Clustering with Adaptive Unsupervised Graph Convolution Network

Maria Al Jreidy, Joseph Constantin (), Fadi Dornaika (), Denis Hamad () and Vinh Truong Hoang ()
Additional contact information
Maria Al Jreidy: Lebanese University, LaRRIS, Faculty of Sciences
Joseph Constantin: Lebanese University, LaRRIS, Faculty of Sciences
Fadi Dornaika: University of the Basque Country UPV/EHU
Denis Hamad: LISIC-ULCO
Vinh Truong Hoang: Ho Chi Minh City Open University

Chapter Chapter 9 in Advances in Data Clustering, 2024, pp 157-179 from Springer

Abstract: Abstract Graph clustering has become one of the most challenging problems in Deep Learning in recent years. There are a number of methods for classifying nodes, including Graph Convolution Network (GCN), a deep semi-supervised learning method. In this chapter, based on GCN architecture, we propose a deep unsupervised learning scheme. The main contributions are as follows. First, the whole architecture is trained with two unsupervised learning losses based on kernelized features and spectral smoothness. Second, spectral smoothing uses an adaptive and additional graph matrix associated with the predicted soft cluster assignments (node representations) and adaptively integrates additional structure information during the learning phase. The adaptive fused graph used for loss of spectral smoothness takes into account structural information coming from both data features and node deep representations. With the proposed objective function, we are able to develop a powerful graph-based deep clustering. Experiments on four benchmark datasets show that our proposed unsupervised GCN provides better clustering performance than other Graph Neural Network-based techniques for most datasets.

Keywords: Deep clustering; Graph convolutional networks; Kernel k-means; Spectral clustering; Graph data; Adaptive graph fusion (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-981-97-7679-5_9

Ordering information: This item can be ordered from
http://www.springer.com/9789819776795

DOI: 10.1007/978-981-97-7679-5_9

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().