Collaborative Decision-Reinforced Self-Supervision for Attributed Graph Clustering

Attributed graph clustering aims to partition nodes of a graph structure into different groups. Recent works usually use variational graph autoencoder (VGAE) to make the node representations obey a specific distribution. Although they have shown promising results, how to introduce supervised informa...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transaction on neural networks and learning systems Ročník 34; číslo 12; s. 10851 - 10863
Hlavní autori:	Zhu, Pengfei, Li, Jialu, Wang, Yu, Xiao, Bin, Zhao, Shuai, Hu, Qinghua
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States IEEE 01.12.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Attributed graph clustering (AGC) Automatic generation control Classification Clustering Collaboration collaborative training Convolutional neural networks Decisions Graphical representations Labels Learning Machine learning Nodes Representation learning self-supervised learning Sorting Supervision Task analysis Training variational graph autoencoder (VGAE)
ISSN:	2162-237X, 2162-2388, 2162-2388
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	Attributed graph clustering aims to partition nodes of a graph structure into different groups. Recent works usually use variational graph autoencoder (VGAE) to make the node representations obey a specific distribution. Although they have shown promising results, how to introduce supervised information to guide the representation learning of graph nodes and improve clustering performance is still an open problem. In this article, we propose a Collaborative Decision-Reinforced Self-Supervision (CDRS) method to solve the problem, in which a pseudo node classification task collaborates with the clustering task to enhance the representation learning of graph nodes. First, a transformation module is used to enable end-to-end training of existing methods based on VGAE. Second, the pseudo node classification task is introduced into the network through multitask learning to make classification decisions for graph nodes. The graph nodes that have consistent decisions on clustering and pseudo node classification are added to a pseudo-label set, which can provide fruitful self-supervision for subsequent training. This pseudo-label set is gradually augmented during training, thus reinforcing the generalization capability of the network. Finally, we investigate different sorting strategies to further improve the quality of the pseudo-label set. Extensive experiments on multiple datasets show that the proposed method achieves outstanding performance compared with state-of-the-art methods. Our code is available at https://github.com/Jillian555/TNNLS_CDRS .
Bibliografia:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ISSN:	2162-237X 2162-2388 2162-2388
DOI:	10.1109/TNNLS.2022.3171583