New RGCN method tackles graph clustering with missing data

Researchers have developed a new Robust Graph Clustering Network (RGCN) designed to handle graphs with missing node attributes and structural links. This method addresses limitations of existing approaches that impute data before clustering, which can suffer from error propagation and blurred cluster boundaries. RGCN employs a dual-branch imputation strategy to mitigate interference and enhance data recovery, a multi-hyperspherical mixture prior for improved cluster compactness and separability, and a boundary-aware contrastive enhancement objective to correct imputation bias. Experiments show RGCN outperforms current state-of-the-art methods on real-world datasets with various missing data patterns. AI

IMPACT Introduces a novel method for graph clustering that could improve performance in datasets with incomplete attribute and structural information.

RANK_REASON The cluster contains a research paper detailing a novel method for graph clustering with missing data. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• Connected Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• IArxiv Recommender
• Influence Flower
• Litmaps
• ScienceCast
• scite Smart Citations

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →