From Node Embedding To Community Embedding : A Hyperbolic Approach

Code

• github.com/drewwilimitis/hyperbolic-learning
  pytorch★ 0
• github.com/tgeral68/HyperbolicGraphAndGMM
  pytorch★ 0

Abstract

Detecting communities on graphs has received significant interest in recent literature. Current state-of-the-art community embedding approach called ComE tackles this problem by coupling graph embedding with community detection. Considering the success of hyperbolic representations of graph-structured data in last years, an ongoing challenge is to set up a hyperbolic approach for the community detection problem. The present paper meets this challenge by introducing a Riemannian equivalent of ComE. Our proposed approach combines hyperbolic embeddings with Riemannian K-means or Riemannian mixture models to perform community detection. We illustrate the usefulness of this framework through several experiments on real-world social networks and comparisons with ComE and recent hyperbolic-based classification approaches.

Tasks

Reproductions