Deep Attention-guided Graph Clustering with Dual Self-supervision
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Pages (from-to) | 3296-3307 |
Number of pages | 13 |
Journal / Publication | IEEE Transactions on Circuits and Systems for Video Technology |
Volume | 33 |
Issue number | 7 |
Online published | 27 Dec 2022 |
Publication status | Published - Jul 2023 |
Link(s)
Abstract
Existing deep embedding clustering methods fail to sufficiently utilize the available off-the-shelf information from feature embeddings and cluster assignments, limiting their performance. 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 the auto-encoder and the 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 an informative 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 off-the-shelf information from the cluster assignments, we develop a dual self-supervision solution consisting of a soft self-supervision strategy with a Kullback-Leibler divergence loss and a hard self-supervision strategy with a pseudo supervision loss. Extensive experiments on nine benchmark datasets validate that our method consistently outperforms state-of-the-art methods. Especially, our method improves the ARI by more than 10.29% over the best baseline. The code will be publicly available at https://github.com/ZhihaoPENG-CityU/DAGC. © 2022 IEEE.
Research Area(s)
- Unsupervised learning, deep embedding clustering, feature fusion, self-supervision
Bibliographic Note
Research Unit(s) information for this publication is provided by the author(s) concerned.
Citation Format(s)
Deep Attention-guided Graph Clustering with Dual Self-supervision. / Peng, Zhihao; Liu, Hui; Jia, Yuheng et al.
In: IEEE Transactions on Circuits and Systems for Video Technology, Vol. 33, No. 7, 07.2023, p. 3296-3307.
In: IEEE Transactions on Circuits and Systems for Video Technology, Vol. 33, No. 7, 07.2023, p. 3296-3307.
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review