xinwang Liu, Xifeng Guo, Zhiping Cai, En Zhu, Jieren Cheng
Publication date
2021/5/18
Journal
Proceedings of the AAAI Conference on Artificial Intelligence
Volume
35
Issue
11
Pages
9978-9987
Description
Deep clustering is a fundamental yet challenging task for data analysis. Recently we witness a strong tendency of combining autoencoder and graph neural networks to exploit structure information for clustering performance enhancement. However, we observe that existing literature 1) lacks a dynamic fusion mechanism to selectively integrate and refine the information of graph structure and node attributes for consensus representation learning; 2) fails to extract information from both sides for robust target distribution (ie,“groundtruth” soft labels) generation. To tackle the above issues, we propose a Deep Fusion Clustering Network (DFCN). Specifically, in our network, an interdependency learning-based Structure and Attribute Information Fusion (SAIF) module is proposed to explicitly merge the representations learned by an autoencoder and a graph autoencoder for consensus representation learning. Also, a reliable target distribution generation measure and a triplet self-supervision strategy, which facilitate cross-modality information exploitation, are designed for network training. Extensive experiments on six benchmark datasets have demonstrated that the proposed DFCN consistently outperforms the state-of-the-art deep clustering methods.
Total citations
Scholar articles
W Tu, S Zhou, X Liu, X Guo, Z Cai, E Zhu, J Cheng - Proceedings of the AAAI Conference on Artificial …, 2021