8000 GitHub - ZPGuiGroupWhu/TSCGC: A Topological and Semantic Contrastive Graph Clustering (TSCGC) model. It fuses original graph view, augmented graph view, and hypergraph view.
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

A Topological and Semantic Contrastive Graph Clustering (TSCGC) model. It fuses original graph view, augmented graph view, and hypergraph view.

Notifications You must be signed in to change notification settings

ZPGuiGroupWhu/TSCGC

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 

Repository files navigation

Topological and semantic contrastive graph clustering by Ricci curvature augmentation and hypergraph fusion

We propose a Topological and Semantic Contrastive Graph Clustering (TSCGC) model consisting of three learning components. The representation learning component augments original graph using Ricci curvature to preserve the cluster structure, and introduces hypergraph view to capture high-order relationships. Graph and hypergraph convolutional networks are used to encode the triple-view embeddings. Meanwhile, we develop a dual contrastive learning component to extract the topological and semantic information. It employs the pseudo clustering labels to guide positive sample selection and reduces the false negative samples. The self-supervised learning component is leveraged to align the three graph views.

image

About

A Topological and Semantic Contrastive Graph Clustering (TSCGC) model. It fuses original graph view, augmented graph view, and hypergraph view.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •  

Languages

0