EUVIMEDEUVIMED entdecken
Crossref

Attribute-Missing Graph Clustering Network

Wenxuan Tu, Renxiang Guan, Sihang Zhou, Chuan Ma, Xin Peng, Zhiping Cai, Zhe Liu, Jieren Cheng, Xinwang Liu

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (14) · 15392-15401

DOI: 10.1609/aaai.v38i14.29464 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Wenxuan Tu und 8 weiteren Autor:innen. Die Arbeit wurde bisher 65-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep clustering with attribute-missing graphs, where only a subset of nodes possesses complete attributes while those of others are missing, is an important yet challenging topic in various practical applications. It has become a prevalent learning paradigm in existing studies to perform data imputation first and subsequently conduct clustering using the imputed information. However, these ``two-stage" methods disconnect the clustering and imputation processes, preventing the model from effectively learning clustering-friendly graph embedding. Furthermore, they are not tailored for clustering tasks, leading to inferior clustering results. To solve these issues, we propose a novel Attribute-Missing Graph Clustering (AMGC) method to alternately promote clustering and imputation in a unified framework, where we iteratively produce the clustering-enhanced nearest neighbor information to conduct the data imputation process and utilize the imputed information to implicitly refine the clustering distribution through model optimization. Specifically, in the imputation step, we take the learned clustering information as imputation prompts to help each attribute-missing sample gather highly correlated features within its clusters for data completion, such that the intra-class compactness can be improved. Moreover, to support reliable clustering, we maximize inter-class separability by conducting cost-efficient dual non-contrastive learning over the imputed latent features, which in turn promotes greater graph encoding capability for clustering sub-network. Extensive experiments on five datasets have verified the superiority of AMGC against competitors.

Zitieren

APA

Tu, W., Guan, R., Zhou, S., Ma, C., Peng, X., Cai, Z., Liu, Z., Cheng, J., & Liu, X. (2024). Attribute-Missing Graph Clustering Network. Proceedings of the AAAI Conference on Artificial Intelligence, 38(14), 15392-15401. https://doi.org/10.1609/aaai.v38i14.29464

Vancouver

Tu W, Guan R, Zhou S, Ma C, Peng X, Cai Z, et al. Attribute-Missing Graph Clustering Network. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(14):15392-15401. doi:10.1609/aaai.v38i14.29464

BibTeX
@article{Tu2024,
  author = {Tu, Wenxuan and Guan, Renxiang and Zhou, Sihang and Ma, Chuan and Peng, Xin and Cai, Zhiping and Liu, Zhe and Cheng, Jieren and Liu, Xinwang},
  title = {Attribute-Missing Graph Clustering Network},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {14},
  pages = {15392--15401},
  doi = {10.1609/aaai.v38i14.29464}
}
Kostenlos starten →