Multi-level Graph Contrastive Prototypical Clustering

Yuchao Zhang, Yuan Yuan, Qi Wang

科研成果: 书/报告/会议事项章节会议稿件同行评审

1 引用 (Scopus)

摘要

Recently, graph neural networks (GNNs) have drawn a surge of investigations in deep graph clustering. Nevertheless, existing approaches predominantly are inclined to semantic-agnostic since GNNs exhibit inherent limitations in capturing global underlying semantic structures. Meanwhile, multiple objectives are imposed within one latent space, whereas representations from different granularities may presumably conflict with each other, yielding severe performance degradation for clustering. To this end, we propose a MultiLevel Graph Contrastive Prototypical Clustering (MLG-CPC) framework for end-to-end clustering. Specifically, a Prototype Discrimination (ProDisc) objective function is proposed to explicitly capture semantic information via cluster assignments. Moreover, to alleviate the issue of objectives conflict, we introduce to perceive representations of different granularities within individual feature-, prototypical-, and cluster-level spaces by the feature decorrelation, prototype contrast, and cluster space consistency respectively. Extensive experiments on four benchmarks demonstrate the superiority of the proposed MLG-CPC against the state-of-the-art graph clustering approaches.

源语言英语
主期刊名Proceedings of the 32nd International Joint Conference on Artificial Intelligence, IJCAI 2023
编辑Edith Elkind
出版商International Joint Conferences on Artificial Intelligence
4611-4619
页数9
ISBN(电子版)9781956792034
DOI
出版状态已出版 - 2023
活动32nd International Joint Conference on Artificial Intelligence, IJCAI 2023 - Macao, 中国
期限: 19 8月 202325 8月 2023

出版系列

姓名IJCAI International Joint Conference on Artificial Intelligence
2023-August
ISSN(印刷版)1045-0823

会议

会议32nd International Joint Conference on Artificial Intelligence, IJCAI 2023
国家/地区中国
Macao
时期19/08/2325/08/23

指纹

探究 'Multi-level Graph Contrastive Prototypical Clustering' 的科研主题。它们共同构成独一无二的指纹。

引用此